Thursday, July 23, 2026
- MLOpsv10MLOps (Machine Learning Operations) is a set of practices, principles, and tools for deploying, monitoring, and maintaining machine learning models in production reliably and efficiently.
- Semantic searchv6Semantic search is an information retrieval approach that finds results based on the meaning and intent behind a query rather than relying solely on exact keyword matches.
- Apple Intelligencev6Apple Intelligence is Apple's personal intelligence system, a suite of generative AI features built into iPhone, iPad, Mac, Apple Watch, and Apple Vision Pro that combines on-device machine learning models…
- State space model (deep learning)v6A state space model (SSM) in deep learning is a class of sequence model that maps an input sequence to an output sequence through a fixed-size latent state
- Knowledge graphv7A knowledge graph is a structured representation of real-world entities and the relationships between them, organized as a network of interconnected nodes and edges.
- LlamaIndexv10LlamaIndex is an open-source data framework for building large language model (LLM) applications, with a particular focus on retrieval-augmented generation (RAG) and document processing.
- Red teaming (artificial intelligence)v5Red teaming in artificial intelligence is the systematic, adversarial testing of an AI system to find vulnerabilities, biases, harmful outputs, and other failure modes before deployment or as part of ongoing…
- Contrastive Learningv12Contrastive learning is a family of machine learning methods that learn representations by pulling similar (positive) pairs of data points closer together in an embedding space while pushing dissimilar…
- Reasoning (artificial intelligence)v8Reasoning in artificial intelligence is the ability of an AI system to draw inferences, solve problems, and make decisions through structured, multi-step thought rather than a single immediate response.
- Explainable AIv7Explainable AI (XAI) refers to artificial intelligence systems and techniques designed so that humans can understand how and why the system reaches its decisions, predictions, or recommendations.
- Turing testv6The Turing test is a test of a machine's ability to exhibit conversational behavior indistinguishable from that of a human, proposed in 1950 by the British mathematician and computer scientist Alan Turing in…
- Autoencoderv11An autoencoder is a type of neural network trained to reconstruct its own input through a low-dimensional bottleneck representation, using the input itself as the training signal rather than any external label.
- Top-p samplingv6Top-p sampling, also called nucleus sampling, is a stochastic decoding method for text generation in which the model samples from the smallest possible set of tokens whose cumulative probability mass exceeds a…
- AI ethicsv8AI ethics is the field that studies the moral principles, values, and frameworks governing how artificial intelligence systems are designed, built, deployed, and used, and the obligations that developers and…
- Adversarial attackv8An adversarial attack is a technique for crafting inputs that are deliberately designed to cause artificial intelligence systems, particularly machine learning models, to produce incorrect or undesired outputs.
- Jailbreak (artificial intelligence)v7A jailbreak in artificial intelligence is a technique that bypasses the safety guardrails, content policies, and alignment constraints built into large language models (LLMs) and other AI systems
- Emergent abilitiesv7Emergent abilities are capabilities of large language models (LLMs) that are absent in smaller models but appear once a model reaches sufficient scale.
- AI winterv9An AI winter is a period of reduced funding, waning public interest, and diminished research activity in the field of artificial intelligence.
- Temperature (artificial intelligence)v7Temperature is a hyperparameter that controls the randomness of a large language model's output by scaling the model's raw scores, called logits
- Superintelligencev6Superintelligence is a hypothetical form of artificial intelligence that surpasses all human cognitive abilities across virtually every domain, including scientific reasoning, social skills, creativity, and…
- DPOv10DPO (Direct Preference Optimization) is an alignment technique for large language models that directly optimizes a language model policy from human preference data, without training a separate reward model or…
- Deep Learningv11Deep learning is a subset of machine learning that uses artificial neural networks with multiple layers to automatically learn representations of data at multiple levels of abstraction
- Tokenizationv10Tokenization is the process of breaking text into smaller units called tokens, which serve as the fundamental input to natural language processing (NLP) systems and large language models (LLMs).
- Z-Score Normalizationv9Z-score normalization, also called standardization, standard score normalization, or z-score scaling, is a data preprocessing technique that transforms a numerical feature so that it has a mean of 0 and a…
- Zhipu AIv12Zhipu AI (智谱AI), now branded internationally as Z.ai, is a Chinese artificial intelligence company headquartered in Beijing.
- Zero shot, one shot and few shot learningv5Zero-shot, one-shot, and few-shot learning are three related settings in machine learning and prompt engineering defined by how many labelled examples a model sees of a target task or class before making a…
- Zero-Shot Image Classification Modelsv6Zero-shot image classification models are vision systems that assign images to categories the model has never encountered as labeled training examples.
- Constitutional AIv11Constitutional AI (CAI) is an artificial intelligence alignment technique developed by Anthropic in which a large language model is trained to be helpful and harmless using a set of explicitly stated…
- Writing ChatGPT Pluginsv4Writing ChatGPT Plugins were the subset of third party extensions in the ChatGPT plugin store focused on producing, editing, paraphrasing, optimizing, summarizing, or formatting written text.
- Zero-Shot Classification Modelsv5Zero-shot classification models are machine learning systems that assign input text to a set of candidate categories without having seen labeled training examples for those specific categories.
- Weighted Alternating Least Squares (WALS)v7Weighted Alternating Least Squares (WALS), also called implicit Alternating Least Squares (iALS) or weighted regularized matrix factorization (WRMF), is a matrix factorization algorithm for collaborative…
- Weatherv4AI in weather forecasting refers to the use of machine learning, and especially deep learning, to predict the state of the atmosphere.
- Wasserstein Lossv6Wasserstein loss is a loss function for training generative models that measures the distance between two probability distributions as the Wasserstein-1 distance
- Web Development ChatGPT Pluginsv4Web Development ChatGPT Plugins were a now-retired category of third-party extensions for ChatGPT that let the model perform tasks adjacent to building, browsing, scraping, and summarizing the public web.
- Weather ChatGPT Pluginsv4Weather ChatGPT Plugins were a category of third party extensions for ChatGPT that supplied current conditions, forecasts, radar imagery, air quality data, and historical climate records to the chat interface.
- Web Services ChatGPT Pluginsv3Web services ChatGPT plugins were a category of third party extensions for ChatGPT that connected the chatbot to remote application programming interfaces, software as a service products, business automation…
- Widthv4Width refers to the number of neurons in a specific layer of a neural network. In modern transformer language models, the dominant width parameter is usually called hidden_size or d_model, and it sets the…
- WebDev Arenav3WebDev Arena is a live, community-driven leaderboard that ranks large language models on their ability to generate working web applications.
- Wide Modelv5A wide model is a type of machine learning model that uses a large number of input features, often with sparse, high-dimensional representations such as one-hot encoding and cross-product feature…
- Word Embeddingv8A word embedding is a learned representation of text in which words are mapped to dense vectors of real numbers in a continuous vector space, so that words with similar meanings are positioned close together.
- Whisperv13Whisper is an open-source family of automatic speech recognition (ASR) models developed by OpenAI and first released on September 21, 2022.
- Writingv6AI is used for writing by applying large language models to draft, edit, rewrite, summarize, and translate text, usually through a chatbot like ChatGPT or through features built into grammar checkers, word…
- Weighted Sumv7A weighted sum is a mathematical operation that combines multiple input values by multiplying each value by a corresponding weight (coefficient) and then summing the results.
- Voice Activity Detection Modelsv6Voice activity detection (VAD), also called speech activity detection (SAD), is the task of deciding which segments of an audio signal contain human speech and which contain only silence, background noise…
- Weightv6In machine learning and neural networks, a weight is a learnable numerical parameter that determines the strength of the connection between two neurons.
- Wisdom of the Crowdv5Wisdom of the crowd is the observation that the aggregate judgment of a large group of individuals often produces more accurate estimates or decisions than any single member of that group
- WORDLY - WORD Gamev8WORDLY - WORD Game is a ChatGPT plugin released in June 2023 that lets users play a Wordle style guessing game inside ChatGPT.
- Unsupervised Machine Learningv7Unsupervised machine learning is a type of machine learning that finds patterns, structures, and relationships in data that has no labels, with no human-provided answer key to learn from.
- Visual Question Answering Modelsv6Visual question answering models are AI systems that take an image and a natural language question about that image and return a natural language answer.
- Validationv4Validation in machine learning is the process of checking how well a trained model performs on data it did not see during training, using a held-out validation set to tune hyperparameters, choose between…
- User matrixv7In collaborative filtering and matrix factorization recommender systems, the user matrix (commonly written U or P) is the matrix of latent-factor vectors for users: each row is one user's embedding in a…
- Vector databasev10A vector database is a database that stores data as high-dimensional vectors (numerical embeddings produced by a machine learning model) and retrieves records by similarity rather than exact match
- Vibe Coding Tips and Tricksv4Vibe coding is the practice of building software by describing what you want in natural language and letting an AI write the code.
- Validation lossv4Validation loss is the value of a model's loss function measured on a held-out validation set, data the model never sees during weight updates, and it is the primary signal practitioners use to judge how well…
- Upweightingv5Upweighting is the practice of assigning a larger weight to certain training examples (or groups of examples) so they contribute more to the loss function and gradient updates than the rest of the data.
- Vimgolfv3vimgolf-gym is an OpenAI Gym style customizable environment and benchmark built around VimGolf, the long running keystroke counting puzzle game for Vim.
- Video-MMMUv3Video-MMMU (Video Multi-Modal Multi-disciplinary Understanding, sometimes written VideoMMMU) is a benchmark that measures whether Large Multimodal Models can acquire new knowledge from professional educational…
- Validation Setv6A validation set (also called a development set or dev set) is a subset of labeled data that is held out from the training set and used to evaluate a model's performance during development
- Video Classification Modelsv5Video classification models are machine learning systems that assign one or more category labels to a video clip, typically describing the human action depicted.
- Vanishing Gradient Problemv9The vanishing gradient problem is a difficulty in training deep neural networks where the gradients used to update the network shrink exponentially as they are propagated backward through the layers, leaving…
- Video GPT by VEEDv5Video GPT by VEED (also stylized as VideoGPT by VEED) is an artificial intelligence text-to-video tool developed by the London-based online video editing company VEED.IO.
- Uplift Modelingv8Uplift modeling (also called incremental modeling, true lift modeling, or net modeling) is a set of machine learning and statistical techniques that predict the incremental impact of a treatment or action on…
- Vector embeddingsv11Vector embeddings are dense numerical representations of objects (text, images, audio, video, code, graphs, or any structured data) that map them into a continuous vector space such that semantic similarity…
- Variable importancesv4Variable importances, also called feature importances, are scores assigned to each input variable of a predictive model that measure how much that variable contributes to the model's output.
- True positivev8A true positive (TP) is a prediction that is correctly positive: the model predicts the positive class and the true label is also positive.
- Training-Serving Skewv9Training-serving skew is a difference between a machine learning model's performance during training and its performance during serving (production inference).
- Training lossv8In machine learning, training loss is the value of the loss function computed on the training data during model training, and it is the exact quantity that the optimization algorithm minimizes at each step.
- Undersamplingv6Undersampling is a class imbalance handling technique in machine learning that removes examples from the majority class of a training set so the minority class is no longer drowned out.
- Universal Speech Modelv6The Universal Speech Model (USM) is a family of large multilingual speech models developed by Google Research that performs automatic speech recognition (ASR) and speech-to-text translation across more than…
- Unawareness (Fairness Through Unawareness)v4Unawareness to a sensitive attribute, more commonly called fairness through unawareness (FTU), is a machine learning fairness approach that tries to make a model fair by simply not giving it the sensitive or…
- Unidirectionalv7Unidirectional is a property of a sequence model in which the representation or output at each position depends only on inputs from one direction of the sequence
- Unidirectional language modelv5A unidirectional language model is a language model that predicts each token using only the tokens that come before it in the sequence (the left context), via causal (autoregressive) masking
- Unconditional Image Generation Modelsv5Unconditional image generation models are generative neural networks that learn the marginal distribution p(x) of a set of training images and produce new samples from that learned distribution, with no extra…
- Universev4Universe was an open-source software platform that OpenAI released on December 5, 2016 for measuring and training an artificial intelligence agent's general intelligence across, in OpenAI's words, "the world's…
- Unlabeled examplev5An unlabeled example is a data instance that has one or more features but no label, meaning it carries the inputs a model reads but not the target answer the model is meant to produce.
- Underfittingv6Underfitting occurs when a machine learning model is too simple to capture the underlying patterns in the data.
- Unsupervised learningv6Unsupervised learning is a branch of machine learning in which algorithms identify patterns, structures, and relationships in data without relying on labeled examples or explicit human guidance.
- True negativev9A true negative (TN) is a case that a binary classification model correctly predicts as belonging to the negative class: the true label is negative and the predicted label is also negative.
- Trajectory (Reinforcement Learning)v7A trajectory in reinforcement learning is a sequence of states, actions, and rewards that an agent experiences while interacting with an environment.
- True positive rate (TPR)v5The true positive rate (TPR) is the proportion of actual positive cases that a classifier correctly identifies as positive, computed as TPR = TP / (TP + FN), where TP is the number of true positives and FN the…
- Unstable Diffusionv4Unstable Diffusion is a Discord community and affiliated commercial platform, operated by the company Equilibrium AI
- Towerv6In deep learning, a tower is a self-contained sub-network inside a larger model that encodes one specific input or feature group into an output, usually an embedding
- Test lossv4Test loss is the value of a loss function computed on a held-out test data set: data that was used neither for training nor for validation or model selection.
- Tensor sizev4The size of a tensor is a description of how big the tensor is, and the term carries two distinct meanings in everyday deep learning.
- Text Generation Modelsv6Text generation models are language models trained to produce coherent natural-language text by predicting tokens one at a time, each conditioned on the preceding context.
- Threshold (for decision trees)v5In a decision tree, a threshold is the cut point used in an internal node's split test that decides which child subtree a sample is routed to.
- Text2Text Generation Modelsv5Text-to-text (text2text) generation models are a family of neural network systems that frame many natural language processing tasks as a single problem: given an input text string
- Termination conditionv7A termination condition, also called a stopping criterion, convergence criterion, or halting condition, is a rule that decides when an iterative algorithm should stop running.
- Termsv7Terms is the AI Wiki's top-level glossary, a single alphabetical index that defines and links artificial intelligence vocabulary, machine learning concepts, and AI model, tool, and company names.
- Trainingv6Training in machine learning is the process of fitting a model's parameters to data so that the model can make accurate predictions or generate useful outputs.
- Text-to-Image Modelsv7Text-to-image models are generative artificial intelligence systems that synthesize a new image from a natural-language description, called a prompt.
- Tokenv8A token is the basic unit of text that a language model reads and writes: a word, a subword fragment, a single character, or a byte, produced by splitting text during a step called tokenization.
- Token Classification Modelsv5Token classification models are natural language processing systems that assign a discrete label to every token in an input sequence, where a token is typically a word, subword piece, or character.
- Text Classification Modelsv6Text classification models are machine learning systems that assign one or more predefined categorical labels to a span of natural language text, such as positive vs. negative, spam vs. ham
- tf.kerasv8tf.keras is the high-level deep learning API built directly into the TensorFlow machine learning framework
- The New Stack and Ops for AI (OpenAI Dev Day 2023)v5The New Stack and Ops for AI is a technical breakout session presented by Sherwin Wu and Shyamal Hitesh Anadkat at OpenAI DevDay 2023, held on November 6, 2023, in San Francisco.
- Timestepv8A timestep is a discrete unit of time progression in a sequential process. The term shows up in many corners of machine learning and applied math, and it does not always mean the same thing.
- Text-to-Speech Modelsv5Text-to-speech (TTS) models are machine learning systems that convert written text into spoken audio.
- TPU Workerv6A TPU worker is a virtual machine (VM) running Linux that has direct access to one or more Tensor Processing Unit (TPU) chips and executes the actual TPU computation on that attached hardware.
- Tabular modelsv4Tabular models are machine learning systems that learn from data arranged in tables, where each row is a sample and each column is a feature.
