AI Wiki

User contributions for Walle

For Walle talk block log uploads logs abuse log
Search for contributionsExpandCollapse
⧼contribs-top⧽
⧼contribs-date⧽
(newest | oldest) View ( | older 500) (20 | 50 | 100 | 250 | 500)

21 May 2023

17 May 2023

  • 23:4423:44, 17 May 2023 diff hist +38,587‎ N Xlm-roberta-large model ‎ Created page with "{{Model infobox | hugging-face-uri = xlm-roberta-large | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, JAX, ONNX, Safetensors, Transformers | dataset = | language = 94 languages | paper = | license = arxiv:1911.02116, mit | related-to = xlm-roberta, exbert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, JAX, ONNX, Safetensors, Transformers, 94 languages, xlm-roberta, exbert, AutoTrain Compatible,..."
  • 23:4423:44, 17 May 2023 diff hist +38,536‎ N Xlm-roberta-base model ‎ Created page with "{{Model infobox | hugging-face-uri = xlm-roberta-base | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, JAX, ONNX, Safetensors, Transformers | dataset = | language = 94 languages | paper = | license = arxiv:1911.02116, mit | related-to = xlm-roberta, exbert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, JAX, ONNX, Safetensors, Transformers, 94 languages, xlm-roberta, exbert, AutoTrain Compatible, a..."
  • 23:4323:43, 17 May 2023 diff hist +38,770‎ N Nlpconnect/vit-gpt2-image-captioning model ‎ Created page with "{{Model infobox | hugging-face-uri = nlpconnect/vit-gpt2-image-captioning | creator = | type = Multimodal | task = Image-to-Text | library = PyTorch, Transformers | dataset = | language = | paper = | license = apache-2.0 | related-to = vision-encoder-decoder, image-captioning | all-tags = Image-to-Text, PyTorch, Transformers, doi:10.57967/hf/0222, vision-encoder-decoder, image-captioning, License: apache-2.0 | all-lang-tags = }} ==Model Description== ==Clone Model..."
  • 23:4223:42, 17 May 2023 diff hist +38,316‎ N Google/vit-base-patch16-224 model ‎ Created page with "{{Model infobox | hugging-face-uri = google/vit-base-patch16-224 | creator = | type = Computer Vision | task = Image Classification | library = PyTorch, TensorFlow, JAX, Transformers | dataset = imagenet-1k, imagenet-21k | language = | paper = | license = arxiv:2010.11929, arxiv:2006.03677, apache-2.0 | related-to = vit, vision, AutoTrain Compatible | all-tags = Image Classification, PyTorch, TensorFlow, JAX, Transformers, imagenet-1k, imagenet-21k, vit, vision, AutoT..."
  • 23:4223:42, 17 May 2023 diff hist +39,276‎ N Cardiffnlp/twitter-roberta-base-sentiment model ‎ Created page with "{{Model infobox | hugging-face-uri = cardiffnlp/twitter-roberta-base-sentiment | creator = | type = Natural Language Processing | task = Text Classification | library = PyTorch, TensorFlow, JAX, Transformers | dataset = tweet_eval | language = English | paper = | license = arxiv:2010.12421 | related-to = roberta | all-tags = Text Classification, PyTorch, TensorFlow, JAX, Transformers, tweet_eval, English, roberta, arxiv:2010.12421 | all-lang-tags = English }} ==Model..."
  • 23:4223:42, 17 May 2023 diff hist +39,623‎ N Cardiffnlp/twitter-roberta-base-sentiment-latest model ‎ Created page with "{{Model infobox | hugging-face-uri = cardiffnlp/twitter-roberta-base-sentiment-latest | creator = | type = Natural Language Processing | task = Text Classification | library = PyTorch, TensorFlow, Transformers | dataset = tweet_eval | language = English | paper = | license = arxiv:2202.03829 | related-to = roberta | all-tags = Text Classification, PyTorch, TensorFlow, Transformers, tweet_eval, English, roberta, arxiv:2202.03829 | all-lang-tags = English }} ==Model Des..."
  • 23:4223:42, 17 May 2023 diff hist +39,497‎ N T5-small model ‎ Created page with "{{Model infobox | hugging-face-uri = t5-small | creator = | type = Natural Language Processing | task = Translation, Text2Text Generation, Summarization | library = PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers | dataset = c4 | language = 5 languages | paper = | license = arxiv:1805.12471, arxiv:1708.00055, arxiv:1704.05426, arxiv:1606.05250, arxiv:1808.09121, arxiv:1810.12885, arxiv:1905.10044, arxiv:1910.09700, apache-2.0 | related-to = t5, AutoTrain Comp..."
  • 23:4223:42, 17 May 2023 diff hist +39,446‎ N T5-base model ‎ Created page with "{{Model infobox | hugging-face-uri = t5-base | creator = | type = Natural Language Processing | task = Translation, Text2Text Generation, Summarization | library = PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers | dataset = c4 | language = 4 languages | paper = | license = arxiv:1805.12471, arxiv:1708.00055, arxiv:1704.05426, arxiv:1606.05250, arxiv:1808.09121, arxiv:1810.12885, arxiv:1905.10044, arxiv:1910.09700, apache-2.0 | related-to = t5, AutoTrain Compa..."
  • 23:4223:42, 17 May 2023 diff hist +2,704‎ N Runwayml/stable-diffusion-v1-5 model ‎ Created page with "{{Model infobox | hugging-face-uri = runwayml/stable-diffusion-v1-5 | creator = | type = Multimodal | task = Text-to-Image | library = Diffusers | dataset = | language = | paper = | license = arxiv:2207.12598, arxiv:2112.10752, arxiv:2103.00020, arxiv:2205.11487, arxiv:1910.09700, creativeml-openrail-m | related-to = stable-diffusion, stable-diffusion-diffusers | all-tags = Text-to-Image, Diffusers, stable-diffusion, stable-diffusion-diffusers, arxiv:2207.12598, arxi..."
  • 23:4123:41, 17 May 2023 diff hist +38,756‎ N CompVis/stable-diffusion-safety-checker model ‎ Created page with "{{Model infobox | hugging-face-uri = CompVis/stable-diffusion-safety-checker | creator = | type = Computer Vision | task = | library = PyTorch, Transformers | dataset = | language = | paper = | license = arxiv:2103.00020, arxiv:1910.09700 | related-to = clip | all-tags = PyTorch, Transformers, clip, arxiv:2103.00020, arxiv:1910.09700 | all-lang-tags = }} ==Model Description== ==Clone Model Repository== <tabber> |-|HTTPS= <pre> #Be sure to have git-lfs installed (..."
  • 23:4123:41, 17 May 2023 diff hist +37,802‎ N Deepset/sentence bert model ‎ Created page with "{{Model infobox | hugging-face-uri = deepset/sentence_bert | creator = | type = Natural Language Processing | task = | library = PyTorch, JAX, Transformers | dataset = | language = | paper = | license = apache-2.0 | related-to = bert | all-tags = PyTorch, JAX, Transformers, bert, License: apache-2.0 | all-lang-tags = }} ==Model Description== ==Clone Model Repository== <tabber> |-|HTTPS= <pre> #Be sure to have git-lfs installed (https://git-lfs.com) git lfs instal..."
  • 23:4123:41, 17 May 2023 diff hist +38,300‎ N Allenai/scibert scivocab uncased model ‎ Created page with "{{Model infobox | hugging-face-uri = allenai/scibert_scivocab_uncased | creator = | type = Natural Language Processing | task = | library = PyTorch, JAX, Transformers | dataset = | language = English | paper = | license = | related-to = bert | all-tags = PyTorch, JAX, Transformers, English, bert | all-lang-tags = English }} ==Model Description== ==Clone Model Repository== <tabber> |-|HTTPS= <pre> #Be sure to have git-lfs installed (https://git-lfs.com) git lfs ins..."
  • 23:4123:41, 17 May 2023 diff hist +39,078‎ N Bigcode/santacoder model ‎ Created page with "{{Model infobox | hugging-face-uri = bigcode/santacoder | creator = | type = Natural Language Processing | task = Text Generation | library = PyTorch, Transformers | dataset = bigcode/the-stack | language = code | paper = | license = arxiv:1911.02150, arxiv:2207.14255, arxiv:2301.03988, bigcode-openrail-m | related-to = gpt2, Eval Results | all-tags = Text Generation, PyTorch, Transformers, bigcode/the-stack, code, gpt2, Eval Results, arxiv:1911.02150, arxiv:2207.14255..."
  • 23:4123:41, 17 May 2023 diff hist +38,440‎ N Roberta-large model ‎ Created page with "{{Model infobox | hugging-face-uri = roberta-large | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, JAX, ONNX, Safetensors, Transformers | dataset = bookcorpus, wikipedia | language = English | paper = | license = arxiv:1907.11692, arxiv:1806.02847, mit | related-to = roberta, exbert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, JAX, ONNX, Safetensors, Transformers, bookcorpus, wikipedia, English,..."
  • 23:4123:41, 17 May 2023 diff hist +38,389‎ N Roberta-base model ‎ Created page with "{{Model infobox | hugging-face-uri = roberta-base | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers | dataset = bookcorpus, wikipedia | language = English | paper = | license = arxiv:1907.11692, arxiv:1806.02847, mit | related-to = roberta, exbert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers, bookcorpus, wikipedia, English,..."
  • 23:4123:41, 17 May 2023 diff hist +40,785‎ N Deepset/roberta-base-squad2 model ‎ Created page with "{{Model infobox | hugging-face-uri = deepset/roberta-base-squad2 | creator = | type = Natural Language Processing | task = Question Answering | library = PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers | dataset = squad_v2 | language = English | paper = | license = cc-by-4.0 | related-to = roberta, Eval Results, AutoTrain Compatible | all-tags = Question Answering, PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers, squad_v2, English, roberta, Eval Res..."
  • 23:4023:40, 17 May 2023 diff hist +37,850‎ N Microsoft/resnet-50 model ‎ Created page with "{{Model infobox | hugging-face-uri = microsoft/resnet-50 | creator = | type = Computer Vision | task = Image Classification | library = PyTorch, TensorFlow, JAX, Transformers | dataset = imagenet-1k | language = | paper = | license = arxiv:1512.03385, apache-2.0 | related-to = resnet, vision, AutoTrain Compatible | all-tags = Image Classification, PyTorch, TensorFlow, JAX, Transformers, imagenet-1k, resnet, vision, AutoTrain Compatible, arxiv:1512.03385, License: apac..."
  • 23:4023:40, 17 May 2023 diff hist +37,866‎ N Microsoft/resnet-18 model ‎ Created page with "{{Model infobox | hugging-face-uri = microsoft/resnet-18 | creator = | type = Computer Vision | task = Image Classification | library = PyTorch, TensorFlow, Safetensors, Transformers | dataset = imagenet-1k | language = | paper = | license = arxiv:1512.03385, apache-2.0 | related-to = resnet, vision, AutoTrain Compatible | all-tags = Image Classification, PyTorch, TensorFlow, Safetensors, Transformers, imagenet-1k, resnet, vision, AutoTrain Compatible, arxiv:1512.0338..."
  • 23:4023:40, 17 May 2023 diff hist +40,076‎ N Helsinki-NLP/opus-mt-en-es model ‎ Created page with "{{Model infobox | hugging-face-uri = Helsinki-NLP/opus-mt-en-es | creator = | type = Natural Language Processing | task = Translation, Text2Text Generation | library = PyTorch, TensorFlow, JAX, Transformers | dataset = | language = English, Spanish | paper = | license = apache-2.0 | related-to = marian, AutoTrain Compatible | all-tags = Translation, PyTorch, TensorFlow, JAX, Transformers, English, Spanish, marian, text2text-generation, AutoTrain Compatible, License: a..."
  • 23:4023:40, 17 May 2023 diff hist +38,221‎ N Allenai/longformer-base-4096 model ‎ Created page with "{{Model infobox | hugging-face-uri = allenai/longformer-base-4096 | creator = | type = Natural Language Processing | task = | library = PyTorch, TensorFlow, Rust, Transformers | dataset = | language = English | paper = | license = arxiv:2004.05150, apache-2.0 | related-to = longformer | all-tags = PyTorch, TensorFlow, Rust, Transformers, English, longformer, arxiv:2004.05150, License: apache-2.0 | all-lang-tags = English }} ==Model Description== ==Clone Model Repos..."
  • 23:4023:40, 17 May 2023 diff hist +38,093‎ N Microsoft/layoutlmv3-base model ‎ Created page with "{{Model infobox | hugging-face-uri = microsoft/layoutlmv3-base | creator = | type = Natural Language Processing | task = | library = PyTorch, TensorFlow, ONNX, Transformers | dataset = | language = English | paper = | license = arxiv:2204.08387, cc-by-nc-sa-4.0 | related-to = layoutlmv3 | all-tags = PyTorch, TensorFlow, ONNX, Transformers, English, layoutlmv3, arxiv:2204.08387, License: cc-by-nc-sa-4.0 | all-lang-tags = English }} ==Model Description== ==Clone Mode..."
  • 23:4023:40, 17 May 2023 diff hist +38,287‎ N Microsoft/layoutlm-base-uncased model ‎ Created page with "{{Model infobox | hugging-face-uri = microsoft/layoutlm-base-uncased | creator = | type = Natural Language Processing | task = | library = PyTorch, TensorFlow, Transformers | dataset = | language = | paper = | license = arxiv:1912.13318 | related-to = layoutlm | all-tags = PyTorch, TensorFlow, Transformers, layoutlm, arxiv:1912.13318 | all-lang-tags = }} ==Model Description== ==Clone Model Repository== <tabber> |-|HTTPS= <pre> #Be sure to have git-lfs installed (..."
  • 23:3923:39, 17 May 2023 diff hist +38,580‎ N Facebook/hubert-large-ls960-ft model ‎ Created page with "{{Model infobox | hugging-face-uri = facebook/hubert-large-ls960-ft | creator = | type = Audio | task = Automatic Speech Recognition | library = PyTorch, TensorFlow, Transformers | dataset = libri-light, librispeech_asr | language = English | paper = | license = arxiv:2106.07447, apache-2.0 | related-to = hubert, speech, audio, hf-asr-leaderboard, Eval Results | all-tags = Automatic Speech Recognition, PyTorch, TensorFlow, Transformers, libri-light, librispeech_asr, En..."
  • 23:3923:39, 17 May 2023 diff hist +38,087‎ N SZTAKI-HLT/hubert-base-cc model ‎ Created page with "{{Model infobox | hugging-face-uri = SZTAKI-HLT/hubert-base-cc | creator = | type = Natural Language Processing | task = | library = PyTorch, TensorFlow, JAX, Transformers | dataset = common_crawl, wikipedia | language = Hungarian | paper = | license = apache-2.0 | related-to = bert | all-tags = PyTorch, TensorFlow, JAX, Transformers, common_crawl, wikipedia, Hungarian, bert, License: apache-2.0 | all-lang-tags = Hungarian }} ==Model Description== ==Clone Model Repo..."
  • 23:3923:39, 17 May 2023 diff hist +38,301‎ N Gpt2 model ‎ Created page with "{{Model infobox | hugging-face-uri = gpt2 | creator = | type = Natural Language Processing | task = Text Generation | library = PyTorch, TensorFlow, JAX, TF Lite, Rust, Safetensors, Transformers | dataset = | language = English | paper = | license = mit | related-to = gpt2, exbert | all-tags = Text Generation, PyTorch, TensorFlow, JAX, TF Lite, Rust, Safetensors, Transformers, English, doi:10.57967/hf/0039, gpt2, exbert, License: mit | all-lang-tags = English }} ==Mo..."
  • 23:3923:39, 17 May 2023 diff hist +38,587‎ N Gpt2-large model ‎ Created page with "{{Model infobox | hugging-face-uri = gpt2-large | creator = | type = Natural Language Processing | task = Text Generation | library = PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers | dataset = | language = English | paper = | license = arxiv:1910.09700, mit | related-to = gpt2 | all-tags = Text Generation, PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers, English, gpt2, arxiv:1910.09700, License: mit | all-lang-tags = English }} ==Model Descriptio..."
  • 23:3923:39, 17 May 2023 diff hist +38,568‎ N Google/electra-base-discriminator model ‎ Created page with "{{Model infobox | hugging-face-uri = google/electra-base-discriminator | creator = | type = Natural Language Processing | task = | library = PyTorch, TensorFlow, JAX, Rust, Transformers | dataset = | language = English | paper = | license = apache-2.0 | related-to = electra, pretraining | all-tags = PyTorch, TensorFlow, JAX, Rust, Transformers, English, electra, pretraining, License: apache-2.0 | all-lang-tags = English }} ==Model Description== ==Clone Model Reposi..."
  • 23:3923:39, 17 May 2023 diff hist +38,689‎ N Distilroberta-base model ‎ Created page with "{{Model infobox | hugging-face-uri = distilroberta-base | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers | dataset = openwebtext | language = English | paper = | license = arxiv:1910.01108, arxiv:1910.09700, apache-2.0 | related-to = roberta, exbert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers, openwebtext, English, roberta..."
  • 23:3823:38, 17 May 2023 diff hist +38,885‎ N Distilgpt2 model ‎ Created page with "{{Model infobox | hugging-face-uri = distilgpt2 | creator = | type = Natural Language Processing | task = Text Generation | library = PyTorch, TensorFlow, JAX, TF Lite, Rust, Core ML, Safetensors, Transformers | dataset = openwebtext | language = English | paper = | license = arxiv:1910.01108, arxiv:2201.08542, arxiv:2203.12574, arxiv:1910.09700, arxiv:1503.02531, apache-2.0 | related-to = gpt2, exbert, Eval Results, Carbon Emissions | all-tags = Text Generation, PyTor..."
  • 23:3823:38, 17 May 2023 diff hist +38,934‎ N Distilbert-base-uncased model ‎ Created page with "{{Model infobox | hugging-face-uri = distilbert-base-uncased | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers | dataset = bookcorpus, wikipedia | language = English | paper = | license = arxiv:1910.01108, apache-2.0 | related-to = distilbert, exbert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers, bookcorpus, wikipedia, Englis..."
  • 23:3823:38, 17 May 2023 diff hist +39,699‎ N Distilbert-base-uncased-finetuned-sst-2-english model ‎ Created page with "{{Model infobox | hugging-face-uri = distilbert-base-uncased-finetuned-sst-2-english | creator = | type = Natural Language Processing | task = Text Classification | library = PyTorch, TensorFlow, Rust, Safetensors, Transformers | dataset = sst2, glue | language = English | paper = | license = arxiv:1910.01108, apache-2.0 | related-to = distilbert, Eval Results | all-tags = Text Classification, PyTorch, TensorFlow, Rust, Safetensors, Transformers, sst2, glue, English, d..."
  • 23:3823:38, 17 May 2023 diff hist +39,499‎ N Distilbert-base-multilingual-cased model ‎ Created page with "{{Model infobox | hugging-face-uri = distilbert-base-multilingual-cased | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, ONNX, Safetensors, Transformers | dataset = wikipedia | language = 104 languages | paper = | license = arxiv:1910.01108, arxiv:1910.09700, apache-2.0 | related-to = distilbert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, ONNX, Safetensors, Transformers, wikipedia, 104 languages..."
  • 23:3823:38, 17 May 2023 diff hist +38,934‎ N Facebook/dino-vits8 model ‎ Created page with "{{Model infobox | hugging-face-uri = facebook/dino-vits8 | creator = | type = Multimodal | task = Feature Extraction | library = PyTorch, Transformers | dataset = imagenet-1k | language = | paper = | license = arxiv:2104.14294, apache-2.0 | related-to = vit, dino, vision | all-tags = Feature Extraction, PyTorch, Transformers, imagenet-1k, vit, dino, vision, arxiv:2104.14294, License: apache-2.0 | all-lang-tags = }} ==Model Description== ==Clone Model Repository== <..."
  • 23:3823:38, 17 May 2023 diff hist +39,009‎ N Facebook/dino-vitb16 model ‎ Created page with "{{Model infobox | hugging-face-uri = facebook/dino-vitb16 | creator = | type = Multimodal | task = Feature Extraction | library = PyTorch, TensorFlow, Transformers | dataset = imagenet-1k | language = | paper = | license = arxiv:2104.14294, apache-2.0 | related-to = vit, dino, vision | all-tags = Feature Extraction, PyTorch, TensorFlow, Transformers, imagenet-1k, vit, dino, vision, arxiv:2104.14294, License: apache-2.0 | all-lang-tags = }} ==Model Description== ==C..."
  • 23:3723:37, 17 May 2023 diff hist +38,641‎ N Microsoft/deberta-base model ‎ Created page with "{{Model infobox | hugging-face-uri = microsoft/deberta-base | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, Rust, Transformers | dataset = | language = English | paper = | license = arxiv:2006.03654, mit | related-to = deberta, deberta-v1 | all-tags = Fill-Mask, PyTorch, TensorFlow, Rust, Transformers, English, deberta, deberta-v1, arxiv:2006.03654, License: mit | all-lang-tags = English }} ==Model Description== =..."
  • 23:3723:37, 17 May 2023 diff hist +38,252‎ N Facebook/convnext-large-224 model ‎ Created page with "{{Model infobox | hugging-face-uri = facebook/convnext-large-224 | creator = | type = Computer Vision | task = Image Classification | library = PyTorch, TensorFlow, Transformers | dataset = imagenet-1k | language = | paper = | license = arxiv:2201.03545, apache-2.0 | related-to = convnext, vision, AutoTrain Compatible | all-tags = Image Classification, PyTorch, TensorFlow, Transformers, imagenet-1k, convnext, vision, AutoTrain Compatible, arxiv:2201.03545, License: ap..."
  • 23:3723:37, 17 May 2023 diff hist +38,201‎ N Facebook/convnext-base-224 model ‎ Created page with "{{Model infobox | hugging-face-uri = facebook/convnext-base-224 | creator = | type = Computer Vision | task = Image Classification | library = PyTorch, TensorFlow, Transformers | dataset = imagenet-1k | language = | paper = | license = arxiv:2201.03545, apache-2.0 | related-to = convnext, vision, AutoTrain Compatible | all-tags = Image Classification, PyTorch, TensorFlow, Transformers, imagenet-1k, convnext, vision, AutoTrain Compatible, arxiv:2201.03545, License: apa..."
  • 23:3723:37, 17 May 2023 diff hist +38,199‎ N Lengyue233/content-vec-best model ‎ Created page with "{{Model infobox | hugging-face-uri = lengyue233/content-vec-best | creator = | type = Natural Language Processing | task = | library = PyTorch, Transformers | dataset = | language = | paper = | license = mit | related-to = hubert | all-tags = PyTorch, Transformers, doi:10.57967/hf/0479, hubert, License: mit | all-lang-tags = }} ==Model Description== ==Clone Model Repository== <tabber> |-|HTTPS= <pre> #Be sure to have git-lfs installed (https://git-lfs.com) git lf..."
  • 23:3723:37, 17 May 2023 diff hist +36,998‎ N CIDAS/clipseg-rd64-refined model ‎ Created page with "{{Model infobox | hugging-face-uri = CIDAS/clipseg-rd64-refined | creator = | type = Computer Vision | task = Image Segmentation | library = PyTorch, Transformers | dataset = | language = | paper = | license = arxiv:2112.10003, apache-2.0 | related-to = clipseg, vision | all-tags = Image Segmentation, PyTorch, Transformers, clipseg, vision, arxiv:2112.10003, License: apache-2.0 | all-lang-tags = }} ==Model Description== ==Clone Model Repository== <tabber> |-|HTTPS..."
  • 23:3423:34, 17 May 2023 diff hist +38,480‎ N Openai/clip-vit-base-patch32 model ‎ Created page with "{{Model infobox | hugging-face-uri = openai/clip-vit-base-patch32 | creator = | type = Computer Vision | task = Zero-Shot Image Classification | library = PyTorch, TensorFlow, JAX, Transformers | dataset = | language = | paper = | license = arxiv:2103.00020, arxiv:1908.04913 | related-to = clip, vision | all-tags = Zero-Shot Image Classification, PyTorch, TensorFlow, JAX, Transformers, clip, vision, arxiv:2103.00020, arxiv:1908.04913 | all-lang-tags = }} ==Model De..."
  • 23:3423:34, 17 May 2023 diff hist +38,456‎ N Openai/clip-vit-base-patch16 model ‎ Created page with "{{Model infobox | hugging-face-uri = openai/clip-vit-base-patch16 | creator = | type = Computer Vision | task = Zero-Shot Image Classification | library = PyTorch, JAX, Transformers | dataset = | language = | paper = | license = arxiv:2103.00020, arxiv:1908.04913 | related-to = clip, vision | all-tags = Zero-Shot Image Classification, PyTorch, JAX, Transformers, clip, vision, arxiv:2103.00020, arxiv:1908.04913 | all-lang-tags = }} ==Model Description== ==Clone Mod..."
  • 23:3423:34, 17 May 2023 diff hist +38,386‎ N Camembert-base model ‎ Created page with "{{Model infobox | hugging-face-uri = camembert-base | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, Safetensors, Transformers | dataset = oscar | language = French | paper = | license = arxiv:1911.03894, mit | related-to = camembert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, Safetensors, Transformers, oscar, French, camembert, AutoTrain Compatible, arxiv:1911.03894, License: mit | all-lang-tag..."
  • 23:3423:34, 17 May 2023 diff hist +39,245‎ N Bigscience/bloom-560m model ‎ Created page with "{{Model infobox | hugging-face-uri = bigscience/bloom-560m | creator = | type = Natural Language Processing | task = Text Generation | library = PyTorch, JAX, Safetensors, Transformers | dataset = | language = 48 languages | paper = | license = arxiv:1909.08053, arxiv:2110.02861, arxiv:2108.12409, bigscience-bloom-rail-1.0 | related-to = bloom | all-tags = Text Generation, PyTorch, JAX, Safetensors, Transformers, 48 languages, bloom, arxiv:1909.08053, arxiv:2110.02861..."
  • 23:3323:33, 17 May 2023 diff hist +38,390‎ N Google/bert uncased L-2 H-128 A-2 model ‎ Created page with "{{Model infobox | hugging-face-uri = google/bert_uncased_L-2_H-128_A-2 | creator = | type = Natural Language Processing | task = | library = PyTorch, JAX, Transformers | dataset = | language = | paper = | license = arxiv:1908.08962, apache-2.0 | related-to = bert | all-tags = PyTorch, JAX, Transformers, bert, arxiv:1908.08962, License: apache-2.0 | all-lang-tags = }} ==Model Description== ==Clone Model Repository== <tabber> |-|HTTPS= <pre> #Be sure to have git-lf..."
  • 23:3323:33, 17 May 2023 diff hist +37,857‎ N Prajjwal1/bert-tiny model ‎ Created page with "{{Model infobox | hugging-face-uri = prajjwal1/bert-tiny | creator = | type = Natural Language Processing | task = | library = PyTorch, Transformers | dataset = | language = English | paper = | license = arxiv:1908.08962, arxiv:2110.01518, mit | related-to = BERT, MNLI, NLI, transformer, pre-training | all-tags = PyTorch, Transformers, English, BERT, MNLI, NLI, transformer, pre-training, arxiv:1908.08962, arxiv:2110.01518, License: mit | all-lang-tags = English }} =..."
  • 23:3323:33, 17 May 2023 diff hist +38,616‎ N Bert-base-uncased model ‎ Created page with "{{Model infobox | hugging-face-uri = bert-base-uncased | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers | dataset = bookcorpus, wikipedia | language = English | paper = | license = arxiv:1810.04805, apache-2.0 | related-to = bert, exbert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers, bookcorpus, wikipedia, English, bert, exb..."
  • 23:3323:33, 17 May 2023 diff hist +39,143‎ N Bert-base-multilingual-cased model ‎ Created page with "{{Model infobox | hugging-face-uri = bert-base-multilingual-cased | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, JAX, Safetensors, Transformers | dataset = wikipedia | language = 104 languages | paper = | license = arxiv:1810.04805, apache-2.0 | related-to = bert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, JAX, Safetensors, Transformers, wikipedia, 104 languages, bert, AutoTrain Compatible, ar..."
  • 23:3323:33, 17 May 2023 diff hist +38,511‎ N Bert-base-chinese model ‎ Created page with "{{Model infobox | hugging-face-uri = bert-base-chinese | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, JAX, Safetensors, Transformers | dataset = | language = Chinese | paper = | license = arxiv:1810.04805 | related-to = bert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, JAX, Safetensors, Transformers, Chinese, bert, AutoTrain Compatible, arxiv:1810.04805 | all-lang-tags = Chinese }} ==Model De..."
  • 23:3323:33, 17 May 2023 diff hist +38,502‎ N Bert-base-cased model ‎ Created page with "{{Model infobox | hugging-face-uri = bert-base-cased | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, JAX, Safetensors, Transformers | dataset = bookcorpus, wikipedia | language = English | paper = | license = arxiv:1810.04805, apache-2.0 | related-to = bert, exbert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, JAX, Safetensors, Transformers, bookcorpus, wikipedia, English, bert, exbert, AutoTrain..."
  • 23:3223:32, 17 May 2023 diff hist +39,378‎ N Dslim/bert-base-NER model ‎ Created page with "{{Model infobox | hugging-face-uri = dslim/bert-base-NER | creator = | type = Natural Language Processing | task = Token Classification | library = PyTorch, TensorFlow, JAX, Safetensors, Transformers | dataset = conll2003 | language = English | paper = | license = arxiv:1810.04805, mit | related-to = bert, AutoTrain Compatible | all-tags = Token Classification, PyTorch, TensorFlow, JAX, Safetensors, Transformers, conll2003, English, bert, AutoTrain Compatible, arxiv:18..."
  • 23:3223:32, 17 May 2023 diff hist +38,939‎ N Facebook/bart-large model ‎ Created page with "{{Model infobox | hugging-face-uri = facebook/bart-large | creator = | type = Multimodal | task = Feature Extraction | library = PyTorch, TensorFlow, JAX, Rust, Transformers | dataset = | language = English | paper = | license = arxiv:1910.13461, apache-2.0 | related-to = bart | all-tags = Feature Extraction, PyTorch, TensorFlow, JAX, Rust, Transformers, English, bart, arxiv:1910.13461, License: apache-2.0 | all-lang-tags = English }} ==Model Description== ==Clone M..."
  • 23:3223:32, 17 May 2023 diff hist +41,735‎ N Facebook/bart-large-mnli model ‎ Created page with "{{Model infobox | hugging-face-uri = facebook/bart-large-mnli | creator = | type = Natural Language Processing | task = Zero-Shot Classification, Text Classification | library = PyTorch, JAX, Rust, Safetensors, Transformers | dataset = multi_nli | language = | paper = | license = arxiv:1910.13461, arxiv:1909.00161, mit | related-to = bart | all-tags = Zero-Shot Classification, PyTorch, JAX, Rust, Safetensors, Transformers, multi_nli, bart, text-classification, arxiv:1..."
  • 23:3223:32, 17 May 2023 diff hist +60,818‎ N Facebook/bart-large-cnn model ‎ Created page with "{{Model infobox | hugging-face-uri = facebook/bart-large-cnn | creator = | type = Natural Language Processing | task = Summarization, Text2Text Generation | library = PyTorch, TensorFlow, JAX, Rust, Transformers | dataset = cnn_dailymail | language = English | paper = | license = arxiv:1910.13461, mit | related-to = bart, Eval Results, AutoTrain Compatible | all-tags = Summarization, PyTorch, TensorFlow, JAX, Rust, Transformers, cnn_dailymail, English, bart, text2text-..."
  • 23:3223:32, 17 May 2023 diff hist +3,886‎ N Sentence-transformers/all-mpnet-base-v2 model ‎ Created page with "{{Model infobox | hugging-face-uri = sentence-transformers/all-mpnet-base-v2 | creator = | type = Natural Language Processing, Multimodal | task = Sentence Similarity, Feature Extraction | library = PyTorch, Sentence Transformers | dataset = s2orc, flax-sentence-embeddings/stackexchange_xml, MS Marco, gooaq, yahoo_answers_topics, code_search_net, search_qa, eli5, snli, multi_nli, wikihow, natural_questions, trivia_qa, embedding-data/sentence-compression, embedding-data/..."
  • 23:3223:32, 17 May 2023 diff hist +3,913‎ N Sentence-transformers/all-MiniLM-L6-v2 model ‎ Created page with "{{Model infobox | hugging-face-uri = sentence-transformers/all-MiniLM-L6-v2 | creator = | type = Natural Language Processing, Multimodal | task = Sentence Similarity, Feature Extraction | library = PyTorch, TensorFlow, Rust, Sentence Transformers | dataset = s2orc, flax-sentence-embeddings/stackexchange_xml, ms_marco, gooaq, yahoo_answers_topics, code_search_net, search_qa, eli5, snli, multi_nli, wikihow, natural_questions, trivia_qa, embedding-data/sentence-compression..."
  • 23:3123:31, 17 May 2023 diff hist +38,451‎ N Albert-base-v2 model ‎ Created page with "{{Model infobox | hugging-face-uri = albert-base-v2 | creator = | type = Natural Language Processing | task = Fill-Mask | library = PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers | dataset = bookcorpus, wikipedia | language = English | paper = | license = arxiv:1909.11942, apache-2.0 | related-to = albert, AutoTrain Compatible | all-tags = Fill-Mask, PyTorch, TensorFlow, JAX, Rust, Safetensors, Transformers, bookcorpus, wikipedia, English, albert, AutoTrain..."
  • 23:3123:31, 17 May 2023 diff hist +40,447‎ N Cambridgeltl/SapBERT-from-PubMedBERT-fulltext model ‎ Created page with "{{Model infobox | hugging-face-uri = cambridgeltl/SapBERT-from-PubMedBERT-fulltext | creator = | type = Multimodal | task = Feature Extraction | library = PyTorch, TensorFlow, JAX, Safetensors, Transformers | dataset = | language = English | paper = | license = arxiv:2010.11784, apache-2.0 | related-to = bert, biomedical, lexical semantics, bionlp, biology, science, embedding, entity linking | all-tags = Feature Extraction, PyTorch, TensorFlow, JAX, Safetensors, Trans..."

21 March 2023

  • 22:2922:29, 21 March 2023 diff hist +4,247‎ N Width ‎ Created page with "{{see also|Machine learning terms}} ==Width in Machine Learning== Width in machine learning refers to the number of neurons, or computational units, contained within a specific layer of a neural network. Neural networks are a class of machine learning algorithms that are designed to mimic the structure and function of the human brain, and they consist of interconnected layers of neurons. Width is an essential aspect of the architecture of a neural network, as it affects..." current
  • 22:2922:29, 21 March 2023 diff hist +3,720‎ N Wide model ‎ Created page with "{{see also|Machine learning terms}} ==Wide Models in Machine Learning== Wide models, also known as wide learning or ''wide & deep learning'', are a class of machine learning models that combine the strengths of both linear models and deep learning models. They were introduced by researchers at Google in a paper titled "Wide & Deep Learning for Recommender Systems" by Heng-Tze Cheng, Levent Koc, Jeremiah Harmsen, et al. in 2016. ==Motivation and Architecture== The primar..." current
  • 22:2922:29, 21 March 2023 diff hist +3,459‎ N User matrix ‎ Created page with "{{see also|Machine learning terms}} ==User Matrix in Machine Learning== In machine learning, a user matrix is a mathematical representation of users in a dataset, particularly in the context of collaborative filtering and recommendation systems. Collaborative filtering is a technique used to provide personalized recommendations by utilizing the preferences and behavior of multiple users. The user matrix is a vital component in model-based collaborative filtering methods,..." current
  • 22:2922:29, 21 March 2023 diff hist +3,324‎ N Upweighting ‎ Created page with "{{see also|Machine learning terms}} ==Upweighting in Machine Learning== Upweighting is a technique used in machine learning to assign higher importance or weights to certain data points or features during the training process. This method is particularly useful when dealing with imbalanced datasets or when attempting to emphasize specific aspects of the data. Upweighting can be applied in various machine learning algorithms, including supervised and unsupervised techniqu..." current
  • 22:2922:29, 21 March 2023 diff hist +3,966‎ N Uplift modeling ‎ Created page with "{{see also|Machine learning terms}} ==Uplift Modeling== Uplift modeling, also known as '''uplift prediction''' or '''treatment effect modeling''', is a technique in machine learning and statistics that focuses on estimating the impact of an intervention on a specific outcome of interest. This method is particularly useful in fields such as marketing, healthcare, and public policy, where it is crucial to identify and target the most responsive..." current
  • 22:2922:29, 21 March 2023 diff hist +3,452‎ N Undersampling ‎ Created page with "{{see also|Machine learning terms}} ==Overview== Undersampling is a technique used in machine learning to address the issue of imbalanced datasets. In this context, an imbalanced dataset refers to a dataset where the classes are not represented equally. This can lead to poor performance for certain machine learning algorithms, as they may be biased towards the majority class. Undersampling involves reducing the number of instances in the majority class, with the goal..." current
  • 22:2822:28, 21 March 2023 diff hist +2,891‎ N Unawareness (to a sensitive attribute) ‎ Created page with "{{see also|Machine learning terms}} ==Unawareness in Machine Learning== Unawareness in machine learning refers to the deliberate exclusion or ignorance of specific sensitive attributes during the process of model training and decision-making. Sensitive attributes are those that may potentially lead to unfair or discriminatory outcomes, such as race, gender, age, or sexual orientation. The primary goal of incorporating unawareness in machine learning is to ensure fairness..." current
  • 22:2822:28, 21 March 2023 diff hist +4,320‎ N Transfer learning ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Transfer learning is a subfield of machine learning that focuses on leveraging the knowledge gained from solving one problem and applying it to a different but related problem. The primary motivation behind transfer learning is to reduce the amount of time, computational resources, and data required to train models for new tasks by reusing the knowledge gained from previous tasks. In this article, we will discuss t..." current
  • 22:2822:28, 21 March 2023 diff hist +2,816‎ N Tower ‎ Created page with "{{see also|Machine learning terms}} ==Tower in Machine Learning== The term "tower" in machine learning typically refers to a specific arrangement of layers within a neural network architecture. The term is primarily used to describe architectures where multiple parallel branches are vertically stacked, allowing for a hierarchical structure that can help improve the model's performance and accuracy. ===Background=== Tower architectures were introduced as a way to address..." current
  • 22:2822:28, 21 March 2023 diff hist +3,938‎ N Tf.keras ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== '''tf.keras''' is a high-level neural networks API, integrated within the TensorFlow machine learning framework. Developed by the Google Brain Team, tf.keras is designed to facilitate the creation, training, and evaluation of deep learning models. It is designed for quick prototyping and is user-friendly, modular, and extensible. In this article, we explore the key features and components of tf.keras, its advantage..." current
  • 22:2822:28, 21 March 2023 diff hist +2,808‎ N Tf.Example ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the realm of machine learning, '''''tf.Example''''' is a standard data serialization format employed by the TensorFlow framework, which is an open-source library developed by the Google Brain Team. The primary purpose of ''tf.Example'' is to facilitate the storage and exchange of data across diverse machine learning pipelines. This data structure efficiently represents data as a collection of key-value pairs, ma..." current
  • 22:2822:28, 21 March 2023 diff hist +3,197‎ N Test set ‎ Created page with "{{see also|Machine learning terms}} ==Test Set in Machine Learning== ===Definition=== In the context of machine learning, the '''test set''' refers to a subset of data that is distinct from the data used for model training and validation. It is typically utilized to evaluate the performance and generalization capabilities of a machine learning model after the training and validation processes are complete. Test sets play a vital role in ensuring that a model can perf..." current
  • 22:2722:27, 21 March 2023 diff hist +2,639‎ N Temporal data ‎ Created page with "{{see also|Machine learning terms}} ==Temporal Data in Machine Learning== Temporal data, also known as time series data, refers to data containing time-dependent observations. These data points are collected at consistent time intervals, which can range from milliseconds to years. In the context of machine learning, temporal data is used to build models that can analyze and predict trends, patterns, and relationships over time. Time series analysis and forecasting are wi..." current
  • 22:2722:27, 21 March 2023 diff hist +3,112‎ N Target ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, the term '''target''' refers to the variable or outcome that a learning algorithm aims to predict, estimate, or classify. The target is also commonly referred to as a '''label''' or '''ground truth'''. Machine learning models utilize target data during the training phase to learn patterns, relationships, or rules, and subsequently generalize these findings to make predictions on un..." current
  • 22:2722:27, 21 March 2023 diff hist +3,681‎ N Summary ‎ Created page with "{{see also|Machine learning terms}} ==Summary in Machine Learning== In machine learning, a '''summary''' refers to the process of reducing a large dataset or model into a simplified representation, which retains the most essential information. This can be done through various methods, such as dimensionality reduction, model compression, and ensemble methods. Summarization is crucial for improving computational efficiency, enhancing interpretability, and mitigating overfi..." current
  • 22:2722:27, 21 March 2023 diff hist +3,576‎ N Structural risk minimization (SRM) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Structural Risk Minimization (SRM) is a fundamental concept in the field of machine learning and statistical learning theory, introduced by Vladimir Vapnik and Alexey Chervonenkis. It serves as a regularization principle that aims to minimize the risk of overfitting in a model by finding an optimal balance between the model's complexity and its ability to generalize to unseen data. In essence, SRM strives to st..." current
  • 22:2722:27, 21 March 2023 diff hist +3,339‎ N Step size ‎ Created page with "{{see also|Machine learning terms}} ==Definition== In machine learning, the '''step size''' (also known as learning rate or alpha) is a hyperparameter that determines the magnitude of the update applied to the weights of a model during optimization. Step size is a crucial factor in the training process, as it influences the model's convergence speed and its ability to reach the global minimum of the loss function. The step size is used in various optimization algorit..." current
  • 22:2722:27, 21 March 2023 diff hist +3,446‎ N Step ‎ Created page with "{{see also|Machine learning terms}} ==Definition of Step in Machine Learning== In the context of machine learning, a '''step''' typically refers to an iteration or a single pass through a specific part of the algorithm during the learning process. A step can involve various actions, such as updating model parameters, assessing the current model's performance, or executing a certain phase of the algorithm. Steps are often part of larger processes like training, validation..." current
  • 22:2722:27, 21 March 2023 diff hist +2,689‎ N Squared hinge loss ‎ Created page with "{{see also|Machine learning terms}} ==Squared Hinge Loss== Squared hinge loss, also known as the squared variant of the hinge loss, is a popular loss function in the field of machine learning and support vector machines (SVM). It is a modification of the standard hinge loss function that provides better convergence properties and smoothness, while still maintaining the ability to handle non-linear classification problems. The squared hinge loss function can be us..." current
  • 22:2622:26, 21 March 2023 diff hist +2,968‎ N Sparsity ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Sparsity, in the context of machine learning, refers to the phenomenon where only a small number of features or parameters have significant non-zero values in a model or dataset. This characteristic can be exploited to improve the efficiency and interpretability of machine learning models. The concept of sparsity has been applied in various areas, including feature selection, regularization, and sparse representati..." current
  • 22:2622:26, 21 March 2023 diff hist +2,858‎ N Shape (Tensor) ‎ Created page with "{{see also|Machine learning terms}} ==Definition== A '''shape''' in the context of machine learning and deep learning refers to the structure or dimensionality of a '''tensor''', which is a multi-dimensional array of numerical values. Tensors are the fundamental building blocks of many machine learning models and frameworks, such as TensorFlow and PyTorch. The shape of a tensor is characterized by the number of dimensions it has, known as its '''rank''', and the..." current
  • 22:2622:26, 21 March 2023 diff hist +3,260‎ N Serving ‎ Created page with "{{see also|Machine learning terms}} ==Serving in Machine Learning== Serving in machine learning refers to the process of deploying and utilizing a trained machine learning model to make predictions or decisions based on new input data. This process is an integral part of the machine learning pipeline, as it allows the machine learning models to be applied to real-world problems and provide value to users. The serving process typically follows the completion of the ..." current
  • 22:2622:26, 21 March 2023 diff hist +3,299‎ N Sensitive attribute ‎ Created page with "{{see also|Machine learning terms}} ==Sensitive Attribute in Machine Learning== Sensitive attributes, also known as protected attributes, are variables that carry the potential of causing unfair or biased outcomes in a machine learning algorithm. These attributes often relate to demographic information such as race, gender, age, religion, or disability, and may inadvertently contribute to discriminatory decisions or predictions when used inappropriate..." current
  • 22:2622:26, 21 March 2023 diff hist +4,243‎ N Semi-supervised learning ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Semi-supervised learning is a type of machine learning approach that combines elements of both supervised and unsupervised learning methods. It leverages a small amount of labeled data along with a larger volume of unlabeled data to train models. This article will provide an overview of semi-supervised learning, discuss its advantages and challenges, and present commonly used techniques. ==Motivation and Advantage..." current
  • 22:2622:26, 21 March 2023 diff hist +3,879‎ N Self-training ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Self-training, a form of semi-supervised learning, is an approach in machine learning that combines both labeled and unlabeled data to improve the performance of a model. In this method, an initial model is trained on a small set of labeled data, and then it iteratively refines itself by incorporating the predictions it generates for the unlabeled data. This article will discuss the key concepts, advantages, and ch..." current
  • 22:2522:25, 21 March 2023 diff hist +4,139‎ N Weighted Alternating Least Squares (WALS) ‎ Created page with "{{see also|Machine learning terms}} ==Weighted Alternating Least Squares (WALS)== Weighted Alternating Least Squares (WALS) is a widely-used optimization algorithm employed in the field of machine learning. It is particularly popular for addressing the matrix factorization problem, which is often used in collaborative filtering and recommendation systems. WALS iteratively refines the latent factors of the input data to minimize the error, while simultaneously applyin..." current
  • 22:2522:25, 21 March 2023 diff hist +3,694‎ N Wasserstein loss ‎ Created page with "{{see also|Machine learning terms}} ==Wasserstein Loss in Machine Learning== Wasserstein loss, also known as the Earth Mover's Distance (EMD), is a metric used in the field of machine learning, particularly in the training of Generative Adversarial Networks (GANs). Introduced by Martin Arjovsky, Soumith Chintala, and Léon Bottou in their 2017 paper "Wasserstein GAN," this loss function has become a popular choice for training GANs due to its stability and th..." current
  • 22:2522:25, 21 March 2023 diff hist +3,103‎ N Tensor size ‎ Created page with "{{see also|Machine learning terms}} ==Definition== In machine learning, '''tensor size''' refers to the dimensions of a tensor, which is a multi-dimensional data structure often used to represent and manipulate data in various mathematical operations. Tensors are the generalization of scalars, vectors, and matrices, with scalars being zero-dimensional tensors, vectors being one-dimensional tensors, and matrices being two-dimensional tensors. Tensor size, also known a..." current
  • 22:2522:25, 21 March 2023 diff hist +2,952‎ N Tensor shape ‎ Created page with "{{see also|Machine learning terms}} ==Tensor Shape in Machine Learning== Tensor shape is a fundamental concept in the field of machine learning, particularly in deep learning architectures, where tensors are used as the primary data structure for representing and processing multidimensional data. In this article, we will explore the meaning of tensor shape, its significance in machine learning, and some common operations performed on tensors. ===Definition and Backgroun..." current
  • 22:2522:25, 21 March 2023 diff hist +2,894‎ N Tensor rank ‎ Created page with "{{see also|Machine learning terms}} ==Definition of Tensor Rank== In the field of machine learning, tensors are multi-dimensional arrays that provide a mathematical framework to represent and manipulate data. The rank of a tensor, also known as its ''order'', refers to the number of dimensions or indices required to describe the tensor. Formally, the tensor rank is defined as the number of axes within a tensor. In other words, the tensor rank determines the complexit..." current
  • 22:2522:25, 21 March 2023 diff hist +3,412‎ N Tensor Processing Unit (TPU) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''Tensor Processing Unit (TPU)''' is a specialized type of hardware accelerator designed specifically for the efficient execution of machine learning tasks, particularly deep learning algorithms. TPUs were first introduced by Google in 2016 and have since become an essential component in the field of artificial intelligence (AI) and machine learning (ML) for their ability to perform high-throughput mathematical oper..." current
  • 22:2422:24, 21 March 2023 diff hist +3,362‎ N TensorFlow Serving ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== TensorFlow Serving is a flexible, high-performance serving system for machine learning models, designed for production environments. Developed by Google, it is part of the larger TensorFlow ecosystem, an open-source machine learning library used to develop, train, and deploy ML models. TensorFlow Serving provides a standardized interface for deploying and serving machine learning models, enabling easy integrati..." current
  • 22:2422:24, 21 March 2023 diff hist +3,419‎ N TensorFlow Playground ‎ Created page with "{{see also|Machine learning terms}} ==TensorFlow Playground== TensorFlow Playground is an interactive, web-based visualization tool for exploring and understanding neural networks. Developed by the TensorFlow team at Google, this tool allows users to visualize and manipulate neural networks in real-time, providing a deeper understanding of how these models work and their underlying principles. The TensorFlow Playground is an invaluable educational resource for those inte..." current
  • 22:2422:24, 21 March 2023 diff hist +3,251‎ N TensorFlow ‎ Created page with "{{see also|Machine learning terms}} ==Overview== TensorFlow is an open-source software library developed by the Google Brain team primarily for machine learning, deep learning, and numerical computation. It uses data flow graphs for computation, where each node represents a mathematical operation, and each edge represents a multi-dimensional data array (tensor) that flows between the nodes. TensorFlow provides a flexible platform for designing, training, and deployin..." current
  • 22:2422:24, 21 March 2023 diff hist +2,998‎ N TensorBoard ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== TensorBoard is an open-source, interactive visualization tool designed for machine learning experiments. Developed by the Google Brain team, TensorBoard is an integral component of the TensorFlow ecosystem, which facilitates the monitoring and analysis of model training processes. It provides users with graphical representations of various metrics, including model performance, variable distributions, and comput..." current
  • 22:2422:24, 21 March 2023 diff hist +3,865‎ N Tensor ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, a '''tensor''' is a mathematical object that generalizes the concepts of scalars, vectors, and matrices. Tensors are extensively used in machine learning and deep learning algorithms, particularly in the development and implementation of neural networks. They provide a flexible and efficient way to represent and manipulate data with multiple dimensions, allowing for the efficient execution of c..." current
  • 22:2422:24, 21 March 2023 diff hist +3,683‎ N TPU worker ‎ Created page with "{{see also|Machine learning terms}} ==Overview== A '''TPU worker''' refers to a specific type of hardware device known as a Tensor Processing Unit (TPU), which is utilized in the field of machine learning to accelerate the training and inference of deep neural networks. TPUs are application-specific integrated circuits (ASICs) developed by Google and optimized for their TensorFlow machine learning framework. TPU workers are designed to perform tensor computations..." current
  • 22:2422:24, 21 March 2023 diff hist +3,115‎ N TPU type ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a ''Tensor Processing Unit'' (TPU) is a specialized type of hardware designed to accelerate various operations in neural networks. TPUs, developed by Google, have gained significant traction in the deep learning community due to their ability to provide high-performance computation with reduced energy consumption compared to traditional GPUs or Central P..." current
  • 22:2322:23, 21 March 2023 diff hist +3,004‎ N TPU slice ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''TPU slice''' refers to a specific portion of a Tensor Processing Unit (TPU), which is a type of specialized hardware developed by Google to accelerate machine learning tasks. TPUs are designed to handle the computationally-intensive operations commonly associated with deep learning and neural networks, such as matrix multiplications and convolutions. TPU slices are integral components of the TPU archit..." current
  • 22:2322:23, 21 March 2023 diff hist +3,719‎ N TPU resource ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The TPU, or Tensor Processing Unit, is a specialized type of hardware developed by Google for the purpose of accelerating machine learning tasks, particularly those involving deep learning and artificial intelligence. TPUs are designed to deliver high performance with low power consumption, making them an attractive option for large-scale machine learning applications. ==Architecture and Design== ===Overview=== Th..." current
  • 22:2322:23, 21 March 2023 diff hist +3,213‎ N TPU node ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''Tensor Processing Unit (TPU) node''' is a specialized hardware accelerator designed to significantly accelerate machine learning workloads. Developed by Google, TPUs are optimized for tensor processing, which is the foundational mathematical operation in various machine learning frameworks such as TensorFlow. By providing dedicated hardware for these calculations, TPUs enable faster training and inference of m..." current
  • 22:2322:23, 21 March 2023 diff hist +2,995‎ N TPU master ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''TPU master''' in machine learning refers to the primary control unit of a Tensor Processing Unit (TPU), which is a specialized hardware accelerator designed to significantly speed up the execution of machine learning tasks. TPUs were developed by Google to improve the performance of deep learning algorithms and reduce their training and inference times. The TPU master coordinates the flow of data and instruc..." current
  • 22:2322:23, 21 March 2023 diff hist +3,296‎ N TPU device ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''Tensor Processing Unit (TPU)''' is a type of application-specific integrated circuit (ASIC) designed and developed by Google specifically for accelerating machine learning tasks. TPUs are custom-built hardware accelerators optimized to handle the computational demands of machine learning algorithms, particularly deep learning and neural networks. They provide significant performance improvements and en..." current
  • 22:2322:23, 21 March 2023 diff hist +3,669‎ N TPU chip ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''Tensor Processing Unit''' ('''TPU''') is a type of application-specific integrated circuit (ASIC) designed by Google specifically for accelerating machine learning workloads. TPUs are optimized for the computational demands of neural networks and are particularly efficient at performing operations with tensors, which are multi-dimensional arrays of data commonly used in machine learning applications. TPU..." current
  • 22:2222:22, 21 March 2023 diff hist +3,534‎ N TPU Pod ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a '''TPU Pod''' is a cluster of Tensor Processing Units (TPUs) designed to accelerate high-performance computation tasks. TPUs are specialized hardware accelerators developed by Google, specifically optimized for performing tensor-based mathematical operations commonly used in machine learning and deep learning algorithms. TPU Pods allow researchers and engineers to scale up their..." current
  • 22:2222:22, 21 March 2023 diff hist +3,422‎ N TPU ‎ Created page with "{{see also|Machine learning terms}} ==Overview== A '''Tensor Processing Unit (TPU)''' is a type of application-specific integrated circuit (ASIC) developed by Google for accelerating machine learning workloads. TPUs are designed to perform tensor computations efficiently, which are the foundational operations in machine learning algorithms, particularly deep learning models. They are optimized for handling large-scale matrix operations with low precision, enabling fa..." current
  • 01:1501:15, 21 March 2023 diff hist +4,348‎ N Self-supervised learning ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Self-supervised learning (SSL) is a subfield of machine learning that focuses on learning representations of data in an unsupervised manner by exploiting the structure and inherent properties of the data itself. This approach has gained significant traction in recent years, as it enables algorithms to learn useful features from large volumes of unlabeled data, thereby reducing the reliance on labeled datasets. The lear..." current
  • 01:1501:15, 21 March 2023 diff hist +4,400‎ N Selection bias ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Selection bias in machine learning refers to the phenomenon where the sample data used to train or evaluate a machine learning model does not accurately represent the underlying population or the target domain. This issue arises when the training data is collected or selected in a way that introduces systematic errors, which can lead to biased predictions or conclusions when the model is applied to real-world scena..." current
  • 01:1501:15, 21 March 2023 diff hist +3,710‎ N Scoring ‎ Created page with "{{see also|Machine learning terms}} ==Overview== In the field of machine learning, scoring refers to the process of evaluating a trained model's performance based on its ability to make predictions on a given dataset. The scoring process typically involves comparing the model's predictions to the actual or true values, also known as ground truth or targets. A variety of evaluation metrics are used to quantify the model's performance, with the choice of metric often d..." current
  • 01:1501:15, 21 March 2023 diff hist +3,467‎ N Scikit-learn ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== '''Scikit-learn''' is an open-source Python library designed for use in the field of machine learning. The library provides a wide range of machine learning algorithms, including those for classification, regression, clustering, dimensionality reduction, and model selection. Developed by a team of researchers and engineers, scikit-learn is built on top of the NumPy, SciPy, and matplotlib libraries,..." current
  • 01:1401:14, 21 March 2023 diff hist +3,041‎ N Scaling ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, scaling refers to the process of adjusting the range of input features or data points to a uniform scale. This normalization of data is an essential pre-processing step that enhances the performance and efficiency of machine learning algorithms by addressing issues of heterogeneity and uneven distribution of features. ==Importance of Scaling in Machine Learning== Scaling is a crit..." current
  • 01:1401:14, 21 March 2023 diff hist +3,027‎ N Scalar ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, a ''scalar'' refers to a single numerical value that can represent a quantity or measurement. Scalars play a crucial role in many aspects of machine learning algorithms, from representing weights and biases in neural networks to serving as input features or output labels in various machine learning models. This article will cover the definition, importance, and usage of scalars in machine learn..." current
  • 01:1401:14, 21 March 2023 diff hist +4,091‎ N Sampling bias ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Sampling bias in machine learning is a type of bias that occurs when the data used for training and testing a model does not accurately represent the underlying population. This can lead to a model that performs poorly in real-world applications, as it is not able to generalize well to the broader population. In this article, we will discuss the various causes and types of sampling bias, the consequences of samplin..." current
  • 01:1401:14, 21 March 2023 diff hist +2,611‎ N Root directory ‎ Created page with "{{see also|Machine learning terms}} ==Root Directory in Machine Learning== In the context of machine learning, the term "root directory" does not directly refer to a specific concept or technique. Instead, it is related to file and folder organization in computer systems, which is crucial for managing datasets, code, and resources for machine learning projects. In this article, we will discuss the concept of a root directory in the context of computer systems and how it..." current
  • 01:1401:14, 21 March 2023 diff hist +3,229‎ N Ridge regularization ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, regularization is a technique used to prevent overfitting and improve the generalization of models by adding a penalty term to the objective function. Ridge regularization, also known as L2 regularization or Tikhonov regularization, is a specific type of regularization that adds a squared L2-norm of the model parameters to the loss function. This article discusses the underlying principles of ridge..." current
  • 01:1401:14, 21 March 2023 diff hist +3,523‎ N Representation ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Representation in machine learning refers to the method by which a model captures and encodes the underlying structure, patterns, and relationships present in the input data. A suitable representation allows the model to learn and generalize from the data effectively, enabling it to make accurate predictions or perform other tasks. Representations can be hand-crafted features, which are based on expert knowledge, o..." current
  • 01:1301:13, 21 March 2023 diff hist +4,297‎ N Reporting bias ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Reporting bias in machine learning refers to a systematic distortion of the information used to train and evaluate machine learning models. This distortion arises when the data being used to train a model is influenced by factors that are not representative of the true underlying phenomenon. These factors can lead to an overestimation or underestimation of certain model predictions, ultimately affecting the performance..." current
  • 01:1301:13, 21 March 2023 diff hist +4,360‎ N Recommendation system ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''recommendation system''' in machine learning is a type of algorithm that provides personalized suggestions or recommendations to users, typically in the context of digital platforms such as e-commerce websites, streaming services, and social media platforms. These systems leverage various techniques from the fields of machine learning, data mining, and information retrieval to identify and rank items or conten..." current
  • 01:1301:13, 21 March 2023 diff hist +3,350‎ N Recall ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== '''Recall''' is a performance metric commonly used in machine learning and information retrieval to evaluate the effectiveness of classification and retrieval models. It is particularly useful when the cost of false negatives (failing to identify positive instances) is high. This article provides an in-depth understanding of the concept of recall, its mathematical formulation, and its relation to other performa..." current
  • 01:1301:13, 21 March 2023 diff hist +3,428‎ N Re-ranking ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Re-ranking, also known as rank refinement or re-scoring, is an essential technique in machine learning that aims to improve the quality of ranked results generated by a primary ranking model. It involves using a secondary model to adjust the initial ranking produced by the primary model, based on various features and criteria. Re-ranking is widely applied in diverse fields, such as information retrieval, natu..." current
  • 01:1301:13, 21 March 2023 diff hist +3,356‎ N Ranking ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, ranking refers to the process of sorting a set of items in a specific order based on their relevance, importance, or some other predefined criteria. This process has become increasingly important in a wide range of applications, such as information retrieval, recommendation systems, and natural language processing. By utilizing machine learning algorithms and models, ranking system..." current
  • 01:1301:13, 21 March 2023 diff hist +3,670‎ N Rank (ordinality) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, '''rank''' or '''ordinality''' refers to a specific type of data that represents a relative order or position among a set of items. Unlike continuous numerical data, which can take any value within a range, or categorical data, which consists of discrete values with no inherent order, ordinal data possesses an inherent order or ranking, but the intervals between the values are not necessarily consi..." current
  • 01:1201:12, 21 March 2023 diff hist +3,596‎ N Rank (Tensor) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, the term "rank" is commonly used in the context of tensor algebra. A tensor is a mathematical object that is a generalization of scalars, vectors, and matrices, and is used to represent complex data structures in various machine learning algorithms. The rank of a tensor refers to the number of dimensions or indices required to represent the tensor. ==Tensor Basics== ===Scalars, Vectors, and Matric..." current
  • 01:1201:12, 21 March 2023 diff hist +3,137‎ N Queue ‎ Created page with "{{see also|Machine learning terms}} ==Queue in Machine Learning== Queue, in the context of machine learning, refers to the use of a data structure known as a queue to store and manage data during the processing of machine learning tasks. Queues are data structures that follow the First-In-First-Out (FIFO) principle, meaning that elements are removed from the queue in the order they were inserted. Queues can be utilized in various stages of the machine learning proces..." current
  • 01:1201:12, 21 March 2023 diff hist +2,897‎ N Quantization ‎ Created page with "{{see also|Machine learning terms}} ==Quantization in Machine Learning== Quantization is a technique utilized in machine learning and deep learning to reduce the size of models and computational resources needed for their operation. The process entails approximating the continuous values of parameters, such as weights and activations, using a smaller, discrete set of values. Quantization is particularly useful in deploying models on resource-constrained devices,..." current
  • 01:1201:12, 21 March 2023 diff hist +3,727‎ N Quantile bucketing ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Quantile bucketing, also known as quantile binning or quantile-based discretization, is a technique in machine learning and data preprocessing that aims to transform continuous numeric features into discrete categories by partitioning the data distribution into intervals, with each interval containing an equal proportion of data points. This process improves the efficiency and interpretability of certain algori..." current
  • 01:1201:12, 21 March 2023 diff hist +3,310‎ N Quantile ‎ Created page with "{{see also|Machine learning terms}} ==Quantile in Machine Learning== A '''quantile''' is a statistical concept used in machine learning, which refers to the division of a data distribution into equal intervals. These intervals represent different portions of the data distribution and are used for various statistical analyses, such as summarizing data, understanding its structure, and making inferences. ===Definition=== Formally, a quantile is defined as a value that div..." current
  • 01:1201:12, 21 March 2023 diff hist +3,135‎ N Proxy (sensitive attributes) ‎ Created page with "{{see also|Machine learning terms}} ==Definition== In machine learning, '''proxy (sensitive attributes)''' refers to variables that indirectly capture information about a sensitive attribute, such as race, gender, or age, which are often used in a model to make predictions or decisions. The use of proxy variables can inadvertently lead to biased outcomes or algorithmic discrimination, even when the original sensitive attribute is not explicitly used in the model. It..." current
  • 01:1201:12, 21 March 2023 diff hist +3,966‎ N Probabilistic regression model ‎ Created page with "{{see also|Machine learning terms}} ==Probabilistic Regression Model== Probabilistic regression models are a class of machine learning techniques that predict the relationship between input features and a continuous target variable by estimating a probability distribution of the target variable. These models account for uncertainties in the predictions by providing a range of possible outcomes and their associated probabilities. Probabilistic regression models are wi..." current
  • 01:1101:11, 21 March 2023 diff hist +3,414‎ N Prior belief ‎ Created page with "{{see also|Machine learning terms}} ==Prior Belief in Machine Learning== Prior belief, also known as '''prior probability''' or simply '''prior''', is a fundamental concept in the field of machine learning, particularly in Bayesian statistics and Bayesian machine learning methods. The prior represents the initial belief or probability distribution of a model regarding the values of its parameters before any data is taken into account. This section will cover the..." current
  • 01:1101:11, 21 March 2023 diff hist +3,954‎ N Preprocessing ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Preprocessing in machine learning refers to the initial stage of preparing raw data for use in machine learning algorithms. This critical step involves transforming and cleaning the data to enhance its quality, reduce noise, and ensure its compatibility with the chosen machine learning model. By performing preprocessing, data scientists and engineers aim to improve the efficiency and accuracy of machine learning al..." current
  • 01:1101:11, 21 March 2023 diff hist +4,065‎ N Predictive rate parity ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Predictive rate parity is an important concept in the field of machine learning, particularly in the context of fairness and bias. It is a metric used to measure the fairness of a machine learning model, especially in cases where the model makes predictions for different groups within a dataset. The goal of achieving predictive rate parity is to ensure that the model's predictions are equitable across these groups, min..." current
  • 01:1101:11, 21 March 2023 diff hist +3,467‎ N Predictive parity ‎ Created page with "{{see also|Machine learning terms}} ==Predictive Parity in Machine Learning== Predictive parity, also known as test fairness, is a crucial criterion for evaluating the fairness of machine learning algorithms. It refers to the condition when the predictive accuracy of an algorithm is consistent across different demographic groups. In other words, the probability of a correct prediction should be equal among all subgroups within the population. This concept is essentia..." current
  • 01:1101:11, 21 March 2023 diff hist +3,685‎ N Prediction bias ‎ Created page with "{{see also|Machine learning terms}} ==Definition== Prediction bias refers to a systematic error in a machine learning model's predictions, where the model consistently over- or under-estimates the true value of the target variable. This phenomenon occurs when the model's predictions exhibit a persistent deviation from the actual values, leading to inaccurate and unreliable results. The presence of prediction bias can significantly impair a model's generalization capabili..." current
  • 01:1101:11, 21 March 2023 diff hist +2,462‎ N Precision ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the context of machine learning, ''precision'' is a fundamental metric used to evaluate the performance of classification models. Precision measures the accuracy of positive predictions made by a model, specifically the proportion of true positive instances among all instances classified as positive. This metric is particularly important in cases where the cost of false positives is high, such as in medical diag..." current
  • 01:1001:10, 21 March 2023 diff hist +3,340‎ N Precision-recall curve ‎ Created page with "{{see also|Machine learning terms}} ==Precision-Recall Curve in Machine Learning== In machine learning, the precision-recall curve is a graphical representation that illustrates the performance of a binary classification model. The curve is used to assess the trade-off between two important evaluation metrics: precision and recall. ===Definition of Precision and Recall=== * '''Precision''' refers to the proportion of true positive predictions out of all positive..." current
  • 01:1001:10, 21 March 2023 diff hist +3,103‎ N Pre-trained model ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a pre-trained model refers to a model that has been previously trained on a large dataset and can be fine-tuned for a specific task. The motivation behind using a pre-trained model is to leverage the knowledge gained during its initial training, thus reducing the time, computational resources, and the amount of data required for training a new model from scratch. ==Pre-training Me..." current
  • 01:1001:10, 21 March 2023 diff hist +3,429‎ N Pipeline ‎ Created page with "{{see also|Machine learning terms}} ==Pipeline in Machine Learning== A '''pipeline''' in machine learning refers to a sequence of data processing and transformation steps, combined with a learning algorithm, to create a complete end-to-end workflow for training and predicting outcomes. Pipelines are essential for streamlining machine learning tasks, ensuring reproducibility and efficiency, and facilitating collaboration among data scientists and engineers. ===Preproces..." current
  • 01:1001:10, 21 March 2023 diff hist +4,109‎ N Performance ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Performance in machine learning refers to the effectiveness of a machine learning model in achieving its intended purpose, which is typically to make accurate predictions or classifications based on input data. Performance evaluation is a critical aspect of machine learning, as it helps determine the quality of a model and its suitability for a particular task. This article will discuss various aspects of performance i..." current
  • 01:1001:10, 21 March 2023 diff hist +3,585‎ N Perceptron ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''perceptron''' is a type of linear classifier and an early form of artificial neural network, which was introduced by Frank Rosenblatt in 1957. Perceptrons are designed to model simple decision-making processes in machine learning, and are primarily used for binary classification tasks, where the goal is to distinguish between two possible outcomes. Although they have been largely superseded by more advanced algori..." current
  • 01:1001:10, 21 March 2023 diff hist +3,220‎ N Partitioning strategy ‎ Created page with "{{see also|Machine learning terms}} ==Partitioning Strategy in Machine Learning== In the field of machine learning, the partitioning strategy refers to the method of dividing a dataset into separate subsets to facilitate the training, validation, and testing of models. Partitioning plays a crucial role in ensuring the robustness, accuracy, and generalizability of the model when applied to real-world situations. This article explores the various partitioning strategie..." current
  • 01:0901:09, 21 March 2023 diff hist +3,883‎ N Participation bias ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Participation bias, also known as selection bias, is a type of bias in machine learning that occurs when the training data used to develop a model is not representative of the population of interest. This can lead to a model that performs poorly on new, unseen data, as it has only learned the patterns present in the biased sample. Participation bias can be particularly problematic in applications such as medical di..." current
  • 01:0901:09, 21 March 2023 diff hist +2,988‎ N Partial derivative ‎ Created page with "{{see also|Machine learning terms}} ==Partial Derivative in Machine Learning== In machine learning, the concept of partial derivatives plays a crucial role in optimization techniques, primarily for the training and refinement of models. Partial derivatives are a mathematical concept derived from calculus and are utilized to understand how a function changes when one of its variables is altered, while keeping the other variables constant. ===Definition and Notation==..." current
  • 01:0901:09, 21 March 2023 diff hist +3,461‎ N Parameter update ‎ Created page with "{{see also|Machine learning terms}} ==Parameter Update in Machine Learning== In the field of machine learning, parameter update refers to the process of iteratively adjusting the values of a model's parameters to minimize the difference between the model's predictions and the actual outcomes. The primary objective of this process is to improve the model's performance on a given task, such as classification or regression, by reducing its error rate. ===Gradient Desce..." current
  • 01:0901:09, 21 March 2023 diff hist +2,687‎ N Oversampling ‎ Created page with "{{see also|Machine learning terms}} ==Oversampling in Machine Learning== Oversampling is a technique used in the field of machine learning to address the issue of imbalanced data by increasing the number of samples in the minority class. This process aims to achieve a balanced distribution of classes within the dataset, which ultimately leads to improved performance of machine learning algorithms. ===Imbalanced Data=== Imbalanced data occurs when the distribution o..." current
  • 01:0901:09, 21 March 2023 diff hist +4,109‎ N Outliers ‎ Created page with "{{see also|Machine learning terms}} ==Outliers in Machine Learning== In the field of machine learning, outliers are data points that deviate significantly from the majority of the other data points in a given dataset. These data points can have a substantial impact on the results and performance of machine learning algorithms, potentially leading to erroneous or misleading conclusions. This article discusses the concept of outliers, their implications in machine learning..." current
  • 01:0901:09, 21 March 2023 diff hist +3,253‎ N Outlier detection ‎ Created page with "{{see also|Machine learning terms}} ==Outlier Detection in Machine Learning== Outlier detection, also referred to as anomaly detection or novelty detection, is a process in machine learning and statistics that involves identifying data points, observations, or patterns that significantly deviate from the expected behavior or the majority of the data. These deviations, known as outliers, can indicate errors in data collection, unusual events, or the presence of pr..." current
  • 01:0801:08, 21 March 2023 diff hist +2,872‎ N Out-group homogeneity bias ‎ Created page with "{{see also|Machine learning terms}} ==Out-group Homogeneity Bias== Out-group homogeneity bias, also known as the out-group homogeneity effect, refers to the cognitive bias that leads individuals to perceive members of an out-group, or those that do not belong to their own social or cultural group, as more similar to one another than they actually are. This bias can manifest in various social, cultural, and demographic contexts, including ethnicity, nationality, gender, a..." current
  • 01:0801:08, 21 March 2023 diff hist +3,285‎ N Optimizer ‎ Created page with "{{see also|Machine learning terms}} ==Definition== An '''optimizer''' in machine learning is an algorithm or method used to adjust the parameters of a model with the aim of minimizing the error or loss function during the training process. Optimizers guide the model in learning patterns from the data and making predictions as accurately as possible. They are a crucial component of machine learning algorithms, as they determine the effectiveness and efficiency of the..." current
  • 01:0801:08, 21 March 2023 diff hist +3,054‎ N Operation (op) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the context of machine learning, an operation (often abbreviated as 'op') refers to a basic computational task or function that manipulates data, typically during the process of training or running a machine learning model. Operations can be arithmetic, logical, or relational, and are performed on input data to produce an output. They are the building blocks of more complex algorithms and machine learning models. =..." current
  • 01:0801:08, 21 March 2023 diff hist +3,237‎ N Saver ‎ Created page with "{{see also|Machine learning terms}} ==Saver in Machine Learning== In the context of machine learning, a '''Saver''' is a utility or class that enables users to save and restore the states of models, variables, or other components during the training and evaluation process. Saving the state of a model is important for various reasons, such as preserving intermediate results, facilitating transfer learning, and enabling the resumption of training after interruptions. Diffe..." current
  • 01:0801:08, 21 March 2023 diff hist +3,390‎ N SavedModel ‎ Created page with "{{see also|Machine learning terms}} ==SavedModel in Machine Learning== SavedModel is a standardized, language-agnostic, and platform-independent serialization format for machine learning models developed by Google as part of the TensorFlow framework. It facilitates the sharing, deployment, and management of trained models across different platforms, programming languages, and applications. ===Overview=== The primary objective of SavedModel is to streamline t..." current
  • 01:0801:08, 21 March 2023 diff hist +3,966‎ N Parameter Server (PS) ‎ Created page with "{{see also|Machine learning terms}} ==Parameter Server (PS) in Machine Learning== The '''Parameter Server (PS)''' is a distributed machine learning framework designed to manage the parameters of large-scale machine learning models during the training process. It is particularly useful when dealing with massive datasets and complex model architectures, which are common in Deep Learning and Distributed Machine Learning. ===Background=== Traditional machine learnin..." current
  • 01:0701:07, 21 March 2023 diff hist +2,844‎ N PR AUC (area under the PR curve) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, the evaluation of classification models is a critical task. One common metric used to measure the performance of such models is the PR AUC, or Area Under the Precision-Recall (PR) Curve. The PR AUC is particularly useful when dealing with imbalanced datasets, where the proportion of positive and negative samples is unequal. ==Precision-Recall Curve== ===Definition=== The Precision-..." current

20 March 2023

  • 11:4511:45, 20 March 2023 diff hist +3,272‎ N One-shot learning ‎ Created page with "{{see also|Machine learning terms}} ==One-shot Learning in Machine Learning== One-shot learning is a type of machine learning approach that aims to build robust models capable of learning from a limited amount of data, typically with only one or very few examples per class. This is in contrast to traditional supervised learning techniques, which require large amounts of labeled data for training. ===Background=== Traditional machine learning and deep learning algorithms..." current
  • 11:4511:45, 20 March 2023 diff hist +3,416‎ N Objective function ‎ Created page with "{{see also|Machine learning terms}} ==Objective Function in Machine Learning== The objective function, also known as the loss function or cost function, is a key concept in machine learning and optimization problems. It is a mathematical function that quantifies the discrepancy between the predicted output and the true output (ground truth) for a given input. The goal of machine learning algorithms is to minimize the value of the objective function to improve the..." current
  • 11:4511:45, 20 March 2023 diff hist +3,081‎ N Objective ‎ Created page with "{{see also|Machine learning terms}} ==Objective in Machine Learning== The objective in machine learning refers to the goal or aim that an algorithm strives to achieve through the learning process. This typically involves minimizing a loss function or maximizing a utility function, which are mathematical representations of the algorithm's performance. The objective provides guidance for the machine learning model to optimize its parameters and improve its predictions over..." current
  • 11:4411:44, 20 March 2023 diff hist +4,102‎ N Novelty detection ‎ Created page with "{{see also|Machine learning terms}} ==Novelty Detection in Machine Learning== Novelty detection is a sub-field of machine learning that focuses on the identification and classification of previously unseen, novel patterns or data points in a given dataset. The primary goal of novelty detection algorithms is to differentiate between normal and abnormal patterns, enabling effective decision-making in various applications, such as anomaly detection, outlier detectio..." current
  • 11:4411:44, 20 March 2023 diff hist +4,182‎ N Non-response bias ‎ Created page with "{{see also|Machine learning terms}} ==Non-response Bias in Machine Learning== Non-response bias, a type of sampling bias, occurs in machine learning when the data used for training and evaluating a model fails to accurately represent the entire population due to the absence or underrepresentation of certain subgroups in the sample. This phenomenon can lead to poor generalization performance, as the model's predictions may be systematically biased and not applicable t..." current
  • 11:4411:44, 20 March 2023 diff hist +4,434‎ N Noise ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, noise refers to the presence of unwanted or irrelevant data that can have a detrimental effect on the performance and accuracy of a model. Noise can be introduced during the data collection process, data preprocessing, or through inherent randomness in the data itself. This article will provide an overview of the various types of noise, their sources, and their impacts on machine l..." current
  • 11:4411:44, 20 March 2023 diff hist +3,051‎ N Node (TensorFlow graph) ‎ Created page with "{{see also|Machine learning terms}} ==Node (TensorFlow graph)== In the context of machine learning, a node is a fundamental unit within a computational graph, which is a directed, acyclic graph (DAG) used to represent the flow of data and operations in a TensorFlow model. A TensorFlow graph is composed of multiple nodes, each representing an operation or a variable, which are connected by edges representing the flow of data between these nodes. The TensorFlow graph is a..." current
  • 11:4411:44, 20 March 2023 diff hist +3,670‎ N Multinomial regression ‎ Created page with "{{see also|Machine learning terms}} ==Multinomial Regression== Multinomial regression, also known as multinomial logistic regression or softmax regression, is a statistical method used in machine learning and statistics for modeling the relationship between a categorical dependent variable and one or more independent variables. It is an extension of binary logistic regression, which is used for predicting binary outcomes. Multinomial regression is particularly us..." current
  • 11:4411:44, 20 March 2023 diff hist +3,478‎ N Multinomial classification ‎ Created page with "{{see also|Machine learning terms}} ==Multinomial Classification== Multinomial classification, also known as multi-class or multi-nominal classification, is a type of supervised machine learning problem where the objective is to categorize an input data point into one of several discrete classes. In contrast to binary classification, where there are only two possible categories, multinomial classification deals with three or more categories. ===Problem Formulation==..." current
  • 11:4311:43, 20 March 2023 diff hist +3,880‎ N Multi-class logistic regression ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== '''Multi-class logistic regression''', also referred to as '''softmax regression''' or '''multinomial logistic regression''', is a supervised machine learning algorithm used for predicting the categorical label of an input instance when there are more than two possible classes. It is an extension of the binary logistic regression model, which can only handle two-class classification problems. Multi-class logistic r..." current
  • 11:4311:43, 20 March 2023 diff hist +4,321‎ N Model training ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Model training in machine learning refers to the process of developing a mathematical model capable of making predictions or decisions based on input data. This is achieved by iteratively adjusting the model's parameters until it can accurately generalize from the training data to previously unseen data. The ultimate goal of this process is to create a model that can perform well on new, real-world data without bei..." current
  • 11:4311:43, 20 March 2023 diff hist +3,193‎ N Model capacity ‎ Created page with "{{see also|Machine learning terms}} ==Definition== In the context of machine learning, ''model capacity'' refers to the ability of a model to learn and represent various functions and patterns within a given dataset. High-capacity models have a larger number of parameters and can therefore represent more complex functions, while low-capacity models have fewer parameters and are limited in the complexity of functions they can represent. Model capacity plays a crucial role..." current
  • 11:4311:43, 20 March 2023 diff hist +2,229‎ N Minimax loss ‎ Created page with "{{see also|Machine learning terms}} ==Minimax Loss== The minimax loss, also known as the minimax regret, is a performance measure in machine learning and game theory that quantifies the worst-case performance of an algorithm or decision rule under uncertainty. This concept is utilized in various optimization problems, where the goal is to minimize the maximum possible loss or regret under uncertain conditions. ===Definition=== Given a decision-making problem, th..." current
  • 11:4311:43, 20 March 2023 diff hist +3,804‎ N Mini-batch stochastic gradient descent ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, '''mini-batch stochastic gradient descent''' ('''MB-SGD''') is an optimization algorithm commonly used for training neural networks and other models. The algorithm operates by iteratively updating model parameters to minimize a loss function, which measures the discrepancy between the model's predictions and actual target values. Mini-batch stochastic gradient descent is a variant of stochastic g..." current
  • 11:4311:43, 20 March 2023 diff hist +3,963‎ N Metric ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, a '''metric''' refers to a quantitative measure that is used to evaluate the performance of an algorithm or model. Metrics help researchers and practitioners understand the effectiveness of their models in solving a particular task and allow for comparison with other models. Several types of metrics exist, each tailored to different types of tasks or problems, such as classification, regression..." current
  • 11:4211:42, 20 March 2023 diff hist +4,027‎ N Matrix factorization ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Matrix factorization is a technique in machine learning that aims to discover latent features underlying the interactions between two different kinds of entities. It has been widely used for tasks such as recommendation systems, dimensionality reduction, and data imputation. The primary goal of matrix factorization is to approximate a given matrix by factorizing it into two or more lower-dimensional matrices, which can..." current
  • 11:4211:42, 20 March 2023 diff hist +3,201‎ N Matplotlib ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== '''Matplotlib''' is a widely used data visualization library in Python that enables developers to create high-quality and interactive visualizations, such as line plots, scatter plots, bar plots, histograms, 3D plots, and more. It is an essential tool in machine learning and data science for exploring and analyzing data, as well as presenting the results of models and algorithm..." current
  • 11:4211:42, 20 March 2023 diff hist +4,075‎ N Loss surface ‎ Created page with "{{see also|Machine learning terms}} ==Loss Surface in Machine Learning== In the field of machine learning, the '''loss surface''' (also referred to as the '''error surface''' or the '''objective function surface''') refers to the graphical representation of the relationship between the parameters of a learning model and the associated loss or error. The primary goal of machine learning algorithms is to optimize these parameters, minimizing the loss and consequently e..." current
  • 11:4211:42, 20 March 2023 diff hist +3,614‎ N NumPy ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== NumPy (Numerical Python) is a highly popular and widely used open-source library in the field of machine learning and data science. NumPy provides a variety of tools and functions for working with numerical data in the Python programming language. It is highly regarded for its efficiency, simplicity, and performance in handling multi-dimensional arrays and matrices, as well as for its comprehensive suite of..." current
  • 11:4211:42, 20 March 2023 diff hist +3,656‎ N NaN trap ‎ Created page with "{{see also|Machine learning terms}} ==NaN Trap in Machine Learning== NaN trap, short for 'Not a Number' trap, is a common issue encountered in machine learning algorithms, particularly during the training process. It occurs when the algorithm's calculations yield undefined or unrepresentable numerical results, leading to the propagation of NaN values throughout the model. This can significantly hinder the model's learning capability and adversely affect its performance...." current
  • 11:4211:42, 20 March 2023 diff hist +3,565‎ N Momentum ‎ Created page with "{{see also|Machine learning terms}} ==Momentum in Machine Learning== Momentum is a widely-used optimization technique in the field of machine learning and deep learning, specifically in training neural networks. This method aims to accelerate the convergence of gradient-based optimization algorithms such as gradient descent and stochastic gradient descent by incorporating information from previous iterations. ===Gradient Descent and Stochastic Gradient Descent==..." current
  • 11:4111:41, 20 March 2023 diff hist +3,723‎ N Metrics API (tf.metrics) ‎ Created page with "{{see also|Machine learning terms}} ==Overview== The '''Metrics API''' in machine learning, specifically in the context of ''TensorFlow'' (TensorFlow), is a collection of utilities and classes designed to compute and represent various evaluation metrics, also known as performance metrics. These metrics are essential for evaluating the performance of machine learning models, and the Metrics API, referred to as '''tf.metrics''' in TensorFlow, facilitates the calculatio..." current
  • 11:4111:41, 20 March 2023 diff hist +2,512‎ N Mean Squared Error (MSE) ‎ Created page with "{{see also|Machine learning terms}} ==Mean Squared Error (MSE)== Mean Squared Error (MSE) is a widely used metric to evaluate the performance of regression models in machine learning. It measures the average of the squared differences between the predicted values and the actual values. MSE is suitable for evaluating continuous variables and is particularly useful when dealing with datasets that include outliers, as it emphasizes larger errors due to the squaring operatio..." current
  • 11:4111:41, 20 March 2023 diff hist +2,953‎ N Mean Absolute Error (MAE) ‎ Created page with "{{see also|Machine learning terms}} ==Mean Absolute Error (MAE)== The '''Mean Absolute Error (MAE)''' is a widely used metric in Machine Learning and Statistics to evaluate the performance of a predictive model. It measures the average magnitude of errors between the predicted and actual values, without considering the direction of the errors. MAE is a popular choice for regression tasks as it provides an easily interpretable representation of the model's error...." current
  • 05:0605:06, 20 March 2023 diff hist +3,021‎ N Logits ‎ Created page with "{{see also|Machine learning terms}} ==Logits in Machine Learning== In the field of machine learning, logits refer to the unnormalized probability values that are output by a classification model before they are transformed into actual probabilities. Logits are often associated with neural networks, particularly in the context of deep learning and artificial intelligence. These values serve as a crucial intermediate step in the process of predicting class prob..." current
  • 05:0605:06, 20 March 2023 diff hist +3,694‎ N Least squares regression ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, '''Least Squares Regression''' is a well-established method for fitting a linear model to a set of data points. It seeks to minimize the sum of the squared differences between the observed values and the values predicted by the linear model. This technique is particularly useful in applications where the relationship between input features and the target variable is linear or near-linear. In this a..." current
  • 05:0505:05, 20 March 2023 diff hist +3,483‎ N Items ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, the term "items" typically refers to individual data points or instances that are used as inputs to train, validate, or test machine learning models. Items can take various forms, such as images, texts, or numerical values, depending on the specific problem being addressed. This article will explore the concept of items in machine learning, their significance in model training, and the..." current
  • 05:0505:05, 20 March 2023 diff hist +3,473‎ N Item matrix ‎ Created page with "{{see also|Machine learning terms}} ==Item Matrix in Machine Learning== The Item Matrix is a fundamental concept in machine learning, particularly in the realm of collaborative filtering and recommendation systems. It is a structured representation of items and their features, allowing algorithms to analyze patterns and provide personalized recommendations to users. This article delves into the definition, purpose, and applications of an Item Matrix, and offers a simplif..." current
  • 05:0505:05, 20 March 2023 diff hist +3,171‎ N Inter-rater agreement ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Inter-rater agreement, also referred to as inter-rater reliability or inter-annotator agreement, is a measure of the degree of consistency or consensus among multiple raters or annotators when evaluating a set of items, such as classifying data points in a machine learning task. This measure is essential in various machine learning and natural language processing (NLP) applications, where human-annotated data i..." current
  • 05:0505:05, 20 March 2023 diff hist +3,230‎ N Instance ‎ Created page with "{{see also|Machine learning terms}} ==Definition of Instance in Machine Learning== An '''instance''' in machine learning refers to a single data point or example used in the process of training and evaluating machine learning models. Instances are essential components of the dataset and are typically represented as a set of features and their corresponding labels or target values. They serve as the basis for learning patterns, making predictions, and evaluating the p..." current
  • 05:0505:05, 20 March 2023 diff hist +3,089‎ N Individual fairness ‎ Created page with "{{see also|Machine learning terms}} ==Individual Fairness in Machine Learning== Individual fairness in machine learning refers to the concept of ensuring that similar individuals are treated similarly by a machine learning algorithm. This idea has gained significant attention in recent years due to concerns about the potential for algorithmic bias and unfair treatment of individuals in various domains, including finance, healthcare, criminal justice, and hiring practices..." current
  • 05:0505:05, 20 March 2023 diff hist +3,470‎ N Independently and identically distributed (i.i.d) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, the concept of ''independently and identically distributed'' (i.i.d) refers to a fundamental assumption about the nature of data used in statistical modeling and analysis. The i.i.d assumption is particularly important in the development of machine learning algorithms and their evaluation, as it affects the validity of the models and the accuracy of their predictions. The i.i.d assumpt..." current
  • 05:0505:05, 20 March 2023 diff hist +3,547‎ N Incompatibility of fairness metrics ‎ Created page with "{{see also|Machine learning terms}} ==Incompatibility of Fairness Metrics in Machine Learning== In the field of machine learning, fairness is a critical issue that has gained increasing attention in recent years. The concept of fairness is essential to ensure that algorithmic decisions are equitable and do not discriminate against particular groups. This article focuses on the incompatibility of fairness metrics in machine learning, its implications, and a simple explana..." current
  • 05:0405:04, 20 March 2023 diff hist +3,827‎ N In-group bias ‎ Created page with "{{see also|Machine learning terms}} ==In-group Bias in Machine Learning== In-group bias, also referred to as in-group favoritism or in-group preference, is a well-established phenomenon in social psychology. It occurs when individuals show a preference for members of their own group over those of other groups. In the context of machine learning, in-group bias refers to the unintentional favoring of specific groups in the algorithmic decision-making process, often resulti..." current
  • 05:0405:04, 20 March 2023 diff hist +3,246‎ N Implicit bias ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Implicit bias in machine learning refers to the unintentional introduction of discriminatory or prejudiced behaviors, patterns, or outcomes in machine learning models, primarily due to the influence of biased training data or algorithmic design. These biases may manifest in the form of unfair treatment of certain demographic groups, perpetuation of stereotypes, or unequal allocation of resources. As machine learning sy..." current
  • 05:0405:04, 20 March 2023 diff hist +2,927‎ N Hyperplane ‎ Created page with "{{see also|Machine learning terms}} ==Definition== In machine learning, a '''hyperplane''' refers to a geometric construct that serves as a decision boundary for separating different classes or categories of data points in a multidimensional space. It is an essential concept for many classification and regression algorithms, including the popular Support Vector Machines (SVM) method. Mathematically, a hyperplane is an (n-1)-dimensional subspace within an n-dimens..." current
  • 05:0405:04, 20 March 2023 diff hist +3,533‎ N Holdout data ‎ Created page with "{{see also|Machine learning terms}} ==Holdout Data in Machine Learning== Holdout data is a subset of the dataset in machine learning that is separated from the training data and is used to evaluate the performance of a model during the model selection process. Holdout data helps to identify potential issues such as overfitting and provides an unbiased estimate of the model's generalization performance. This section discusses the importance of holdout data, the pr..." current
  • 05:0405:04, 20 March 2023 diff hist +2,980‎ N Hinge loss ‎ Created page with "{{see also|Machine learning terms}} ==Hinge Loss== Hinge loss is a type of loss function used in machine learning and specifically in support vector machines (SVMs). It measures the error between the predicted output and the actual output for a given training example. Hinge loss is particularly effective for binary classification problems, as it aims to find the optimal decision boundary (or margin) that maximally separates two classes of data points. ===Definit..." current
  • 05:0405:04, 20 March 2023 diff hist +3,587‎ N Heuristic ‎ Created page with "{{see also|Machine learning terms}} ==Definition of Heuristic== Heuristics, derived from the Greek word ''heuriskein'' which means "to discover," are problem-solving techniques that employ a practical approach to finding an adequate, though not always optimal, solution to complex problems. In machine learning, heuristics are often utilized to guide the search for an appropriate model or to optimize algorithmic parameters when an exhaustive search is computationally i..." current
  • 05:0305:03, 20 March 2023 diff hist +2,970‎ N Hashing ‎ Created page with "{{see also|Machine learning terms}} ==Hashing in Machine Learning== Hashing, a technique commonly used in computer science, has found various applications in the field of machine learning. In this context, hashing mainly refers to the process of converting high-dimensional input data into lower-dimensional representations, while preserving important information about the original data. This transformation can be beneficial for numerous machine learning tasks, including f..." current
  • 05:0305:03, 20 March 2023 diff hist +3,075‎ N Hallucination ‎ Created page with "{{see also|Machine learning terms}} ==Hallucination in Machine Learning== Hallucination in machine learning refers to the phenomenon where a model generates outputs that are not entirely accurate or relevant to the input data. This occurs when the model overfits to the training data or does not generalize well to new or unseen data. This behavior has been observed in various machine learning models, including deep learning models like neural networks and natural lang..."
  • 05:0305:03, 20 March 2023 diff hist +4,320‎ N Group attribution bias ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Group attribution bias is a term used to describe a phenomenon in machine learning where an algorithm systematically and unfairly associates certain characteristics or outcomes with specific groups of individuals. This bias often stems from the training data that a machine learning model is exposed to, which may contain unrepresentative or skewed examples. When a model is trained on such data, it may inadvertently lear..." current
  • 05:0305:03, 20 March 2023 diff hist +3,518‎ N Graph execution ‎ Created page with "{{see also|Machine learning terms}} ==Graph Execution in Machine Learning== Graph execution in machine learning refers to a computational paradigm that employs directed graphs to represent and execute complex operations and dependencies between data, models, and algorithms. The graph execution approach is typically used in conjunction with TensorFlow, a popular open-source machine learning library, to optimize performance and parallelism in deep learning models. It p..." current
  • 05:0305:03, 20 March 2023 diff hist +4,228‎ N Graph ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the context of machine learning, a '''graph''' is a mathematical structure that represents relationships between objects or entities, typically in the form of nodes (or vertices) connected by edges (or links). Graphs have become increasingly popular in recent years due to their ability to represent complex data and their effectiveness in solving various machine learning tasks. They are particularly useful for repres..." current
  • 05:0305:03, 20 March 2023 diff hist +3,206‎ N Layers API (tf.layers) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''Layers API''' (commonly referred to as '''tf.layers''') is a high-level interface within the TensorFlow machine learning framework, specifically designed to simplify the process of building and training neural networks. It provides pre-built, reusable components, known as layers, that can be easily combined and customized to create a wide range of machine learning models. The Layers API encourages modular de..." current
  • 05:0205:02, 20 March 2023 diff hist +4,059‎ N Kernel Support Vector Machines (KSVMs) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Kernel Support Vector Machines (KSVMs) are a class of machine learning algorithms that are particularly well-suited for classification and regression tasks. They are an extension of the Support Vector Machine (SVM) algorithm and utilize kernel functions to project data into a higher-dimensional space, allowing for nonlinear decision boundaries. This article aims to provide an academic-style overview of the key..." current
  • 05:0205:02, 20 March 2023 diff hist +4,117‎ N Keras ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Keras is an open-source, high-level neural networks API (Application Programming Interface) designed to simplify the process of building and training deep learning models. It was developed by François Chollet and released in March 2015. Keras acts as a user-friendly interface to the more complex deep learning libraries like TensorFlow, Theano, and Microsoft Cognitive Toolkit (CNTK). By providin..." current
  • 05:0205:02, 20 March 2023 diff hist +3,253‎ N IoU ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning and computer vision, '''Intersection over Union (IoU)''' is a commonly used evaluation metric for object detection and segmentation tasks. This metric measures the overlap between the predicted bounding box (or segmentation mask) and the ground truth bounding box (or segmentation mask), providing a quantitative assessment of the model's performance in terms of its ability to acc..." current
  • 01:1901:19, 20 March 2023 diff hist +2,630‎ N Gradient ‎ Created page with "{{see also|Machine learning terms}} ==Gradient in Machine Learning== Gradient is a fundamental concept in machine learning, particularly in the optimization process of training algorithms. It is a multi-dimensional generalization of the derivative, which quantifies the rate of change of a function with respect to its variables. In machine learning, the gradient is typically used to minimize a loss function, which measures the discrepancy between the predictions made by t..." current
  • 01:1801:18, 20 March 2023 diff hist +3,237‎ N Generator ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a '''generator''' refers to a model or algorithm that generates new data samples, which can be either synthetic or based on existing data. Generators have become increasingly popular with the advent of generative models, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), which are capable of generating complex data distributions. These models ha..." current
  • 01:1801:18, 20 March 2023 diff hist +3,917‎ N Generative model ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A generative model is a type of machine learning algorithm that aims to learn the underlying probability distribution of the training data in order to generate new data samples that resemble the original dataset. These models have been widely adopted in various applications such as natural language processing, image synthesis, and anomaly detection. ==Types of Generative Models== Generative models can be broadly c..." current
  • 01:1801:18, 20 March 2023 diff hist +3,866‎ N Generative adversarial network (GAN) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''Generative Adversarial Network''' ('''GAN''') is a type of machine learning algorithm developed by Ian Goodfellow and his colleagues in 2014<ref>Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. In ''Advances in neural information processing systems'' (pp. 2672-2680).</ref>. GANs are comprised of two distinct..." current
  • 01:1801:18, 20 March 2023 diff hist +3,320‎ N Generalized linear model ‎ Created page with "{{see also|Machine learning terms}} ==Generalized Linear Models (GLMs)== Generalized Linear Models (GLMs) are a class of statistical models that extend the linear regression model, allowing for response variables with distributions other than the normal distribution. GLMs were first introduced by John Nelder and Robert Wedderburn in 1972, and have since become a fundamental tool in statistical modeling and machine learning. ===Components of a Generalized Linear Mode..." current
  • 01:1801:18, 20 March 2023 diff hist +2,540‎ N Fully connected layer ‎ Created page with "{{see also|Machine learning terms}} ==Fully Connected Layer in Machine Learning== The fully connected layer, also known as a dense layer, is an essential component in various machine learning models, particularly deep learning architectures such as artificial neural networks (ANNs) and convolutional neural networks (CNNs). This layer serves to connect each neuron in one layer to every neuron in the subsequent layer, enabling information to be transmitted and proc..." current
  • 01:1801:18, 20 March 2023 diff hist +4,035‎ N Full softmax ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, the softmax function is an essential component for the classification of multiple categories. The full softmax, also known as the standard softmax, is a method used to convert a vector of real numbers into a probability distribution. The output of the full softmax function is a probability distribution that can be interpreted as the likelihood of an input belonging to each of the considered classes..." current
  • 01:1701:17, 20 March 2023 diff hist +3,523‎ N Fine tuning ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Fine tuning, also known as transfer learning, is a technique used in machine learning to improve the performance of a pre-trained model on a specific task. This approach leverages the knowledge gained from a related task, typically one with a larger dataset, to fine-tune the model for a new task with a smaller dataset. Fine tuning has gained popularity in deep learning, especially for tasks involving Convolutional Ne..." current
  • 01:1701:17, 20 March 2023 diff hist +3,096‎ N Few-shot learning ‎ Created page with "{{see also|Machine learning terms}} ==Few-shot Learning in Machine Learning== Few-shot learning is a subfield of machine learning, particularly focused on training algorithms to perform tasks or make predictions with a limited amount of data. In contrast to traditional machine learning, which often relies on large volumes of data for training, few-shot learning aims to achieve similar performance using only a few samples. ===Background and Motivation=== The development..." current
  • 01:1701:17, 20 March 2023 diff hist +4,142‎ N Feedforward neural network (FFN) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''feedforward neural network''' (FFN) is a type of artificial neural network used in machine learning that is characterized by its unidirectional flow of information, from input to output, without any loops or cycles. The network is composed of layers of interconnected nodes, known as neurons or artificial neurons, that process and transmit information. Feedforward neural networks have been used extensively in vario..." current
  • 01:1701:17, 20 March 2023 diff hist +3,387‎ N Federated learning ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Federated learning is a decentralized approach to machine learning that aims to enable multiple participants to collaboratively train a shared model while keeping their data private. This method has garnered significant attention in recent years due to its potential to address privacy, security, and scalability concerns in distributed machine learning systems. The core principle of federated learning is to allow local..." current
  • 01:1701:17, 20 March 2023 diff hist +4,298‎ N Feature spec ‎ Created page with "{{see also|Machine learning terms}} ==Feature Specification in Machine Learning== Feature specification is a crucial aspect of machine learning and data preprocessing that involves defining and selecting the relevant features or attributes for a given problem. The process is essential to improve model performance, reduce computational complexity, and facilitate easier interpretation of the results. ===Definition=== In machine learning, features refer to the meas..." current
  • 01:1701:17, 20 March 2023 diff hist +4,255‎ N Feature extraction ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Feature extraction is a crucial step in the field of machine learning and pattern recognition that involves extracting relevant and informative attributes from raw data. These attributes, also known as features or variables, are then used by machine learning algorithms to classify or predict outcomes. The process of feature extraction is essential in simplifying and enhancing the performance of models by reduci..." current
  • 01:1601:16, 20 March 2023 diff hist +2,637‎ N False negative rate ‎ Created page with "{{see also|Machine learning terms}} ==Definition== The '''false negative rate''' (Type II error) in machine learning refers to the proportion of positive instances that the algorithm incorrectly classifies as negative. This is an important metric when evaluating the performance of machine learning models, particularly when assessing the capability of the model to accurately identify positive cases. The false negative rate is complementary to the sensitivity (re..." current
  • 01:1601:16, 20 March 2023 diff hist +3,204‎ N Fairness metric ‎ Created page with "{{see also|Machine learning terms}} ==Fairness Metric in Machine Learning== In the field of machine learning, fairness is an increasingly important consideration. The concept of fairness relates to the equitable treatment of different groups by algorithms and the avoidance of discriminatory outcomes. Fairness metrics are quantitative measures that help assess the fairness of a machine learning model, thus allowing researchers and practitioners to mitigate potential biase..." current
  • 01:1601:16, 20 March 2023 diff hist +3,534‎ N Fairness constraint ‎ Created page with "{{see also|Machine learning terms}} ==Fairness Constraint in Machine Learning== Machine learning is a subfield of artificial intelligence that focuses on the development of algorithms that enable computers to learn from and make predictions or decisions based on data. In the context of machine learning, fairness is an important ethical consideration, as it pertains to the equitable treatment of different individuals or groups by the algorithm. Fairness constraint..." current
  • 01:1601:16, 20 March 2023 diff hist +3,641‎ N Experimenter's bias ‎ Created page with "{{see also|Machine learning terms}} ==Experimenter's Bias in Machine Learning== Experimenter's bias, also known as researcher bias or confirmation bias, is a phenomenon that occurs when researchers unintentionally influence the outcomes of their studies or experiments to align with their expectations or preconceived beliefs. In the context of machine learning, experimenter's bias can manifest in various stages of the development process, including data collection, prepro..." current
  • 01:1601:16, 20 March 2023 diff hist +3,429‎ N Equalized odds ‎ Created page with "{{see also|Machine learning terms}} ==Equalized Odds in Machine Learning== Equalized Odds is a fairness criterion in machine learning, which aims to mitigate discriminatory outcomes that may arise from the use of algorithms in various applications. This criterion focuses on ensuring that the error rates for different demographic groups are equal, in order to avoid biased decision-making. In the following sections, we will delve into the definition, motivation, and implem..." current
  • 01:1601:16, 20 March 2023 diff hist +3,727‎ N Equality of opportunity ‎ Created page with "{{see also|Machine learning terms}} ==Equality of Opportunity in Machine Learning== Equality of opportunity in machine learning refers to the design, implementation, and assessment of algorithms and models that ensure fairness and unbiased outcomes for different subgroups within a given population. This is particularly important when these models are used to make decisions that may have significant impacts on people's lives, such as job applications, loan approvals, or m..." current
  • 01:1601:16, 20 March 2023 diff hist +3,160‎ N Ensemble ‎ Created page with "{{see also|Machine learning terms}} ==Ensemble Methods in Machine Learning== Ensemble methods are a group of techniques in machine learning that combine the predictions of multiple models, or "base learners," to improve overall predictive performance. The idea behind ensemble methods is that the aggregation of the predictions of several individual models can lead to a more robust and accurate result than any single model alone. ===Types of Ensemble Methods=== There..." current
  • 01:1501:15, 20 March 2023 diff hist +3,014‎ N Empirical risk minimization (ERM) ‎ Created page with "{{see also|Machine learning terms}} ==Empirical Risk Minimization (ERM)== Empirical Risk Minimization (ERM) is a fundamental concept in the field of machine learning and statistical learning theory. ERM is a strategy that aims to minimize the risk of making incorrect predictions by selecting the best hypothesis from a given hypothesis set. The risk is defined as the expected loss incurred when using the selected hypothesis to make predictions on unseen data. ERM..." current
  • 01:1501:15, 20 March 2023 diff hist +3,341‎ N Earth mover's distance (EMD) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''Earth Mover's Distance''' (EMD), also known as the '''Wasserstein distance''' or '''Mallows distance''', is a measure of dissimilarity between two probability distributions in machine learning, statistics, and computer vision. It was originally introduced by Y. Rubner, C. Tomasi, and L.J. Guibas in their 1998 paper titled "A Metric for Distributions with Applications to Image Databases". EMD is especially useful..." current
  • 01:1501:15, 20 March 2023 diff hist +3,283‎ N GAN ‎ Created page with "{{see also|Machine learning terms}} ==Generative Adversarial Networks (GANs)== Generative Adversarial Networks, or GANs, are a class of machine learning models introduced by Ian Goodfellow and his colleagues in 2014. GANs consist of two neural networks, a generator and a discriminator, which are trained simultaneously in a process of competing against each other. GANs have been widely used in various applications, including image synthesis, data augmentation, and sem..." current
  • 01:1501:15, 20 March 2023 diff hist +3,358‎ N Estimator ‎ Created page with "{{see also|Machine learning terms}} ==Estimator in Machine Learning== In the context of machine learning, an '''estimator''' is an algorithm or function that approximates a target function or model based on a set of input data. The primary goal of an estimator is to make predictions or infer properties of an unknown function using observed data. Estimators can be broadly categorized into two types: '''parametric''' and '''non-parametric'''. ==Parametric Estimators== Par..." current

19 March 2023

  • 19:1719:17, 19 March 2023 diff hist +3,705‎ N Eager execution ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Eager execution is a programming paradigm in machine learning that offers a more intuitive and flexible way of building, training, and debugging computational graphs. Unlike the traditional graph-based execution, which requires the construction of a static computation graph before running any operations, eager execution allows operations to be executed immediately as they are called, similar to standard Python programs..." current
  • 19:1719:17, 19 March 2023 diff hist +3,328‎ N Dropout regularization ‎ Created page with "{{see also|Machine learning terms}} ==Dropout Regularization in Machine Learning== Dropout regularization is a technique used in machine learning to prevent overfitting in neural networks. Overfitting occurs when a model learns to perform well on the training data but fails to generalize to unseen data. This article discusses the concept of dropout regularization, its implementation, and its advantages in the context of neural networks. ===Concept=== Dropout regularizat..." current
  • 19:1719:17, 19 March 2023 diff hist +3,187‎ N Disparate treatment ‎ Created page with "{{see also|Machine learning terms}} ==Disparate Treatment in Machine Learning== Disparate treatment in machine learning refers to the unjust or prejudicial treatment of individuals or groups based on certain attributes, such as race, gender, or age, in the context of algorithmic decision-making systems. This phenomenon occurs when the model learns to make biased decisions due to the presence of discriminatory patterns in the training data, resulting in unfair treatment f..." current
  • 19:1719:17, 19 March 2023 diff hist +2,972‎ N Disparate impact ‎ Created page with "{{see also|Machine learning terms}} ==Disparate Impact in Machine Learning== Disparate impact in machine learning refers to the unintended and potentially discriminatory consequences of an algorithmic decision-making process, where certain groups or individuals may be adversely affected due to biases in the data or model. This phenomenon raises significant ethical, legal, and social concerns, as it may perpetuate or exacerbate existing inequalities. ===Causes of Dispara..." current
  • 19:1619:16, 19 March 2023 diff hist +3,750‎ N Discriminator ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''discriminator''' in the context of machine learning refers to a model or a component of a model designed to distinguish between different types of data. Discriminators are most commonly used in Generative Adversarial Networks (GANs), where they play a crucial role in the training process by evaluating the authenticity of generated data samples. This article provides an overview of discriminators, their applica..." current
  • 19:1619:16, 19 March 2023 diff hist +2,891‎ N Discriminative model ‎ Created page with "{{see also|Machine learning terms}} ==Discriminative Models in Machine Learning== Discriminative models are a class of machine learning algorithms that aim to model the decision boundary between different classes or categories. These models focus on estimating the conditional probability of a class label given a set of input features, denoted as P(Y|X), where Y represents the class label and X the input features. Discriminative models are widely used for various tasks, s..." current
  • 19:1619:16, 19 March 2023 diff hist +3,783‎ N Dimensions ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, dimensions refer to the number of features or attributes used to represent data points in a dataset. High-dimensional data can pose challenges to traditional machine learning algorithms, while also providing opportunities for more complex and detailed analyses. This article will explore the concept of dimensions in machine learning, their implications, and strategies for dealing wi..." current
  • 19:1619:16, 19 March 2023 diff hist +3,866‎ N Dimension reduction ‎ Created page with "{{see also|Machine learning terms}} ==Dimension Reduction in Machine Learning== Dimension reduction, also known as dimensionality reduction, is a fundamental technique in the field of machine learning and data analysis. The primary goal of dimension reduction is to reduce the number of features or variables in a dataset while preserving its underlying structure and information. This process aids in improving computational efficiency, reducing the risk of overfitt..." current
  • 19:1619:16, 19 March 2023 diff hist +3,404‎ N Device ‎ Created page with "{{see also|Machine learning terms}} ==Device in Machine Learning== The term "device" in the context of machine learning generally refers to the hardware that is utilized for running machine learning algorithms, models, and training processes. Devices can range from basic personal computers to powerful, specialized processors designed specifically for machine learning tasks. In this article, we will explore the various types of devices used in machine learning, their char..." current
  • 19:1619:16, 19 March 2023 diff hist +3,081‎ N Derived label ‎ Created page with "{{see also|Machine learning terms}} ==Derived Label in Machine Learning== In machine learning, a '''derived label''' refers to the output variable that has been transformed or computed from the raw data in order to improve the performance or interpretability of a model. The process of creating derived labels often involves feature engineering and domain expertise to determine the most relevant or meaningful representations of the data. ===Feature Engineering and Derived..." current
  • 19:1519:15, 19 March 2023 diff hist +3,050‎ N Dense layer ‎ Created page with "{{see also|Machine learning terms}} ==Dense Layer in Machine Learning== A '''dense layer''' in machine learning, also referred to as a '''fully connected layer''' or simply '''FC layer''', is a fundamental architectural component of artificial neural networks (ANNs) and deep learning models. The dense layer functions as a linear transformation followed by an optional non-linear activation function, which facilitates the learning and representation of complex..." current
  • 19:1519:15, 19 March 2023 diff hist +2,955‎ N Demographic parity ‎ Created page with "{{see also|Machine learning terms}} ==Demographic Parity in Machine Learning== Demographic parity, also known as statistical parity, is a fairness metric used in machine learning to assess the performance of classification algorithms with respect to different demographic groups. It measures the extent to which an algorithm's predictions are unbiased with respect to a protected attribute, such as gender, race, or age. The goal of demographic parity is to ensure equal trea..." current
  • 19:1519:15, 19 March 2023 diff hist +3,580‎ N Deep neural network ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''deep neural network''' (DNN) is a type of artificial neural network (ANN) used in machine learning and deep learning that consists of multiple interconnected layers of artificial neurons. DNNs have gained significant attention in recent years due to their ability to effectively model complex and large-scale data, leading to breakthroughs in various domains, such as computer vision, natural langua..." current
  • 19:1519:15, 19 March 2023 diff hist +3,701‎ N Decision threshold ‎ Created page with "{{see also|Machine learning terms}} ==Definition== A '''decision threshold''' is a predefined value or cut-off point that determines the classification of instances in a machine learning algorithm. It is particularly useful in binary classification problems, where a model outputs a probability score for a given instance belonging to one of two classes (e.g., positive or negative). By comparing the probability score to the decision threshold, the model can assign the..." current
  • 19:1519:15, 19 March 2023 diff hist +3,583‎ N Decision boundary ‎ Created page with "{{see also|Machine learning terms}} ==Decision Boundary in Machine Learning== ===Definition=== In machine learning, a '''decision boundary''' is the surface that separates different classes or categories in a classification problem. It represents the boundary in the feature space where the algorithm makes decisions to classify input data points into their respective categories, based on the chosen classification model. A well-defined decision boundary can aid in accurate..." current
  • 19:1519:15, 19 March 2023 diff hist +4,473‎ N Data parallelism ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Data parallelism is a technique in machine learning that involves the simultaneous processing of data subsets across multiple computational resources to expedite training processes. It is particularly useful when dealing with large-scale datasets and computationally-intensive models, such as deep neural networks and other complex machine learning architectures. By distributing the workload across multiple resou..." current
  • 19:1519:15, 19 March 2023 diff hist +4,387‎ N Data analysis ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Data analysis in machine learning is the process of inspecting, cleaning, transforming, and modeling data to extract useful information, draw conclusions, and support decision-making. Machine learning is a subfield of artificial intelligence that focuses on designing algorithms and models that can learn from data to make predictions or decisions. In this context, data analysis is crucial in selecting appropriate fe..." current
  • 19:1419:14, 19 March 2023 diff hist +2,854‎ N Cross-validation ‎ Created page with "{{see also|Machine learning terms}} ==Cross-validation in Machine Learning== Cross-validation is a widely used technique in machine learning for estimating the performance of a predictive model. It aims to assess how well a model can generalize to an independent dataset by evaluating its performance on multiple subsets of the training data. This approach helps to mitigate overfitting, a common issue in machine learning where the model learns the training data too wel..." current
  • 19:1419:14, 19 March 2023 diff hist +3,615‎ N Cross-entropy ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Cross-entropy is a measure of the dissimilarity between two probability distributions, commonly used in machine learning, particularly in the context of training neural networks and other classification models. It serves as a widely used loss function in optimization algorithms, where the objective is to minimize the discrepancy between the predicted distribution and the true distribution of data. In this article,..." current
  • 19:1419:14, 19 March 2023 diff hist +3,445‎ N Coverage bias ‎ Created page with "{{see also|Machine learning terms}} ==Coverage Bias in Machine Learning== Coverage bias, also referred to as sampling bias, is a form of bias that occurs in machine learning when the data used to train a model does not accurately represent the target population or the problem space. This leads to models that may perform well on the training data, but poorly on the general population, ultimately resulting in biased predictions or decisions. The primary cause of coverage b..." current
  • 19:1419:14, 19 March 2023 diff hist +4,000‎ N Counterfactual fairness ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Counterfactual fairness is a concept in machine learning that aims to ensure that an algorithm's predictions are fair by considering hypothetical alternative outcomes under different conditions. The idea is to create models that make unbiased decisions by accounting for potential biases in data, which could lead to unfair treatment of individuals or groups. This concept is particularly important in the context of sensi..." current
  • 19:1419:14, 19 March 2023 diff hist +3,584‎ N Cost ‎ Created page with "{{see also|Machine learning terms}} ==Definition of Cost in Machine Learning== In the context of machine learning, the term '''cost''' refers to a metric that quantifies the difference between the predicted values generated by a model and the true values of the target variable. This metric, also known as the '''loss function''' or '''objective function''', is an essential component of the optimization process, as it guides the model's learning process to minimize the..." current
  • 19:1419:14, 19 March 2023 diff hist +3,087‎ N Convex set ‎ Created page with "{{see also|Machine learning terms}} ==Definition== In the context of machine learning, a '''convex set''' is a collection of points in a Euclidean space, such that for any two points within the set, the entire line segment connecting these points also lies within the set. Convex sets are fundamental to the study of optimization problems and are particularly important in machine learning due to their desirable properties, which often lead to efficient and robust a..." current
  • 19:1319:13, 19 March 2023 diff hist +3,162‎ N Co-training ‎ Created page with "{{see also|Machine learning terms}} ==Co-training in Machine Learning== Co-training is a semi-supervised learning technique in the domain of machine learning. It leverages both labeled and unlabeled data to improve the performance of classifiers. The technique was first introduced by Avrim Blum and Tom Mitchell in their 1998 paper, ''Combining Labeled and Unlabeled Data with Co-Training''. Co-training is particularly useful when labeled data is scarce, as it make..." current
  • 19:1319:13, 19 March 2023 diff hist +4,114‎ N Dataset API (tf.data) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''Dataset API (tf.data)''' is a versatile and high-performance input pipeline system designed for use with the TensorFlow machine learning framework. It facilitates the process of loading, preprocessing, and transforming data efficiently, thus allowing for optimal utilization of computational resources during model training and evaluation. The tf.data API is specifically tailored to address the requirements of..." current
  • 15:4615:46, 19 March 2023 diff hist +4,158‎ N Time series analysis ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Time series analysis is a statistical technique used to identify and analyze patterns and trends in data collected over time. It plays a critical role in various fields, including finance, economics, and meteorology. In machine learning, time series analysis is used to build predictive models that forecast future events based on historical data. The primary goal of time series analysis in machine learning is to extract..." current
  • 15:4615:46, 19 March 2023 diff hist +3,889‎ N Sketching ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, ''sketching'' refers to a technique used to reduce the dimensionality of data, while approximately preserving its essential properties. The primary goal of sketching is to facilitate the efficient processing and analysis of large datasets, which is crucial for the success of various machine learning algorithms. This article provides an overview of sketching techniques, their applic..." current
  • 15:4615:46, 19 March 2023 diff hist +4,162‎ N Similarity measure ‎ Created page with "{{see also|Machine learning terms}} ==Similarity Measure in Machine Learning== A '''similarity measure''' is a metric used in machine learning to quantify the degree of resemblance between two objects or data points. Similarity measures are essential for many machine learning tasks, such as clustering, classification, and recommender systems. These metrics facilitate the identification of similar instances and the organization of data into meaningful grou..." current
  • 15:4615:46, 19 March 2023 diff hist +3,645‎ N K-median ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''k-median''' algorithm is a popular unsupervised learning technique in the field of machine learning and data science. It is a variant of the well-known k-means clustering algorithm, which aims to partition a set of data points into ''k'' distinct clusters, where each data point belongs to the cluster with the nearest mean. The k-median algorithm, on the other hand, seeks to minimize the sum of distan..." current
  • 15:4615:46, 19 March 2023 diff hist +3,555‎ N K-means ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning and data analysis, '''k-means''' is an unsupervised clustering algorithm that partitions a dataset into '''k''' distinct clusters. The algorithm aims to minimize the sum of squared distances between the data points and the centroids of their corresponding clusters. It is widely used for a variety of applications such as pattern recognition, image segmentation, and customer segmentation...." current
  • 15:4615:46, 19 March 2023 diff hist +3,072‎ N Convex optimization ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Convex optimization is a subfield of mathematical optimization that deals with the minimization (or maximization) of convex functions over convex sets. In the context of machine learning, convex optimization plays a crucial role in finding the best model parameters, given a particular training dataset and a loss function. This field has gained significant attention in recent years, as it provides reliable and efficient..." current
  • 15:4515:45, 19 March 2023 diff hist +2,289‎ N Convex function ‎ Created page with "{{see also|Machine learning terms}} ==Definition== A '''convex function''' is a type of function that has particular mathematical properties, which are especially useful in the field of machine learning. Formally, a function ''f'' : ''R^n'' → ''R'' is called convex if, for all points ''x'' and ''y'' in its domain and for any scalar ''t'' in the range of 0 ≤ ''t'' ≤ 1, the following inequality holds: f(tx + (1 - t)y) ≤ tf(x) + (1 - t)f(y) This property ensur..." current
  • 15:4515:45, 19 March 2023 diff hist +3,452‎ N Convenience sampling ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Convenience sampling, also known as opportunity sampling or accidental sampling, is a non-probability sampling method utilized in various fields, including machine learning and statistics. It involves selecting a sample based on its accessibility and ease of collection, rather than following a random sampling process. Despite its limitations, convenience sampling can serve as a useful preliminary step for exploratory r..." current
  • 15:4515:45, 19 March 2023 diff hist +3,387‎ N Confirmation bias ‎ Created page with "{{see also|Machine learning terms}} ==Definition== Confirmation bias in machine learning refers to the phenomenon where a learning algorithm tends to prioritize or overfit data that confirms its pre-existing beliefs or hypotheses, while ignoring or underfitting data that contradicts them. This type of bias may arise from various sources, such as biased training data, biased model initialization, or biased model architectures. The existence of confirmation bias in machine..." current
  • 15:4515:45, 19 March 2023 diff hist +4,171‎ N Collaborative filtering ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Collaborative filtering (CF) is a widely-used technique in the field of machine learning, specifically in the domain of recommendation systems. It leverages the behavior or preferences of users within a community to make personalized recommendations for individual users. Collaborative filtering can be broadly categorized into two main approaches: user-based and item-based collaborative filtering. ==User-based Collabor..." current
  • 15:4515:45, 19 March 2023 diff hist +4,027‎ N Co-adaptation ‎ Created page with "{{see also|Machine learning terms}} ==Co-adaptation in Machine Learning== Co-adaptation is a phenomenon in machine learning that occurs when a model becomes too reliant on certain features or training examples, leading to a decrease in generalization performance. This article provides an overview of co-adaptation in the context of machine learning, its implications, and methods for mitigating its effects. ===Definition and Causes=== In machine learning, co-adaptation re..." current
  • 15:4515:45, 19 March 2023 diff hist +2,756‎ N Checkpoint ‎ Created page with "{{see also|Machine learning terms}} ==Definition== In machine learning, a '''checkpoint''' refers to a snapshot of the current state of a model during the training process. Checkpoints are primarily used for saving the model's weights and architecture, and sometimes additional information such as learning rates and optimizer states, at regular intervals or after a specified number of iterations. This allows the training process to be resumed from a previous state in..." current
  • 15:4415:44, 19 March 2023 diff hist +3,494‎ N Candidate sampling ‎ Created page with "{{see also|Machine learning terms}} ==Candidate Sampling in Machine Learning== Candidate sampling is a method used in machine learning, particularly in the context of training large-scale models. It is an optimization technique that reduces the computational complexity of learning algorithms by approximating the gradient of the loss function. In this section, we will explore the concept of candidate sampling, its motivation, and its applications in machine learning. ===..." current
  • 15:4415:44, 19 March 2023 diff hist +3,747‎ N Candidate generation ‎ Created page with "{{see also|Machine learning terms}} ==Candidate Generation in Machine Learning== Candidate generation is a critical process in machine learning (ML) that involves identifying a set of potential solutions, or "candidates," to solve a specific problem. This process is commonly used in various ML tasks, such as recommender systems, pattern mining, and search algorithms. The main goal of candidate generation is to efficiently explore the solution space and reduce..." current
  • 15:4415:44, 19 March 2023 diff hist +3,234‎ N Calibration layer ‎ Created page with "{{see also|Machine learning terms}} ==Calibration Layer in Machine Learning== Calibration is a crucial aspect of machine learning, specifically in the context of probabilistic models. The calibration layer refers to an additional component in a machine learning model designed to adjust the predicted probabilities so that they better match the true probabilities of the outcomes. This article discusses the concept of calibration in machine learning, its importance, and the..." current
  • 15:4415:44, 19 March 2023 diff hist +3,474‎ N Broadcasting ‎ Created page with "{{see also|Machine learning terms}} ==Broadcasting in Machine Learning== Broadcasting is a fundamental concept in machine learning, particularly in the context of linear algebra operations and array manipulation. It is used to perform element-wise operations on arrays of different shapes and dimensions without the need for explicit loops or reshaping, making it both computationally efficient and memory efficient. Broadcasting is widely implemented in various machine lear..." current
  • 15:4415:44, 19 March 2023 diff hist +3,180‎ N Boosting ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Boosting is an ensemble technique in machine learning that aims to improve the predictive accuracy of a model by combining the outputs of multiple weak learners. The concept of boosting was first introduced by Schapire (1990) and Freund (1995), who later developed the widely used algorithm AdaBoost (Adaptive Boosting) with Schapire in 1997. Boosting algorithms work by iteratively adjusting the weights of data point..." current
  • 15:4415:44, 19 March 2023 diff hist +2,760‎ N Bias (math) or bias term ‎ Created page with "{{see also|Machine learning terms}} ==Definition== In the context of Machine Learning, '''bias''' is a term used to describe the systematic error that a learning algorithm may have when trying to predict the true underlying relationship between input features and output targets. The '''bias term''', also known as the '''intercept''' or simply '''bias''', is a constant value added to the prediction function of a model, usually denoted as ''b'' or ''w₀'', which helps..." current
  • 15:4315:43, 19 March 2023 diff hist +3,930‎ N Batch normalization ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Batch normalization (BN) is a widely-used technique in machine learning and deep learning that helps to stabilize and accelerate the training of deep neural networks. It was first introduced by Sergey Ioffe and Christian Szegedy in their 2015 paper titled "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift" 1. The primary goal of batch normalization is to address th..." current
  • 15:4315:43, 19 March 2023 diff hist +2,853‎ N Baseline ‎ Created page with "{{see also|Machine learning terms}} ==Definition== In machine learning, the term '''baseline''' refers to a simple or naïve model that serves as a reference point against which the performance of more sophisticated models is compared. Establishing a baseline is essential in machine learning tasks, as it provides a starting point to measure the improvement achieved by more advanced techniques. Baselines can be established using simple statistical measures, random cho..." current
  • 15:4315:43, 19 March 2023 diff hist +3,655‎ N Average precision ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== '''Average precision''' is a widely used evaluation metric in the field of machine learning and information retrieval. It measures the effectiveness of an algorithm in retrieving relevant instances within a ranked list of items. This metric is particularly useful in scenarios where the list of items contains a large number of irrelevant items, such as in search engines and recommender systems. In this article, we w..." current
  • 15:4315:43, 19 March 2023 diff hist +3,550‎ N Cloud TPU ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Cloud TPU (Tensor Processing Unit) is a specialized hardware accelerator designed by Google for machine learning tasks, specifically tailored to accelerate the training and inference of TensorFlow models. It was introduced in 2017 and has since become an integral part of Google's Cloud Platform for researchers, developers, and businesses that require powerful and efficient processing capabilities for th..." current
  • 15:4315:43, 19 March 2023 diff hist +3,947‎ N Bayesian optimization ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Bayesian optimization is a global optimization technique in the field of machine learning, primarily used for hyperparameter tuning and expensive black-box optimization problems. The approach is based on the principles of Bayesian inference, where prior knowledge is updated with observed data to make better predictions about the unknown function. Bayesian optimization has been widely used in various applications, inclu..." current
  • 15:4315:43, 19 March 2023 diff hist +4,086‎ N Bayesian neural network ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''Bayesian neural network''' (BNN) is a probabilistic model in the field of machine learning that combines the flexibility and learning capabilities of artificial neural networks (ANNs) with the principles of Bayesian inference to make predictions and perform decision-making under uncertainty. BNNs extend ANNs by incorporating probability distributions over the weights and biases, enabling the network to..." current
  • 12:2512:25, 19 March 2023 diff hist +4,156‎ N Vanishing gradient problem ‎ Created page with "{{see also|Machine learning terms}} ==Vanishing Gradient Problem== The '''vanishing gradient problem''' is a significant challenge encountered in training deep neural networks, particularly in the context of backpropagation and gradient-based optimization algorithms. It arises due to the exponential decay of gradients as they are back-propagated through the layers, which results in very slow learning or, in some cases, no learning at all. This issue has hinde..." current
  • 12:1912:19, 19 March 2023 diff hist +3,438‎ N Translational invariance ‎ Created page with "{{see also|Machine learning terms}} ==Translational Invariance in Machine Learning== ===Introduction=== Translational invariance is a property of certain machine learning models, specifically in the field of image and signal processing, that allows the model to recognize patterns, regardless of their location in the input data. This property is particularly important for tasks like image recognition, where the model must identify features of interest irrespective of wher..." current
  • 12:1912:19, 19 March 2023 diff hist +2,861‎ N Timestep ‎ Created page with "{{see also|Machine learning terms}} ==Timestep in Machine Learning== A '''timestep''' in the context of machine learning refers to a specific instance in time or the unit of time progression used in various types of time-dependent algorithms. This concept is particularly relevant when working with time series data, sequential data, and when developing models for tasks such as natural language processing and reinforcement learning. In these scenarios,..." current
  • 12:1912:19, 19 March 2023 diff hist +3,708‎ N Subsampling ‎ Created page with "{{see also|Machine learning terms}} ==Definition== Subsampling, also known as '''downsampling''', is a technique used in machine learning and statistics to reduce the size of a dataset by selecting a smaller representative subset of the data. This process is applied to decrease the computational complexity and memory requirements of machine learning algorithms, while maintaining the quality of the obtained results. Subsampling is especially useful when dealing wi..."
  • 12:1912:19, 19 March 2023 diff hist +3,272‎ N Stride ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, '''stride''' refers to a parameter that determines the step size used during the convolution or pooling process in convolutional neural networks (CNNs). Stride plays a critical role in managing the spatial dimensions of feature maps, which can directly affect the model's efficiency and computational requirements. This article will explain the concept of stride, its role in CNNs, and its impact..." current
  • 12:1812:18, 19 March 2023 diff hist +2,769‎ N Spatial pooling ‎ Created page with "{{see also|Machine learning terms}} ==Spatial Pooling in Machine Learning== Spatial pooling, also known as spatial subsampling, is a technique utilized in various machine learning algorithms, particularly in the field of Convolutional Neural Networks (CNNs). It is designed to reduce the spatial dimensions of feature maps while retaining significant information. Spatial pooling is essential in creating a more compact representation of the input data, which consequentl..." current
  • 12:1812:18, 19 March 2023 diff hist +3,302‎ N Size invariance ‎ Created page with "{{see also|Machine learning terms}} ==Size Invariance in Machine Learning== Size invariance is a property of machine learning models and algorithms that allows them to be robust to variations in the size or scale of input data. This property is particularly important in tasks such as image recognition and object detection, where the same object may appear in different sizes and scales within the input data. Achieving size invariance can greatly improve the generalization..." current
  • 12:1812:18, 19 March 2023 diff hist +3,280‎ N Sequence model ‎ Created page with "{{see also|Machine learning terms}} ==Sequence Models in Machine Learning== Sequence models in machine learning are a class of computational models that deal with data represented as sequences or time series. These models are designed to capture the underlying patterns, dependencies, and structures in sequential data, which can be critical for tasks such as natural language processing, speech recognition, and time series forecasting. ===Types of Sequence Models=== There..." current
  • 12:1812:18, 19 March 2023 diff hist +3,403‎ N Rotational invariance ‎ Created page with "{{see also|Machine learning terms}} ==Rotational Invariance in Machine Learning== Rotational invariance, in the context of machine learning, refers to the ability of a model or algorithm to recognize and accurately process data regardless of the orientation or rotation of the input. This property is particularly important in computer vision and pattern recognition tasks, where the same object or pattern can appear in different orientations within the input data. ===Back..." current
  • 12:1812:18, 19 March 2023 diff hist +3,282‎ N Recurrent neural network ‎ Created page with "{{see also|Machine learning terms}} ==Recurrent Neural Network== A '''recurrent neural network''' ('''RNN''') is a class of artificial neural network designed to model sequential data by maintaining an internal state that can persist information across time steps. RNNs are particularly effective in tasks that involve time series data or sequences, such as natural language processing, speech recognition, and time series prediction. ===Structure and Function=== Recurr..." current
  • 12:1812:18, 19 March 2023 diff hist +2,975‎ N Pooling ‎ Created page with "{{see also|Machine learning terms}} ==Pooling in Machine Learning== Pooling is a technique employed in the field of machine learning, specifically in the context of convolutional neural networks (CNNs). The primary goal of pooling is to reduce the spatial dimensions of input data, while maintaining essential features and reducing computational complexity. It is an essential component in the processing pipeline of CNNs and aids in achieving translational invariance, w..." current
  • 12:1712:17, 19 March 2023 diff hist +3,603‎ N Hierarchical clustering ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Hierarchical clustering is a method of cluster analysis in machine learning and statistics used to group similar objects into clusters based on a measure of similarity or distance between them. This approach organizes data into a tree-like structure, called a dendrogram, that represents the nested hierarchical relationships among the clusters. Hierarchical clustering can be categorized into two primary appr..." current
  • 12:1712:17, 19 March 2023 diff hist +3,276‎ N Gradient clipping ‎ Created page with "{{see also|Machine learning terms}} ==Gradient Clipping in Machine Learning== Gradient clipping is a technique employed in machine learning, specifically during the training of deep neural networks, to mitigate the effect of exploding gradients. Exploding gradients occur when the gradients of the model parameters become excessively large, leading to instabilities and impairments in the learning process. Gradient clipping aids in the regularization of the learning process..." current
  • 12:1712:17, 19 March 2023 diff hist +2,788‎ N Forget gate ‎ Created page with "{{see also|Machine learning terms}} ==Forget Gate in Machine Learning== The '''forget gate''' is an essential component in machine learning models, particularly in Long Short-Term Memory (LSTM) neural networks. The primary function of the forget gate is to control the flow of information, enabling the network to learn long-term dependencies by regulating which information to retain or discard from the previous time step. This capability is crucial for sequence-to-sequenc..." current
  • 12:1712:17, 19 March 2023 diff hist +4,163‎ N Exploding gradient problem ‎ Created page with "{{see also|Machine learning terms}} ==Exploding Gradient Problem== The exploding gradient problem is a phenomenon encountered in the training of certain types of artificial neural networks, particularly deep networks and recurrent neural networks (RNNs). This problem occurs when the gradients of the loss function with respect to the model's parameters grow exponentially during the backpropagation process, leading to unstable learning dynamics and suboptimal model per..." current
  • 12:1712:17, 19 March 2023 diff hist +2,788‎ N Divisive clustering ‎ Created page with "{{see also|Machine learning terms}} ==Divisive Clustering== Divisive clustering, also referred to as "top-down" clustering, is a hierarchical clustering method employed in machine learning and data analysis. It involves recursively partitioning a dataset into smaller subsets, where each subset represents a cluster. This process starts with a single cluster encompassing all data points and proceeds by iteratively dividing the clusters until a certain stopping criterion is..." current
  • 12:1712:17, 19 March 2023 diff hist +3,965‎ N Clustering ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== '''Clustering''' is a technique in the field of machine learning and data mining that involves the grouping of similar data points or objects into clusters, based on some form of similarity or distance metric. The goal of clustering is to identify underlying patterns or structures in data, enabling efficient data representation, classification, and interpretation. Clustering is an unsupervised learning method,..." current
  • 12:1612:16, 19 March 2023 diff hist +2,883‎ N Centroid ‎ Created page with "{{see also|Machine learning terms}} ==Centroid in Machine Learning== The '''centroid''' is a central concept in machine learning, particularly in the realm of clustering algorithms. It is a geometrical point that represents the average of all data points in a particular cluster or group. Centroids are used to calculate the similarity or distance between data points, which helps in grouping similar data points together and separating dissimilar ones. ===Definition=== In..." current
  • 12:1612:16, 19 March 2023 diff hist +3,428‎ N Centroid-based clustering ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Centroid-based clustering is a class of machine learning algorithms that group data points into clusters based on the similarity of their features. These algorithms rely on the computation of centroids, which represent the central points of clusters in the feature space. The most well-known centroid-based clustering algorithm is the K-means algorithm. ==Centroid-based Clustering Algorithms== Centroid-based clu..." current
  • 12:1512:15, 19 March 2023 diff hist +3,824‎ N RNN ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, '''Recurrent Neural Networks''' ('''RNNs''') are a class of artificial neural networks that are designed to process sequences of data. RNNs have gained significant popularity in recent years, particularly for tasks involving natural language processing, time series analysis, and speech recognition. Unlike traditional feedforward neural networks, RNNs possess a unique architecture t..." current
  • 12:1312:13, 19 March 2023 diff hist +3,691‎ N Long Short-Term Memory (LSTM) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Long Short-Term Memory (LSTM) is a type of recurrent neural network (RNN) architecture designed to address the limitations of traditional RNNs in learning long-term dependencies. LSTM networks were introduced by Hochreiter and Schmidhuber in 1997<ref name="Hochreiter1997">{{Cite journal|last1=Hochreiter|first1=Sepp|last2=Schmidhuber|first2=Jürgen|title=Long short-term memory|journal=Neural Computation|date=1997|volume..." current
  • 12:1312:13, 19 March 2023 diff hist +3,537‎ N LSTM ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Long Short-Term Memory (LSTM) is a type of recurrent neural network (RNN) architecture that is specifically designed to handle long-range dependencies in sequential data. It was first introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997 to address the limitations of traditional RNNs, such as the vanishing gradient problem. LSTMs have since become a popular choice for various applications in machine lea..." current
  • 06:2406:24, 19 March 2023 diff hist +2,983‎ N Trajectory ‎ Created page with "{{see also|Machine learning terms}} ==Trajectory in Machine Learning== Trajectory in machine learning refers to the sequence of decisions, actions, and states that a model undergoes as it learns to solve a particular problem. The concept of trajectory is especially important in the context of reinforcement learning and optimization algorithms, where an agent iteratively refines its knowledge and actions in order to achieve better performance. ===Reinforcement Le..." current
  • 06:2406:24, 19 March 2023 diff hist +2,857‎ N Termination condition ‎ Created page with "{{see also|Machine learning terms}} ==Termination Condition in Machine Learning== In the field of machine learning, a termination condition, also known as stopping criterion, refers to a set of predefined criteria that determines when an optimization algorithm should cease its search for the optimal solution. Termination conditions are essential to prevent overfitting, underfitting, and excessive computational resources consumption. They help ensure that the learning..." current
  • 06:2406:24, 19 March 2023 diff hist +4,119‎ N Target network ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a '''target network''' is a critical component of certain algorithms, primarily used to improve the stability of learning processes. It is predominantly associated with reinforcement learning methods, such as Deep Q-Networks (DQN). This article discusses the purpose and significance of target networks, along with the principles guiding their function and their role in stabilizing l..." current
  • 06:2406:24, 19 March 2023 diff hist +3,669‎ N Tabular Q-learning ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Tabular Q-learning is a fundamental reinforcement learning algorithm used in the field of machine learning. It is a value-based approach that helps agents learn optimal policies through interaction with their environment. The algorithm aims to estimate the expected cumulative reward or ''value'' for each state-action pair in a discrete environment. ==Q-learning Algorithm== Q-learning is a model-free, off-polic..." current
  • 06:2406:24, 19 March 2023 diff hist +3,637‎ N State ‎ Created page with "{{see also|Machine learning terms}} ==State in Machine Learning== State in machine learning refers to the internal representation of information or data that a model uses to make decisions or predictions. In the context of machine learning, a state is a snapshot of the variables, parameters, and information at a given point in time, during the learning or inference process. This state is crucial in determining the subsequent actions or decisions made by the model. ===Ty..." current
  • 06:2406:24, 19 March 2023 diff hist +2,844‎ N State-action value function ‎ Created page with "{{see also|Machine learning terms}} ==State-Action Value Function in Machine Learning== In the field of machine learning, particularly in the area of reinforcement learning, the state-action value function, often denoted as Q(s, a), is a crucial concept that helps agents learn optimal behavior by quantifying the expected return or long-term value of taking a specific action a in a given state s. ===Definition=== The state-action value function, or Q-function, is formall..." current
  • 06:2306:23, 19 March 2023 diff hist +3,479‎ N Reward ‎ Created page with "{{see also|Machine learning terms}} ==Reward in Machine Learning== In the field of machine learning, the concept of '''reward''' plays a crucial role in the process of learning from interaction with the environment. Reward is used as a measure of success, guiding the learning process in reinforcement learning algorithms. The objective of reinforcement learning algorithms is to maximize the cumulative reward over time. This allows the learning agent to evaluate it..." current
  • 06:2306:23, 19 March 2023 diff hist +3,133‎ N Return ‎ Created page with "{{see also|Machine learning terms}} ==Return in Machine Learning== In the context of machine learning, the term "return" refers to the cumulative reward or outcome of a series of decisions or actions taken by an agent in a reinforcement learning (RL) environment. Reinforcement learning is a subfield of machine learning in which an agent learns to make decisions by interacting with an environment to achieve a certain goal, such as maximizing a reward function. The return..." current
  • 06:2306:23, 19 March 2023 diff hist +3,485‎ N Replay buffer ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the realm of machine learning, the '''replay buffer''' is a crucial component in a specific class of algorithms known as reinforcement learning (RL). Reinforcement learning is a branch of machine learning that involves training an agent to learn an optimal behavior by interacting with its environment, where it receives feedback in the form of rewards or penalties. The replay buffer is primarily used in a cla..." current
  • 06:2306:23, 19 March 2023 diff hist +4,075‎ N Reinforcement learning (RL) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Reinforcement learning (RL) is a subfield of machine learning that focuses on training algorithms to make decisions by interacting with an environment. The primary objective in RL is to learn an optimal behavior or strategy, often called a ''policy'', which enables an agent to maximize its cumulative reward over time. RL algorithms are characterized by the use of trial-and-error and delayed feedback, making them pa..." current
  • 06:2306:23, 19 March 2023 diff hist +3,707‎ N Random policy ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A random policy, in the context of machine learning, refers to a decision-making process where actions are selected with equal probability, regardless of the state or history of the environment. This approach is typically used as a baseline in reinforcement learning, to compare the performance of more sophisticated policies that attempt to learn the optimal strategy for a given problem. In this article, we will discuss..." current
  • 06:2306:23, 19 March 2023 diff hist +3,572‎ N Landmarks ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, the term "landmarks" is often used in the context of manifold learning and dimensionality reduction techniques, where the goal is to uncover the underlying structure of high-dimensional data by representing it in a lower-dimensional space. One popular method for achieving this is by using landmark-based methods, which rely on a set of carefully selected reference points (i.e., landmarks) to capture..." current
  • 06:2206:22, 19 March 2023 diff hist +3,805‎ N Keypoints ‎ Created page with "{{see also|Machine learning terms}} ==Keypoints in Machine Learning== In the field of machine learning, keypoints play an essential role in facilitating the understanding and analysis of data. These distinctive, informative points in data serve as important elements in various machine learning applications, such as image recognition, computer vision, and natural language processing. ===Definition=== Keypoints, also known as interest points or salient points, are unique..." current
  • 06:2206:22, 19 March 2023 diff hist +3,392‎ N Intersection over union (IoU) ‎ Created page with "{{see also|Machine learning terms}} ==Intersection over Union (IoU)== Intersection over Union (IoU) is a widely used metric for evaluating the performance of object detection and instance segmentation algorithms in machine learning. It measures the degree of overlap between two bounding boxes or shapes, often representing the predicted output and the ground truth. IoU is particularly important in tasks such as object detection, semantic segmentation, and instance segment..." current
  • 06:2206:22, 19 March 2023 diff hist +4,090‎ N Image recognition ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Image recognition, also referred to as Computer Vision or object recognition, is a subfield of Machine Learning and Artificial Intelligence that deals with the ability of a computer system or model to identify and classify objects or features within digital images. The primary goal of image recognition is to teach machines to emulate the human visual system, allowing them to extract useful information from..." current
  • 06:2206:22, 19 March 2023 diff hist +3,944‎ N Downsampling ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Downsampling is a technique used in machine learning and signal processing to reduce the amount of data being processed. It involves systematically selecting a smaller subset of data points from a larger dataset, thereby reducing its size and complexity. Downsampling can be applied in various contexts, such as image processing, time series analysis, and natural language processing, among others. The primary goal of dow..." current
  • 06:2206:22, 19 March 2023 diff hist +3,395‎ N Depthwise separable convolutional neural network (sepCNN) ‎ Created page with "{{see also|Machine learning terms}} ==Depthwise Separable Convolutional Neural Network (SepCNN)== Depthwise Separable Convolutional Neural Networks (SepCNNs) are a variant of Convolutional Neural Networks (CNNs) designed to reduce computational complexity and memory usage while preserving performance in various computer vision tasks. SepCNNs achieve this by factorizing the standard convolution operation into two separate steps: depthwise convolution and pointwise con..." current
  • 06:2206:22, 19 March 2023 diff hist +3,821‎ N Data augmentation ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, ''data augmentation'' refers to the process of expanding the size and diversity of a training dataset by applying various transformations and manipulations. The primary goal of data augmentation is to improve the generalization capabilities of machine learning models, thus enhancing their performance on unseen data. This article delves into the principles, techniques, and applicati..." current
  • 06:2206:22, 19 March 2023 diff hist +3,189‎ N Convolutional operation ‎ Created page with "{{see also|Machine learning terms}} ==Convolutional Operation in Machine Learning== The convolutional operation, often used in the context of Convolutional Neural Networks (CNNs), is a core element in modern machine learning techniques for image and signal processing. It involves the application of mathematical functions known as ''convolutions'' to input data, enabling the extraction of important features, patterns, and structures from raw data. This operation h..." current
  • 06:2106:21, 19 March 2023 diff hist +3,837‎ N Convolutional neural network ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''convolutional neural network''' (CNN) is a type of artificial neural network specifically designed for processing grid-like data, such as images, speech signals, and time series data. CNNs have achieved remarkable results in various tasks, particularly in the field of image and speech recognition. The architecture of CNNs is inspired by the organization of the animal visual cortex and consists of multiple layers o..." current
  • 06:2106:21, 19 March 2023 diff hist +3,121‎ N Convolutional layer ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, a '''convolutional layer''' is a key component of Convolutional Neural Networks (CNNs) that specializes in processing and analyzing grid-like data structures, such as images. It is designed to automatically learn and detect local patterns and features through the use of convolutional filters. These filters, also known as kernels, are applied to the input data in a sliding-window manner, ena..." current
  • 06:2106:21, 19 March 2023 diff hist +3,155‎ N Convolutional filter ‎ Created page with "{{see also|Machine learning terms}} ==Convolutional Filters in Machine Learning== A '''convolutional filter''' (also known as a '''kernel''' or '''feature detector''') is a fundamental component of Convolutional Neural Networks (CNNs), a class of deep learning models specifically designed for processing grid-like data, such as images and time-series data. Convolutional filters are used to perform a mathematical operation called '''convolution''' on input data to dete..." current
  • 06:2106:21, 19 March 2023 diff hist +3,694‎ N Convolution ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Convolution is a mathematical operation widely used in the field of machine learning, especially in the domain of deep learning and convolutional neural networks (CNNs). The operation involves the element-wise multiplication and summation of two matrices or functions, typically an input matrix (or image) and a kernel (or filter). The primary purpose of convolution is to extract features from the input data,..." current
  • 06:2106:21, 19 March 2023 diff hist +2,657‎ N Bounding box ‎ Created page with "{{see also|Machine learning terms}} ==Bounding Box in Machine Learning== ===Definition=== A '''bounding box''' is a rectangular box used in machine learning and computer vision to represent the spatial extent of an object within an image or a sequence of images. It is generally defined by the coordinates of its top-left corner and its width and height. Bounding boxes are widely employed in object detection, localization, and tracking tasks, where the objective is..." current
  • 06:2106:21, 19 March 2023 diff hist +2,966‎ N MNIST ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''Modified National Institute of Standards and Technology (MNIST)''' dataset is a large collection of handwritten digits that has been widely used as a benchmark for evaluating the performance of various machine learning algorithms, particularly in the field of image recognition and computer vision. MNIST, introduced by Yann LeCun, Corinna Cortes, and Christopher J.C. Burges in 1998, has played a pivot..." current

18 March 2023

  • 21:5721:57, 18 March 2023 diff hist +4,215‎ N Wisdom of the crowd ‎ Created page with "{{see also|Machine learning terms}} ==Wisdom of the Crowd in Machine Learning== The ''Wisdom of the Crowd'' is a phenomenon that refers to the collective intelligence and decision-making ability of a group, which often leads to more accurate and reliable outcomes than individual judgments. In the context of machine learning, this concept is employed to improve the performance of algorithms by aggregating the predictions of multiple models, a technique commonly known as [..." current
  • 21:5721:57, 18 March 2023 diff hist +3,827‎ N Variable importances ‎ Created page with "{{see also|Machine learning terms}} ==Variable Importance in Machine Learning== Variable importance, also referred to as feature importance, is a concept in machine learning that quantifies the relative significance of individual variables, or features, in the context of a given predictive model. The primary goal of assessing variable importance is to identify and understand the most influential factors in a model's decision-making process. This information can be us..." current
  • 21:5721:57, 18 March 2023 diff hist +2,927‎ N Threshold (for decision trees) ‎ Created page with "{{see also|Machine learning terms}} ==Threshold in Decision Trees== In the field of machine learning, a decision tree is a widely used model for representing hierarchical relationships between a set of input features and a target output variable. The decision tree is composed of internal nodes, which test an attribute or feature, and leaf nodes, which represent a class or output value. The threshold is a critical parameter in decision tree algorithms that determines..." current
  • 21:5621:56, 18 March 2023 diff hist +2,916‎ N Splitter ‎ Created page with "{{see also|Machine learning terms}} ==Splitter in Machine Learning== A '''splitter''' in the context of machine learning refers to a method or technique used to divide a dataset into subsets, typically for the purposes of training, validation, and testing. The process of splitting data helps to prevent overfitting, generalizes the model, and provides a more accurate evaluation of a model's performance. Various techniques exist for splitting data, such as k-fold cross-val..." current
  • 21:5621:56, 18 March 2023 diff hist +3,523‎ N Split ‎ Created page with "{{see also|Machine learning terms}} ==Overview== In machine learning, the term ''split'' generally refers to the process of dividing a dataset into two or more non-overlapping parts, typically for the purposes of training, validation, and testing a machine learning model. These distinct subsets enable the evaluation and fine-tuning of model performance, helping to prevent overfitting and allowing for an unbiased estimation of the model's ability to generalize to unse..." current
  • 21:5621:56, 18 March 2023 diff hist +2,960‎ N Shrinkage ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== '''Shrinkage''' in machine learning is a regularization technique that aims to prevent overfitting in statistical models by adding a constraint or penalty to the model's parameters. Shrinkage methods reduce the complexity of the model by pulling its coefficient estimates towards zero, leading to more robust and interpretable models. Popular shrinkage methods include Ridge Regression and Lasso Regression. ==Shrinka..." current
  • 21:5621:56, 18 March 2023 diff hist +3,775‎ N Sampling with replacement ‎ Created page with "{{see also|Machine learning terms}} ==Sampling with Replacement in Machine Learning== In machine learning, sampling with replacement refers to a statistical technique used for selecting samples from a given dataset or population during the process of model training or evaluation. This method allows for a sample to be selected multiple times, as each time it is drawn, it is returned to the pool of possible samples. In this article, we will discuss the implications of samp..." current
  • 21:5621:56, 18 March 2023 diff hist +3,687‎ N Root ‎ Created page with "{{see also|Machine learning terms}} ==Root in Machine Learning== The term "root" in machine learning may refer to different concepts, depending on the context in which it is being used. Two of the most common meanings are related to decision trees and the root mean square error (RMSE) in regression models. ===Decision Trees=== In the context of decision trees, the root refers to the starting point of the tree, where the first split or decision is made. Decision trees ar..." current
  • 21:5621:56, 18 March 2023 diff hist +3,423‎ N Random forest ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Random Forest is a versatile and powerful ensemble learning method used in machine learning. It is designed to improve the accuracy and stability of predictions by combining multiple individual decision trees, each of which is trained on a random subset of the available data. This technique helps to overcome the limitations of a single decision tree, such as overfitting and high variance, while preserving the b..." current
  • 21:5521:55, 18 March 2023 diff hist +3,253‎ N Policy ‎ Created page with "{{see also|Machine learning terms}} ==Policy in Machine Learning== In the field of machine learning, a policy refers to a decision-making function that maps a given state or input to an action or output. A policy is often denoted by the symbol π (pi) and is central to the process of learning and decision-making in various machine learning algorithms, particularly in the realm of reinforcement learning. ===Reinforcement Learning and Policies=== Reinforcement lea..." current
  • 21:5521:55, 18 March 2023 diff hist +3,580‎ N Permutation variable importances ‎ Created page with "{{see also|Machine learning terms}} ==Permutation Variable Importance== Permutation Variable Importance (PVI) is a technique used in machine learning to evaluate the importance of individual features in a predictive model. This method estimates the impact of a specific feature on the model's predictive accuracy by assessing the changes in model performance when the values of that feature are permuted randomly. The main advantage of PVI is its applicability to a wide..." current
  • 21:5521:55, 18 March 2023 diff hist +4,116‎ N Greedy policy ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning and reinforcement learning, a '''greedy policy''' is a decision-making strategy that selects the action with the highest immediate value or reward, without considering the long-term consequences or future states. This approach can be effective in specific scenarios, but may fail to achieve optimal solutions in complex environments. This article will discuss the concept of greedy policy,..." current
  • 21:5521:55, 18 March 2023 diff hist +4,173‎ N Experience replay ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Experience Replay is a technique used in machine learning, particularly in reinforcement learning, to improve the efficiency and stability of the learning process. It is widely used in algorithms such as Deep Q-Network (DQN), Asynchronous Advantage Actor-Critic (A3C), and other deep reinforcement learning methods. Experience Replay allows the agent to store past experiences in a memory buffer and then reuse the..." current
  • 21:5521:55, 18 March 2023 diff hist +3,508‎ N Epsilon greedy policy ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''Epsilon-Greedy Policy''' is a widely used exploration-exploitation strategy in Reinforcement Learning (RL) algorithms. It helps balance the decision-making process between exploring new actions and exploiting the knowledge acquired thus far in order to maximize the expected cumulative rewards. ==Exploration and Exploitation Dilemma== In the context of RL, an agent interacts with an environment and learns an..." current
  • 21:5521:55, 18 March 2023 diff hist +3,334‎ N Episode ‎ Created page with "{{see also|Machine learning terms}} ==Episode in Machine Learning== An '''episode''' in machine learning refers to a sequence of steps or interactions that an agent goes through within an environment. It is a fundamental concept in the field of Reinforcement Learning (RL), where the learning process relies on trial and error. The term "episode" describes the process from the initial state until a termination condition is reached, often involving the completion of a t..." current
  • 21:5421:54, 18 March 2023 diff hist +4,076‎ N Environment ‎ Created page with "{{see also|Machine learning terms}} ==Environment in Machine Learning== The environment in machine learning is a term that refers to the contextual setting, data, and external factors that influence the training, performance, and evaluation of a machine learning algorithm. It includes a wide range of aspects, such as the type of data used, data preprocessing techniques, and the problem domain. ==Data Types and Sources== ===Structured Data=== Structured data is informati..."
  • 21:5421:54, 18 March 2023 diff hist +2,274‎ N Critic ‎ Created page with "{{see also|Machine learning terms}} ==Critic in Machine Learning== In machine learning, a critic refers to a component or model that evaluates and provides feedback on the performance of another model, typically a learning agent. The term is commonly associated with reinforcement learning and actor-critic methods, where it is used to estimate the value function or provide a performance gradient for the learning agent. ===Reinforcement Learning and Critic=== Re..." current
  • 21:5421:54, 18 March 2023 diff hist +3,645‎ N Q-learning ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== '''Q-learning''' is a model-free, reinforcement learning algorithm in the field of machine learning. The algorithm aims to train an agent to make optimal decisions in a given environment by learning the best action-selection policy. Q-learning is particularly well-suited for problems with a large state-action space and is widely used in robotics, control systems, and game playing. ==Background== ===Reinforcement L..." current
  • 21:5421:54, 18 March 2023 diff hist +3,046‎ N Q-function ‎ Created page with "{{see also|Machine learning terms}} ==Q-function in Machine Learning== The Q-function, also known as the state-action value function or simply Q-value, is a fundamental concept in the field of Reinforcement Learning (RL). It represents the expected cumulative reward an agent will receive from a specific state by taking a certain action and then following a given policy. Mathematically, the Q-function is denoted as Q(s, a), where 's' represents the state and 'a' repre..." current
  • 21:5421:54, 18 March 2023 diff hist +3,011‎ N Markov property ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''Markov property''' is a fundamental concept in the fields of probability theory, statistics, and machine learning. It is named after the Russian mathematician Andrey Markov, who first formalized the idea in the early 20th century. The Markov property describes a stochastic process, where the future state of a system depends only on its current state and not on its previous history. ==Markov Chains== ===Defi..." current
  • 21:5421:54, 18 March 2023 diff hist +3,569‎ N Markov decision process (MDP) ‎ Created page with "{{see also|Machine learning terms}} ==Markov Decision Process (MDP)== Markov Decision Process (MDP) is a mathematical model in machine learning and decision theory, used for modeling decision-making problems in stochastic environments. MDPs provide a formal framework for decision-making under uncertainty, taking into account the probabilistic nature of state transitions, the rewards or penalties associated with actions, and the influence of the decision-maker's choices o..." current
  • 21:5321:53, 18 March 2023 diff hist +3,757‎ N Deep Q-Network (DQN) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, '''Deep Q-Network (DQN)''' is an algorithm that combines the concepts of deep learning and reinforcement learning to create a robust and efficient model for solving complex problems. The DQN algorithm, introduced by researchers at DeepMind in 2013<ref>{{cite journal |title=Playing Atari with Deep Reinforcement Learning |author=Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Io..." current
  • 21:5321:53, 18 March 2023 diff hist +3,905‎ N DQN ‎ Created page with "{{see also|Machine learning terms}} ==Overview== The '''Deep Q-Network''' ('''DQN''') is an advanced model-free, online, off-policy reinforcement learning (RL) technique that combines the strengths of both deep neural networks and Q-learning. DQN was proposed by Volodymyr Mnih, et al. in their 2015 paper Playing Atari with Deep Reinforcement Learning. The primary motivation behind DQN was to address the challenges of high-dimensional..." current
  • 21:5321:53, 18 March 2023 diff hist +3,399‎ N Bellman equation ‎ Created page with "{{see also|Machine learning terms}} ==Bellman Equation in Machine Learning== The Bellman equation, named after its inventor Richard Bellman, is a fundamental concept in the field of reinforcement learning (RL), a subdomain of machine learning. The equation describes the optimal value function, which is a key element in solving many sequential decision-making problems. The Bellman equation serves as the foundation for various RL algorithms, including value iteration, poli..." current
  • 19:0419:04, 18 March 2023 diff hist +3,026‎ N Word embedding ‎ Created page with "{{see also|Machine learning terms}} ==Word Embedding in Machine Learning== Word embedding is a technique used in natural language processing (NLP), a subfield of machine learning, which focuses on enabling machines to understand, interpret, and generate human languages. Word embedding refers to the process of representing words in a numerical format, specifically as high-dimensional vectors in a continuous vector space. These vector representations capture the semantic m..." current
  • 19:0419:04, 18 March 2023 diff hist +3,239‎ N Unidirectional language model ‎ Created page with "{{see also|Machine learning terms}} ==Unidirectional Language Model== A unidirectional language model is a type of language model used in machine learning, specifically within the field of natural language processing (NLP). These models are designed to process and generate human-like text based on the input data they are provided. They function by estimating the probability of a word or token occurring within a given context, only taking into account the precedin..." current
  • 19:0419:04, 18 March 2023 diff hist +3,705‎ N Unidirectional ‎ Created page with "{{see also|Machine learning terms}} ==Unidirectional Models in Machine Learning== In the field of machine learning, unidirectional models refer to a specific class of algorithms that process input data in a single direction, from the beginning to the end. These models, in contrast to bidirectional models, do not possess the ability to consider information from later portions of the input data while processing earlier parts. Unidirectional models are particularly rele..." current
  • 19:0419:04, 18 March 2023 diff hist +2,548‎ N Trigram ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning and natural language processing (NLP), a '''trigram''' is a continuous sequence of three items from a given sample of text or speech. Trigrams are a type of n-gram, where ''n'' represents the number of items in the sequence. N-grams are used in various language modeling and feature extraction tasks to analyze and predict text data. ==Language Modeling== ===Probability Estimatio..."
  • 19:0419:04, 18 March 2023 diff hist +3,978‎ N Token ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a '''token''' refers to a fundamental unit of text or data that is used for processing, analysis, or modeling. Tokens are essential components of natural language processing (NLP) systems, which aim to enable computers to understand, interpret, and generate human language. In this context, a token can represent a single word, a character, a subword, or any other unit of text that serve..." current
  • 19:0319:03, 18 March 2023 diff hist +3,571‎ N Out-of-bag evaluation (OOB evaluation) ‎ Created page with "{{see also|Machine learning terms}} ==Out-of-Bag Evaluation== Out-of-Bag (OOB) evaluation is a model validation technique commonly used in ensemble learning methods, particularly in bagging algorithms such as Random Forests. The main idea behind OOB evaluation is to use a portion of the training data that was not used during the construction of individual base learners, for the purpose of estimating the performance of the ensemble without resorting to a separ..." current
  • 19:0319:03, 18 March 2023 diff hist +3,379‎ N Oblique condition ‎ Created page with "{{see also|Machine learning terms}} ==Oblique Condition in Machine Learning== The oblique condition refers to a specific type of decision boundary used in machine learning algorithms, particularly in classification tasks. Decision boundaries are mathematical functions or models that separate different classes or categories in the input data. Oblique decision boundaries are characterized by their non-orthogonal orientation, allowing for more complex and flexible separatio..." current
  • 19:0319:03, 18 March 2023 diff hist +4,339‎ N Non-binary condition ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the context of machine learning, the term "non-binary condition" refers to a situation where the output or target variable of a predictive model is not restricted to two distinct classes or labels. This contrasts with binary classification tasks, where the goal is to predict one of two possible outcomes. Non-binary conditions arise in various types of problems, such as multi-class classification, multi-label classif..." current
  • 19:0319:03, 18 March 2023 diff hist +3,561‎ N Node (decision tree) ‎ Created page with "{{see also|Machine learning terms}} ==Definition== In machine learning, a '''node''' refers to a point within a decision tree at which a decision is made based on the input data. Decision trees are hierarchical, tree-like structures used to model decisions and their possible consequences, including the chance event outcomes, resource costs, and utility. Nodes in decision trees can be of three types: root node, internal node, and leaf node. ===Root Node=== The ''..." current
  • 19:0319:03, 18 March 2023 diff hist +3,425‎ N Leaf ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, a '''leaf''' is an essential component of decision tree-based algorithms, such as decision trees, random forests, and gradient boosting machines. A leaf, also known as a terminal node, is the endpoint of a branch in a decision tree, which is used to make predictions based on a set of input features. In this article, we will discuss the concept of leaves, their role in decision tree-..." current
  • 19:0319:03, 18 March 2023 diff hist +3,049‎ N Information gain ‎ Created page with "{{see also|Machine learning terms}} ==Information Gain in Machine Learning== Information gain is a crucial concept in the field of machine learning, particularly when dealing with decision trees and feature selection. It is a metric used to measure the decrease in uncertainty or entropy after splitting a dataset based on a particular attribute. The primary goal of information gain is to identify the most informative attribute, which can be used to construct an effect..." current
  • 19:0319:03, 18 March 2023 diff hist +4,001‎ N Inference path ‎ Created page with "{{see also|Machine learning terms}} ==Inference Path in Machine Learning== The '''inference path''' in machine learning refers to the process of applying a trained model to new, unseen data in order to make predictions or decisions. This process is critical in realizing the practical applications of machine learning models, as it enables them to generalize their learned knowledge to real-world situations. ==Training and Inference Phases== Machine learning models typical..." current
  • 19:0219:02, 18 March 2023 diff hist +2,994‎ N In-set condition ‎ Created page with "{{see also|Machine learning terms}} ==In-set Condition in Machine Learning== The in-set condition is a concept in the field of machine learning that refers to the circumstance in which the training data used to train a machine learning model is representative of the data distribution that the model will encounter during real-world applications. This concept is related to the generalization performance of a model, which refers to its ability to perform well on unseen..." current
  • 19:0219:02, 18 March 2023 diff hist +3,910‎ N Gradient boosting ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Gradient boosting is a popular and powerful machine learning algorithm used for both classification and regression tasks. It belongs to the family of ensemble learning methods, which combine the predictions of multiple base models to produce a more accurate and robust prediction. The main idea behind gradient boosting is to sequentially add weak learners (typically decision trees) to the ensemble, each..." current
  • 19:0219:02, 18 March 2023 diff hist +3,691‎ N Gradient boosted (decision) trees (GBT) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Gradient Boosted Trees (GBT), also known as Gradient Boosted Decision Trees or Gradient Boosting Machines, is a powerful ensemble learning technique in the field of machine learning. GBT constructs an ensemble of weak learners, typically decision trees, in a sequential manner, with each tree optimizing the model's performance by minimizing the error made by the previous tree. The technique is particularly well-suited f..." current
  • 19:0219:02, 18 March 2023 diff hist +2,571‎ N Gini impurity ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, Gini impurity is a metric used to measure the impurity or disorder within a dataset. It is commonly employed in decision tree algorithms, such as the Classification and Regression Tree (CART) algorithm, to decide the best splitting points for nodes. The Gini impurity index quantifies the probability of misclassification by calculating the degree of purity in a dataset, which he..." current
  • 19:0219:02, 18 March 2023 diff hist +4,051‎ N Feature importances ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Feature importances refer to the quantification of the relative contribution of each feature (or input variable) to the overall predictive performance of a machine learning model. Identifying and understanding the importance of features in a model can aid in model interpretation, feature selection, and ultimately, the improvement of model performance. Various techniques have been proposed to assess the significance..." current
  • 19:0219:02, 18 March 2023 diff hist +3,036‎ N Entropy ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, entropy is a fundamental concept that is derived from information theory. It is used to measure the impurity or randomness in a set of data. Entropy has various applications in machine learning, such as decision tree construction, feature selection, and information gain calculation. Understanding entropy and its implications is essential for designing and implementing effective mac..." current
  • 19:0119:01, 18 March 2023 diff hist +3,697‎ N Decision tree ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a '''decision tree''' is a popular and widely used model that helps in making predictions based on a series of decisions. The decision tree model can be used for both classification and regression tasks, and it works by recursively splitting the input data into subsets based on the values of the input features, ultimately making a prediction. ==Structure of a Decision Tree== ===No..." current
  • 19:0119:01, 18 March 2023 diff hist +4,307‎ N Decision forest ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''decision forest''' (also known as a '''random forest''') is an ensemble learning method in machine learning that combines multiple decision trees to generate a more accurate and robust prediction model. This method is widely used in classification and regression tasks, and it can handle both categorical and numerical input features. Decision forests are known for their ability to mitigate overfitting and improve g..." current
  • 19:0119:01, 18 March 2023 diff hist +3,940‎ N Condition ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, the term "condition" typically refers to a criterion or a set of criteria that must be met for a specific event to occur or an action to be taken. Conditions are used in various aspects of machine learning, including decision trees, rule-based systems, and optimization algorithms. This article aims to provide an understanding of conditions in machine learning and their significance, as well as..." current
  • 19:0119:01, 18 March 2023 diff hist +3,425‎ N Binary condition ‎ Created page with "{{see also|Machine learning terms}} ==Binary Condition in Machine Learning== In the field of machine learning, a '''binary condition''' refers to a specific type of classification problem where the target variable consists of only two distinct classes or categories. These types of problems are often encountered in various applications, such as spam detection, medical diagnosis, and sentiment analysis. The primary goal of binary classification models is to correctly p..." current
  • 19:0119:01, 18 March 2023 diff hist +3,720‎ N Bagging ‎ Created page with "{{see also|Machine learning terms}} ==Bagging in Machine Learning== Bagging, or '''Bootstrap Aggregating''', is a popular ensemble learning technique in machine learning that aims to improve the stability and accuracy of a base learning algorithm by training multiple instances of the same model on different subsamples of the training data. The predictions from the individual models are then combined, usually by means of a majority vote, to produce the final output. This..." current
  • 19:0119:01, 18 March 2023 diff hist +3,352‎ N Axis-aligned condition ‎ Created page with "{{see also|Machine learning terms}} ==Axis-Aligned Condition in Machine Learning== The axis-aligned condition is a concept commonly used in various machine learning algorithms, especially in the context of decision trees and spatial data structures. This condition refers to a restriction imposed on the decision boundaries, such that they are parallel to the coordinate axes of the feature space. The concept is relevant for understanding the behavior, limitations, and impr..." current
  • 19:0019:00, 18 March 2023 diff hist +4,134‎ N Transformer ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, the '''Transformer''' is a deep learning architecture that has revolutionized the field of natural language processing (NLP) since its introduction in 2017 by Vaswani et al. in the paper "Attention is All You Need" 1. The Transformer model leverages self-attention mechanisms to effectively capture long-range dependencies and contextual information in sequence data. It has been the foundation fo..." current
  • 13:3013:30, 18 March 2023 diff hist +2,809‎ N Synthetic feature ‎ Created page with "{{see also|Machine learning terms}} ==Synthetic Feature in Machine Learning== In the domain of machine learning and data science, a synthetic feature, also known as a feature engineering or constructed feature, refers to a new attribute or variable that is generated through the transformation or combination of existing features. This process aims to improve the performance and interpretability of machine learning models by providing additional, relevant informati..." current
  • 13:2913:29, 18 March 2023 diff hist +3,697‎ N Supervised machine learning ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Supervised machine learning is an approach in the field of machine learning where a model is trained using labeled data, which consists of input-output pairs. This type of learning aims to establish a relationship between input features and corresponding target outputs, allowing the model to make predictions on new, previously unseen data. Supervised learning is widely used in various applications, including imag..." current
  • 13:2913:29, 18 March 2023 diff hist +3,672‎ N Stochastic gradient descent (SGD) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== '''Stochastic gradient descent''' ('''SGD''') is an optimization algorithm commonly used in machine learning and deep learning to minimize a given objective function. It is a variant of the gradient descent algorithm that performs updates on a randomly selected subset of the data, rather than the entire dataset, at each iteration. This approach offers several advantages, including faster convergence and the abi..." current
  • 13:2913:29, 18 March 2023 diff hist +3,999‎ N Stationarity ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, '''stationarity''' refers to a property of time series data or stochastic processes where the statistical properties, such as the mean and variance, remain constant over time. It is an important concept in various machine learning tasks, particularly in time series analysis and forecasting, as it enables the development of reliable models and the identification of patterns and trends in..." current
  • 13:2913:29, 18 March 2023 diff hist +2,989‎ N Static inference ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Static inference is a technique in machine learning that involves predicting the output of a given input without explicitly training a model on the input data. It is a form of inference that relies on a model's prior knowledge and pre-existing learned representations, rather than adjusting its parameters to fit the data at hand. This approach is particularly useful in situations where the data is sparse, noisy, or..." current
  • 13:2913:29, 18 March 2023 diff hist +2,850‎ N Static ‎ Created page with "{{see also|Machine learning terms}} ==Static in Machine Learning== Static in machine learning refers to the invariant aspects or fixed properties of a learning model or dataset. These properties remain unchanged throughout the model's learning process and its subsequent deployment. This contrasts with dynamic aspects, which can be altered or adapted as the model evolves. Static properties are crucial for establishing a baseline and ensuring consistent performance of a ma..." current
  • 13:2913:29, 18 March 2023 diff hist +3,648‎ N Staged training ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Staged training is a technique in machine learning that involves training a model in successive stages, each with a distinct objective, in order to improve overall performance. This method is particularly useful for training deep learning models, as it helps to overcome challenges such as vanishing gradients, optimization difficulties, and training instability. Staged training can be applied to a variety of domains, in..." current
  • 13:2913:29, 18 March 2023 diff hist +2,824‎ N Squared loss ‎ Created page with "{{see also|Machine learning terms}} ==Squared Loss== Squared loss, also known as mean squared error (MSE) or L2 loss, is a widely used loss function in machine learning and statistical modeling for measuring the discrepancy between predicted values and true values in a given dataset. The objective of any machine learning model is to minimize the loss function, which in turn improves the model's prediction accuracy. ===Definition=== Formally, the squared loss..." current
  • 13:2813:28, 18 March 2023 diff hist +3,364‎ N Sparse vector ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a '''sparse vector''' is a vector representation of data that contains a significant number of zero-valued elements. Sparse vectors are widely used in various applications, such as natural language processing, information retrieval, and recommender systems, to name a few. This article will discuss the concept of sparse vectors, their properties, and applications in machine learning. =..." current
  • 13:2813:28, 18 March 2023 diff hist +4,341‎ N Sparse representation ‎ Created page with "{{see also|Machine learning terms}} ==Sparse Representation in Machine Learning== Sparse representation is a concept in machine learning and signal processing that involves encoding data or signals using a small number of non-zero coefficients. This approach has become popular due to its ability to capture the essential features of the data, while reducing the computational complexity and storage requirements. Sparse representations have been successfully applied in vari..." current
  • 13:2813:28, 18 March 2023 diff hist +3,631‎ N Sparse feature ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a sparse feature is a representation of data that consists predominantly of zero or null values, indicating the absence of some attributes or characteristics. Sparse features can be found in various data types and domains, such as text data, image data, and graph data. Utilizing sparse features effectively can significantly improve the efficiency and performance of machine learning alg..." current
  • 13:2813:28, 18 March 2023 diff hist +3,252‎ N Softmax ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, the '''softmax function''' is a widely used mathematical function for transforming a vector of numerical values into a probability distribution. Softmax is particularly useful in classification tasks where the goal is to assign an input to one of several possible categories. Softmax is often employed in combination with neural networks, such as multilayer perceptrons and convolutional neu..." current
  • 13:2813:28, 18 March 2023 diff hist +2,942‎ N Sigmoid function ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, the '''sigmoid function''' is a widely used mathematical function that transforms input values into probabilities, ranging from 0 to 1. It is often employed in various types of machine learning algorithms, particularly in artificial neural networks and logistic regression models, to map continuous inputs to probabilities for binary classification tasks. The sigmoid function is characterized..." current
  • 13:2813:28, 18 March 2023 diff hist +3,189‎ N Sequence-to-sequence task ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, particularly deep learning, a '''sequence-to-sequence (seq2seq) task''' refers to the process of mapping an input sequence to an output sequence. This type of task is particularly useful in various natural language processing (NLP) and time series prediction applications. It has gained significant attention in recent years due to the advancements in recurrent neural networks (RNNs)..." current
  • 13:2713:27, 18 March 2023 diff hist +3,622‎ N Sentiment analysis ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Sentiment analysis, also known as opinion mining or emotion AI, is a subfield of Natural Language Processing (NLP) in machine learning that focuses on determining the sentiment, emotions, or opinions expressed in a given text. It is commonly applied to a wide range of areas, such as social media monitoring, customer feedback analysis, and market research. ==Approaches to Sentiment Analysis== There are three pr..." current
  • 13:2713:27, 18 March 2023 diff hist +3,686‎ N Self-attention (also called self-attention layer) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Self-attention, also known as the self-attention layer, is a mechanism used in machine learning models, particularly in deep learning architectures such as Transformers. It enables the models to weigh and prioritize different input elements based on their relationships and relevance to one another. Self-attention has been widely adopted in various applications, including nat..." current
  • 13:2713:27, 18 March 2023 diff hist +2,995‎ N Regularization rate ‎ Created page with "{{see also|Machine learning terms}} ==Regularization Rate in Machine Learning== Regularization is an important technique in machine learning that helps prevent overfitting, a common problem where a model performs well on the training data but does not generalize well to new, unseen data. The regularization rate, also known as the regularization parameter or hyperparameter, is a constant value used to control the strength of regularization applied to a learning algorithm...." current
  • 13:2713:27, 18 March 2023 diff hist +3,000‎ N Regularization ‎ Created page with "{{see also|Machine learning terms}} ==Regularization in Machine Learning== Regularization is a technique used in machine learning to prevent overfitting, which occurs when a model learns to perform well on the training data but does not generalize well to unseen data. Regularization works by adding a penalty term to the objective function, which encourages the model to select simpler solutions that are more likely to generalize to new data. There are several types of reg..." current
  • 13:2713:27, 18 March 2023 diff hist +3,623‎ N Regression model ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A regression model in machine learning is a type of supervised learning algorithm that is designed to predict continuous output values, based on input features. The main goal of regression models is to understand the relationships between the dependent variable (target) and the independent variables (features). Regression models have been widely adopted in various fields such as finance, healthcare, and economics,..." current
  • 13:2713:27, 18 March 2023 diff hist +3,212‎ N Rater ‎ Created page with "{{see also|Machine learning terms}} ==Rater in Machine Learning== In the field of machine learning, a '''rater''' refers to an individual or group responsible for evaluating and scoring a model's predictions, usually by comparing them to a known ground truth. Raters play a crucial role in the development, training, and validation of machine learning algorithms, ensuring that models are accurate, reliable, and unbiased. ===Role of Raters in Machine Learning=== Raters are..." current
  • 13:2613:26, 18 March 2023 diff hist +2,488‎ N Proxy labels ‎ Created page with "{{see also|Machine learning terms}} ==Proxy Labels in Machine Learning== Proxy labels are a technique used in the field of machine learning to approximate the true labels of a dataset when obtaining the exact labels is infeasible or expensive. This method is particularly useful in situations where acquiring ground truth labels would require a significant investment of time or resources, or when the true labels are not directly observable. ===Applications=== Proxy la..." current
  • 13:2613:26, 18 March 2023 diff hist +3,623‎ N Prediction ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Prediction in machine learning refers to the process by which a trained model estimates or forecasts the outcome of a given input based on its learned patterns and relationships from past data. The prediction task is essential to various machine learning applications, including classification, regression, and time series forecasting. This article provides an overview of the concept of prediction in machine..." current
  • 13:2613:26, 18 March 2023 diff hist +3,809‎ N Post-processing ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Post-processing, in the context of machine learning, refers to a set of techniques and methods applied to the output of a machine learning model in order to improve or refine its results. This may include steps such as data transformation, calibration, and thresholding. Post-processing is often used to enhance model performance, interpretability, and reliability when deployed in real-world applications. ==Purpose of P..." current
  • 13:2613:26, 18 March 2023 diff hist +3,372‎ N Positive class ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, the term '''positive class''' refers to one of the two possible outcomes in a binary classification problem. Binary classification is a type of supervised learning where the objective is to categorize a given input into one of two mutually exclusive categories or classes. These classes are often labeled as the positive and negative classes. The positive class is typically the t..." current
  • 13:2613:26, 18 March 2023 diff hist +3,470‎ N Pipelining ‎ Created page with "{{see also|Machine learning terms}} ==Pipelining in Machine Learning== Pipelining in machine learning refers to the process of chaining together multiple steps of a machine learning workflow, from data preprocessing and feature extraction to model training and evaluation, to create an efficient and organized end-to-end solution. Pipelining is commonly used to simplify the implementation, facilitate the management, and improve the reproducibility of complex machine learni..." current
  • 13:2613:26, 18 March 2023 diff hist +3,448‎ N Parameter ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a '''parameter''' refers to a variable that is adjusted during the model training process to minimize errors and improve the accuracy of the model's predictions. These parameters enable the model to learn from data and represent the relationship between input features and target outputs. This article will provide an overview of parameters in machine learning, including their role in th..." current
  • 13:2613:26, 18 March 2023 diff hist +3,017‎ N Pandas ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Pandas is a widely used, open-source data manipulation and analysis library in Python that provides flexible, high-performance data structures for efficient handling of large and complex datasets. Although not specifically designed for machine learning, it has become an essential tool for data preprocessing, cleaning, and transformation tasks in the Machine Learning pipeline. ==Fe..." current
  • 13:2513:25, 18 March 2023 diff hist +3,570‎ N Overfitting ‎ Created page with "{{see also|Machine learning terms}} ==Overfitting in Machine Learning== ===Definition=== Overfitting is a phenomenon that occurs in machine learning when a model becomes excessively tailored to the training dataset, resulting in a decrease in its generalization performance on unseen data. In essence, the model learns the noise and peculiarities present in the training data, which negatively impacts its ability to make accurate predictions for new, unseen data. Overfittin..." current
  • 13:2513:25, 18 March 2023 diff hist +2,626‎ N Output layer ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the context of machine learning and artificial neural networks, the '''output layer''' is a crucial component that translates the computational results from the hidden layers into meaningful and interpretable predictions or classifications. The output layer, consisting of one or more neurons, is responsible for generating the final output of a neural network model, which can be used for various purposes,..." current
  • 13:2513:25, 18 March 2023 diff hist +3,667‎ N Online inference ‎ Created page with "{{see also|Machine learning terms}} ==Online Inference in Machine Learning== ===Overview=== Online inference in machine learning refers to the process of making predictions or drawing conclusions in real-time based on new data, as opposed to relying on a pre-trained model. This approach is commonly employed in situations where data is received incrementally and predictions must be made promptly, such as in recommendation systems, financial markets, or real-time computer..." current
  • 13:2513:25, 18 March 2023 diff hist +3,139‎ N One-vs.-all ‎ Created page with "{{see also|Machine learning terms}} ==One-vs.-All in Machine Learning== One-vs.-all (OvA), also known as one-vs.-rest (OvR) or one-against-all, is a multi-class classification strategy commonly used in machine learning. It is a method for training a classifier to distinguish between multiple classes by converting the multi-class problem into several binary classification problems. The key idea is to train a separate binary classifier for each class, treating it as the po..." current
  • 13:2513:25, 18 March 2023 diff hist +3,145‎ N One-hot encoding ‎ Created page with "{{see also|Machine learning terms}} ==One-Hot Encoding== One-hot encoding is a widely used technique in the field of machine learning and data preprocessing. It is employed to convert categorical variables into a numerical format that is suitable for machine learning algorithms to process. This method involves transforming a categorical variable into a binary vector, where each category is represented by a unique combination of zeros and ones. ===Background=== C..." current
  • 13:2513:25, 18 March 2023 diff hist +2,660‎ N Offline inference ‎ Created page with "{{see also|Machine learning terms}} ==Offline Inference in Machine Learning== Offline inference, also known as batch inference, is a process in machine learning whereby a trained model is used to make predictions on a dataset in a non-interactive or non-real-time manner. This approach allows for the efficient processing of large datasets, as it does not require an immediate response to user inputs. ===Characteristics of Offline Inference=== Offline inference is char..."
  • 13:2413:24, 18 March 2023 diff hist +3,269‎ N Offline ‎ Created page with "{{see also|Machine learning terms}} ==Offline Machine Learning== Offline machine learning, also known as batch learning or learning from static data, is a type of machine learning methodology where an algorithm is trained on a fixed dataset before deployment, rather than continuously updating its knowledge based on new data. In this approach, the model's training and testing phases are separate, and the model's generalization capabilities are of utmost importance..." current
  • 13:2413:24, 18 March 2023 diff hist +3,890‎ N Numerical data ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Numerical data, also referred to as quantitative data, is a type of data used extensively in machine learning and other computational disciplines. It consists of data points that can be represented and manipulated using numbers. In machine learning, numerical data is particularly important as it forms the foundation for mathematical models and algorithms that learn patterns and make predictions. This article will d..." current
  • 13:2413:24, 18 March 2023 diff hist +3,052‎ N Normalization ‎ Created page with "{{see also|Machine learning terms}} ==Normalization in Machine Learning== Normalization is a crucial preprocessing step in machine learning that aims to scale features or data points to a standardized range or distribution. By transforming the data to a common scale, it helps machine learning algorithms converge faster and achieve better performance. This is particularly important for algorithms that are sensitive to the scale of input features, such as gradient descen..." current
  • 13:2413:24, 18 March 2023 diff hist +4,182‎ N Nonstationarity ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Nonstationarity is a significant concept in the field of machine learning and statistics, which refers to the phenomenon where the underlying properties of a data-generating process change over time. In many real-world problems, the data encountered by machine learning models are subject to such changes, making it challenging to develop algorithms that can adapt and maintain their performance. In this article,..." current
  • 13:2413:24, 18 March 2023 diff hist +3,334‎ N Nonlinear ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Nonlinear methods in machine learning refer to a class of algorithms and techniques that are designed to model complex relationships between input and output variables, which cannot be adequately captured by linear models. These nonlinear models are particularly useful in situations where the underlying relationships between variables are more intricate or involve higher-order interactions. In this article, we will dis..." current
  • 13:2413:24, 18 March 2023 diff hist +3,274‎ N Node (neural network) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a node, also known as a neuron or unit, is a fundamental component of a neural network. It is responsible for receiving, processing, and transmitting information within the network. The functioning of nodes is inspired by the biological neurons found in the human brain, although the two differ significantly in their complexity and operation. ==Structure and Function== ===Input..." current
  • 13:2413:24, 18 March 2023 diff hist +3,462‎ N Neuron ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a '''neuron''' refers to an elementary unit within an artificial neural network (ANN). These units, also known as nodes or artificial neurons, are inspired by biological neurons found in the nervous systems of living organisms. Neurons in ANNs serve to process and transmit information through the network, enabling various machine learning tasks such as classification, regression, and p..." current
  • 13:2313:23, 18 March 2023 diff hist +3,011‎ N Negative class ‎ Created page with "{{see also|Machine learning terms}} ==Negative Class in Machine Learning== The negative class in machine learning refers to the category or label assigned to instances in a dataset that do not possess the characteristics or features of interest. It is the counterpart to the positive class, which represents instances with the desired attributes. The concept of negative and positive classes is particularly relevant in binary classification problems, where the goal..." current
  • 13:2313:23, 18 March 2023 diff hist +4,198‎ N Natural language understanding ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Natural Language Understanding (NLU) is a subfield of Artificial Intelligence and Computational Linguistics, concerned with enabling machines to comprehend, interpret, and generate human language in a meaningful way. NLU plays a pivotal role in the development of Machine Learning models, which are designed to automatically learn and improve from experience, with a focus on tasks such as Sentiment Analysis..." current
  • 13:2313:23, 18 March 2023 diff hist +4,018‎ N Multimodal model ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''multimodal model''' in machine learning is an advanced computational approach that involves the integration and processing of multiple types of data, or modalities, to enhance the learning process and improve predictive performance. Multimodal models aim to capture complex patterns and relationships that exist within and across various data modalities, such as text, images, audio, and video, to enable more acc..." current
  • 13:2313:23, 18 March 2023 diff hist +3,303‎ N Multi-head self-attention ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Multi-head self-attention is a core component of the Transformer architecture, a type of neural network introduced by Vaswani et al. (2017) in the paper "Attention Is All You Need". This mechanism allows the model to capture complex relationships between the input tokens by weighing their importance with respect to each other. The multi-head aspect refers to the parallel attention computations performed on differen..." current
  • 13:2313:23, 18 March 2023 diff hist +4,009‎ N Multi-class classification ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Multi-class classification is a type of supervised learning problem in machine learning where an algorithm is tasked with categorizing instances into one of multiple possible classes. In contrast to binary classification, which deals with only two classes, multi-class classification handles three or more classes. This article provides an overview of multi-class classification, discusses common techniques an..." current
  • 13:2313:23, 18 March 2023 diff hist +4,375‎ N Model parallelism ‎ Created page with "{{see also|Machine learning terms}} ==Model Parallelism in Machine Learning== Model parallelism is an approach in machine learning that addresses the computational challenges posed by the increasing size and complexity of modern neural network models. It involves the concurrent execution of different parts of a single model across multiple processing units, often in parallel to other parts of the model. This article discusses the motivation behind model parallelism,..." current
  • 13:2213:22, 18 March 2023 diff hist +3,122‎ N Model ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a '''model''' refers to a mathematical representation or abstraction of a real-world process or phenomenon. Machine learning models are developed using algorithms that learn from and make predictions or decisions based on input data. The primary goal of these models is to generalize from the training data in order to accurately predict outcomes for unseen data points. ==Types of M..." current
  • 13:2213:22, 18 March 2023 diff hist +3,995‎ N Modality ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the context of machine learning, '''modality''' refers to the different types, forms, or structures of data that a model can process or learn from. Understanding the concept of modality is essential for designing and implementing machine learning algorithms that can handle diverse data types effectively. This article discusses the concept of modality in machine learning, its various types, and its importance in mode..." current
  • 13:2113:21, 18 March 2023 diff hist +4,259‎ N Meta-learning ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Meta-learning, also referred to as "learning to learn", is an advanced paradigm in the field of machine learning that focuses on the design of algorithms and models capable of improving their performance on new tasks by utilizing previous learning experiences. The primary objective of meta-learning is to develop models that can adapt quickly to new tasks with minimal data and training time. This article provides an..." current
  • 13:2113:21, 18 March 2023 diff hist +2,712‎ N Masked language model ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, particularly natural language processing (NLP), a '''masked language model''' (MLM) is an important and widely used approach to train deep learning models on large-scale text data. This unsupervised technique has gained significant attention due to its success in various NLP tasks, such as text classification, translation, and sentiment analysis. ==Masked Language Modeling== Masked la..." current
  • 13:1913:19, 18 March 2023 diff hist +2,990‎ N Loss function ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, a '''loss function''' (also known as a cost function or objective function) is a crucial mathematical formulation that quantifies the difference between the predicted outcome of a model and the actual or desired outcome. Loss functions serve as the basis for optimization, enabling the model to iteratively adjust its parameters to minimize this difference and improve its performance..." current
  • 13:1913:19, 18 March 2023 diff hist +2,890‎ N Loss curve ‎ Created page with "{{see also|Machine learning terms}} ==Loss Curve in Machine Learning== In the field of machine learning, a '''loss curve''' is a graphical representation that demonstrates the performance of a learning algorithm during its training process. By plotting the value of the loss function against the number of training iterations or epochs, researchers and practitioners can assess the algorithm's progress in learning the underlying patterns in the given dataset. ===Im..." current
  • 13:1913:19, 18 March 2023 diff hist +3,549‎ N Loss ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, ''loss'' refers to a quantitative measure of the discrepancy between a model's predicted outputs and the true or observed values. It serves as an evaluation metric to assess the performance of a machine learning algorithm during the training process. By minimizing the loss function, practitioners aim to improve the model's accuracy and generalization capabilities. ==Loss Functions..." current
  • 13:1913:19, 18 March 2023 diff hist +2,793‎ N Logistic regression ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Logistic regression is a statistical method for analyzing a dataset in which there are one or more independent variables that determine an outcome. In the context of machine learning, logistic regression is a supervised learning algorithm used for solving binary classification problems. It predicts the probability of an event occurring based on the given input features. ==Logistic Regression Model== ===Model F..." current
  • 13:1913:19, 18 March 2023 diff hist +3,328‎ N Log-odds ‎ Created page with "{{see also|Machine learning terms}} ==Log-odds in Machine Learning== Log-odds, also known as logit, is a concept frequently used in machine learning, particularly in the context of binary classification problems. It is a method of representing the probability of an event occurring in the form of a logarithmic function. The log-odds function is often used in conjunction with logistic regression, a popular machine learning algorithm for classification tasks. ===Definition..." current
  • 13:1913:19, 18 March 2023 diff hist +2,863‎ N Linear regression ‎ Created page with "{{see also|Machine learning terms}} ==Linear Regression in Machine Learning== Linear regression is a fundamental supervised learning technique used in machine learning and statistics to model the relationship between a dependent variable and one or more independent variables. It is a linear approach that assumes a linear relationship between input and output variables. ===Overview=== In machine learning, linear regression is a popular algorithm for solving reg..." current
  • 13:1913:19, 18 March 2023 diff hist +3,597‎ N Linear model ‎ Created page with "{{see also|Machine learning terms}} ==Linear Models in Machine Learning== Linear models are a class of statistical models and machine learning algorithms that assume a linear relationship between input features and output. They are often used for regression and classification tasks due to their simplicity and ease of interpretation. ===Introduction=== In machine learning, linear models are used to predict a target variable based on one or more input features. These..." current
  • 13:1813:18, 18 March 2023 diff hist +3,518‎ N Linear ‎ Created page with "{{see also|Machine learning terms}} ==Linear Models in Machine Learning== ===Introduction=== In machine learning, linear models are a class of algorithms that utilize a linear relationship between input features and the output variable to make predictions. These models assume that the relationship between the input features (independent variables) and the output (dependent variable) can be represented by a straight line, or more generally, a hyperplane in higher-..." current
  • 13:1613:16, 18 March 2023 diff hist +3,821‎ N Large language model ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A large language model in machine learning refers to an advanced type of artificial intelligence that is designed to understand and generate human-like text. These models are trained on vast amounts of text data and can perform various tasks, such as translation, summarization, and question answering. The development of large language models has been driven by advancements in both deep learning and natural la..." current
  • 13:1613:16, 18 March 2023 diff hist +3,427‎ N Language model ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''language model''' in the context of machine learning is a computational model designed to understand and generate human language. Language models leverage statistical and probabilistic techniques to analyze, process, and produce text or speech data, making them indispensable in a wide range of natural language processing (NLP) tasks. Over time, the development of increasingly sophisticated models has led to signif..."
  • 13:1513:15, 18 March 2023 diff hist +2,526‎ N Lambda ‎ Created page with "{{see also|Machine learning terms}} ==Lambda in Machine Learning== Lambda is a term commonly used in machine learning and refers to a hyperparameter associated with regularization techniques. It is particularly relevant in the context of linear regression and logistic regression models, where regularization is employed to prevent overfitting and improve the generalization ability of the model. The two most popular regularization techniques using lambda are L1 reg..." current
  • 13:1513:15, 18 March 2023 diff hist +3,682‎ N Labeled example ‎ Created page with "{{see also|Machine learning terms}} ==Labeled Example in Machine Learning== ===Definition=== In the field of machine learning, a labeled example refers to a data point that consists of an input feature vector and its corresponding output value, often referred to as the target or label. Labeled examples are essential for supervised learning algorithms, which use these examples to learn a model that can make predictions or classifications on unseen data. The process of..." current
  • 13:1513:15, 18 March 2023 diff hist +3,008‎ N Label ‎ Created page with "{{see also|Machine learning terms}} ==Definition== In machine learning, a '''label''' refers to the desired output, or the "correct" value, for a particular instance in a dataset. Labels are used in supervised learning algorithms, where the goal is to learn a mapping from input data to output data, based on a set of examples containing input-output pairs. These output values in the training dataset are known as labels. The process of assigning labels to instances..." current
  • 13:1513:15, 18 March 2023 diff hist +3,546‎ N Encoder ‎ Created page with "{{see also|Machine learning terms}} ==Overview== An '''encoder''' in the context of machine learning refers to a specific component of a broader class of algorithms, typically used in unsupervised learning tasks, such as dimensionality reduction and representation learning. Encoders work by transforming input data into a lower-dimensional, more compact representation, which can be efficiently used for further processing, such as for clustering, classificati..." current
  • 13:1513:15, 18 March 2023 diff hist +3,376‎ N Embedding vector ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== An '''embedding vector''' in machine learning refers to a continuous, dense representation of discrete objects such as words, images, or nodes in a graph. Embedding vectors are used to convert these discrete objects into a continuous space, which makes it easier to apply machine learning algorithms that rely on mathematical operations. Typically, these embeddings are generated through unsupervised or supervised learnin..." current
  • 13:1513:15, 18 March 2023 diff hist +3,971‎ N Embedding space ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, the concept of '''embedding space''' refers to a continuous, high-dimensional space where objects, such as words, images, or user profiles, can be represented as vectors. These vector representations capture the underlying relationships and semantics of the objects in a more compact and computationally efficient manner. Embedding spaces are utilized in various machine learning applications, includi..." current
  • 13:1413:14, 18 March 2023 diff hist +4,226‎ N Denoising ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, denoising refers to the process of removing noise from the input data, which can significantly improve the performance and reliability of the resulting models. Noise in data can arise from various sources, such as measurement errors, transmission errors, or other disturbances. Denoising techniques play a crucial role in many applications, including image processing, speech recognition,..." current
  • 13:1413:14, 18 March 2023 diff hist +2,808‎ N Decoder ‎ Created page with "{{see also|Machine learning terms}} ==Decoder in Machine Learning== The '''decoder''' is a fundamental component in various machine learning architectures, particularly in sequence-to-sequence (seq2seq) models and autoencoders. It is responsible for generating output sequences or reconstructing input data based on the internal representation or context vector provided by the encoder. Decoders can be utilized in a wide array of applications such as natural langu..." current
  • 13:1413:14, 18 March 2023 diff hist +3,240‎ N Crash blossom ‎ Created page with "{{see also|Machine learning terms}} ==Crash Blossom in Machine Learning== Crash blossom is a term that originates from the field of journalism and linguistic ambiguity, referring to a headline that can be interpreted in more than one way, often resulting in humorous or confusing interpretations. However, in the context of machine learning, crash blossom does not have a direct application or meaning. Nevertheless, we can discuss related concepts in machine learning that t..." current
  • 13:1413:14, 18 March 2023 diff hist +3,395‎ N Confusion matrix ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning and pattern recognition, a '''confusion matrix''', also known as an '''error matrix''' or '''classification matrix''', is a specific table layout that allows for visualization and analysis of the performance of an algorithm, usually a classifier. It is a useful tool to assess the correctness and accuracy of a classification model by comparing the predicted outcomes with the actu..." current
  • 13:1413:14, 18 March 2023 diff hist +3,652‎ N Causal language model ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== A '''causal language model''' is a type of machine learning model designed to generate text by predicting the next word in a sequence based on the context of the preceding words. These models are particularly useful in natural language processing (NLP) tasks, as they can capture the inherent structure and meaning of language in a probabilistic manner. Causal language models, which are also known as autoregressive l..." current
  • 13:1413:14, 18 March 2023 diff hist +2,718‎ N Bigram ‎ Created page with "{{see also|Machine learning terms}} ==Bigram in Machine Learning== A '''bigram''' is a fundamental concept in the field of natural language processing (NLP), a subfield of machine learning. Bigrams are pairs of consecutive words in a given text or sequence of words. They play a vital role in various NLP tasks, such as language modeling, text classification, and sentiment analysis, by capturing the contextual information of words in a language. ===Definition and..."
  • 13:1413:14, 18 March 2023 diff hist +3,105‎ N Bidirectional language model ‎ Created page with "{{see also|Machine learning terms}} ==Bidirectional Language Models in Machine Learning== Bidirectional language models (BiLMs) are a type of machine learning model that are specifically designed for natural language processing (NLP) tasks. They have gained popularity in recent years due to their superior ability to understand and generate human-like text. This article provides an overview of bidirectional language models, their architecture, and applications in NLP task..." current
  • 13:1313:13, 18 March 2023 diff hist +3,284‎ N Bidirectional ‎ Created page with "{{see also|Machine learning terms}} ==Bidirectional Approaches in Machine Learning== Bidirectional approaches in machine learning refer to a class of algorithms designed to process and analyze data sequences in both forward and backward directions. These algorithms are particularly useful for tasks involving natural language processing, time series analysis, and other domains where temporal or sequential dependencies exist within the data. In this article, we will discus..." current
  • 13:1313:13, 18 March 2023 diff hist +3,334‎ N Bag of words ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, the '''bag of words''' (BoW) model is a common and simplified representation method used for natural language processing (NLP) and text classification tasks. The primary goal of the BoW model is to convert a collection of text documents into numerical feature vectors, which can be used as input for machine learning algorithms. ==Methodology== The bag of words model comprises two main..." current
  • 13:1313:13, 18 March 2023 diff hist +2,635‎ N Root Mean Squared Error (RMSE) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning, '''Root Mean Squared Error (RMSE)''' is a widely used metric for evaluating the performance of regression models. It quantifies the difference between the predicted values and the true values by calculating the square root of the average of the squared differences. The RMSE is particularly useful because it gives a measure of error that is interpretable in the same unit as the original..." current
  • 13:1313:13, 18 March 2023 diff hist +2,677‎ N Rectified Linear Unit (ReLU) ‎ Created page with "{{see also|Machine learning terms}} ==Rectified Linear Unit (ReLU)== The Rectified Linear Unit (ReLU) is a widely-used activation function in the field of machine learning and deep learning. It is a non-linear function that helps to model complex patterns and relationships in data. ReLU has gained significant popularity because of its simplicity and efficiency in training deep neural networks. ===History of ReLU=== The concept of ReLU can be traced back to t..." current
  • 13:1313:13, 18 March 2023 diff hist +2,929‎ N ReLU ‎ Created page with "{{see also|Machine learning terms}} ==ReLU in Machine Learning== ReLU, or '''Rectified Linear Unit''', is a popular activation function used in artificial neural networks (ANNs) for implementing deep learning models. The primary role of an activation function is to introduce non-linearity in the model and improve its learning capability. ReLU has been widely adopted due to its simplicity, efficiency, and ability to mitigate the vanishing gradient problem...." current
  • 13:1313:13, 18 March 2023 diff hist +3,770‎ N ROC (receiver operating characteristic) Curve ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''Receiver Operating Characteristic''' ('''ROC''') curve is a graphical representation that illustrates the diagnostic ability of a binary classifier system as its discrimination threshold is varied. It is widely used in machine learning, statistics, and data analysis for evaluating the performance of classification algorithms, particularly in the presence of imbalanced class distribution. ==Background== ===Origi..." current
  • 13:1213:12, 18 March 2023 diff hist +4,269‎ N NLU ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== Natural Language Understanding (NLU) is a subfield of Artificial Intelligence (AI) and Machine Learning (ML) that focuses on enabling computers to comprehend and interpret human language. This process includes the analysis of linguistic data to identify key elements such as entities, relations, and sentiments. NLU enables machines to understand the meaning and context of natural language input, allowing them to..." current
  • 13:1213:12, 18 March 2023 diff hist +3,105‎ N N-gram ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In the field of machine learning and natural language processing, an '''N-gram''' is a contiguous sequence of N items from a given sample of text or speech. N-grams are widely used for various tasks in computational linguistics, such as statistical language modeling, text classification, and information retrieval. The term "N-gram" is derived from the combination of the letter "N" and the word "gram," which originates..."
  • 13:1213:12, 18 March 2023 diff hist +2,368‎ N Log Loss ‎ Created page with "{{see also|Machine learning terms}} ==Log Loss== Log Loss, also known as logarithmic loss or cross-entropy loss, is a common loss function used in machine learning for classification problems. It is a measure of the difference between the predicted probabilities and the true labels of a dataset. The Log Loss function quantifies the performance of a classifier by penalizing the predicted probabilities that deviate from the actual class labels. ==Usage in Machine Learning..." current
  • 13:1213:12, 18 March 2023 diff hist +3,450‎ N LaMDA (Language Model for Dialogue Applications) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== '''LaMDA''' ('''L'''anguage '''M'''odel for '''D'''ialogue '''A'''pplications) is a conversational AI model developed by Google in the field of machine learning. LaMDA aims to improve the interaction between humans and computers by enabling open-domain conversations, thereby allowing machines to understand and respond to a wide range of topics. This article discusses the design, functionality, and key aspects of La..." current
  • 13:1213:12, 18 March 2023 diff hist +3,193‎ N L2 regularization ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== L2 regularization, also known as ridge regression or Tikhonov regularization, is a technique employed in machine learning to prevent overfitting and improve the generalization of a model. It is a form of regularization that adds a penalty term to the objective function, which helps in constraining the model's complexity. L2 regularization is particularly useful for linear regression models, but can also be appl..." current
  • 13:1213:12, 18 March 2023 diff hist +2,352‎ N L2 loss ‎ Created page with "{{see also|Machine learning terms}} ==L2 Loss in Machine Learning== L2 Loss, also known as Euclidean Loss or Squared Error Loss, is a widely-used loss function in machine learning and deep learning. It is a popular choice for regression tasks, where the goal is to predict a continuous output value. L2 Loss quantifies the difference between the predicted output and the true output, providing a measure of model accuracy. ===Definition and Properties=== The L2 Loss is def..." current
  • 13:1113:11, 18 March 2023 diff hist +3,011‎ N L1 regularization ‎ Created page with "{{see also|Machine learning terms}} ==L1 Regularization in Machine Learning== L1 regularization, also known as Lasso regularization or L1 norm, is a widely used regularization technique in machine learning and statistical modeling to prevent overfitting and enhance the generalization of the model. It achieves this by introducing a penalty term in the optimization objective that encourages sparsity in the model parameters. ===Overview=== Regularization techniques are emp..." current
  • 13:1113:11, 18 March 2023 diff hist +3,112‎ N L1 loss ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, various loss functions are used to measure the discrepancy between predicted values and actual values. L1 loss, also known as ''Least Absolute Deviations'' (LAD) or ''Least Absolute Errors'' (LAE), is one such loss function used in regression problems to estimate model parameters. L1 loss calculates the sum of absolute differences between predicted and actual values, making it robust to outliers an..." current
  • 13:1113:11, 18 March 2023 diff hist +3,859‎ N GPT (Generative Pre-trained Transformer) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''Generative Pre-trained Transformer''' ('''GPT''') is a series of machine learning models developed by OpenAI for natural language processing tasks. These models are based on the Transformer architecture introduced by Vaswani et al. in 2017. GPT models are designed to generate text by predicting subsequent words in a sequence, and have been applied to tasks such as text generation, translation, summarization,..." current
  • 13:1113:11, 18 March 2023 diff hist +3,877‎ N BLEU (Bilingual Evaluation Understudy) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== The '''Bilingual Evaluation Understudy''' ('''BLEU''') is an automatic evaluation metric used in the field of Natural Language Processing (NLP) to measure the quality of machine-generated translations. Developed by IBM Research in 2002, it compares translations generated by a machine with a set of human-generated reference translations. BLEU scores are widely used in the evaluation of machine translation system..." current
  • 13:1113:11, 18 March 2023 diff hist +3,640‎ N BERT (Bidirectional Encoder Representations from Transformers) ‎ Created page with "{{see also|Machine learning terms}} ==Introduction== BERT, or '''Bidirectional Encoder Representations from Transformers''', is a pre-training technique for natural language understanding tasks in the field of machine learning. Developed by researchers at Google AI Language, BERT has significantly advanced the state of the art in a wide range of tasks, such as question answering, sentiment analysis, and named entity recognition. BERT's breakthrough lies in its abilit..." current
(newest | oldest) View ( | older 500) (20 | 50 | 100 | 250 | 500)
Retrieved from "http:///wiki/Special:Contributions/Walle"