Skip to content
AI Wiki
CtrlK
All PagesCategoriesRecentRandom
Log inSign up
Loading
AI WikiAI Wiki

The free encyclopedia of artificial intelligence. Explore 4,056 articles on AI concepts, models, tools, and applications.

Navigate

HomeAll PagesCategoriesRecent ChangesRandom ArticleRequested ArticlesStatisticsSearch

Popular

ChatGPTLarge Language ModelsDeep LearningNeural Networks

About

AboutPoliciesCorrectionsContent LicenseAI & Developer AccessPrivacy PolicyTerms of Service

AIWiki.ai · Text is available under CC BY 4.0; reuse welcome

RSS Feed

Open knowledge for everyone

Recent changes

RSS

4,056 articles updated. New pages start at v1; higher version numbers mean an existing article was revised. Page 7 of 41.

Tuesday, July 14, 2026

  • Harness (AI)newThis article is about software that wraps and evaluates AI models. For the 2015 paper "Explaining and Harnessing Adversarial Examples" and other uses of the...
  • GENISOM AInewValue ------- Private; embodied-AI and robotics developer Industry December 2023 (per company and trade press) Headquarters Suzhou, Jiangsu, China...
  • Humanoid robot marketv6The humanoid robot market is the global commercial ecosystem for designing, manufacturing, selling, and deploying humanoid robots, robots built to resemble and...
  • Huawei Ascend 910BnewValue --- Data-center AI training and inference accelerator (NPU) Designer Huawei Ascend Architecture 7nm class: SMIC (variously called N+1 or N+2);...
  • 1X Neov7--- General information 1X Technologies Country of origin 2024 (NEO Beta) Status $20,000 (early access) / $499/month (subscription) Height 30 kg...
  • UWORLD U1v2--- Manufacturer UWORLD Country of origin Companion humanoid robot Unveiled June 2, 2026 (JD.com) Trims 1.60 to 1.85 m (full-body models) Degrees...
  • Stepper motornewA stepper motor (also called a stepping motor) is an electric motor that converts a sequence of electrical pulses into discrete mechanical steps rather than...
  • Axial flux motornewAn axial flux motor is an electric motor in which the magnetic flux crossing the gap between rotor and stator runs parallel to the shaft, rather than radiating...
  • Coreless motornewA coreless motor, also called an ironless motor, is a small electric motor whose rotor, the spinning part, carries a self-supporting winding of copper wire...
  • Servo motornewA servo motor is a motor operated inside a closed feedback loop: a controller sends a target position, speed, or torque, a sensor, typically a rotary encoder,...
  • Brushless DC motornewA brushless DC motor (BLDC motor) is an electric motor design in which permanent magnets are mounted on the rotating rotor and an electronic controller...

Monday, July 13, 2026

  • Web Developmentv4See also: Web Development ChatGPT Plugins AI in web development is the use of large language models and related generative systems to design, build, deploy,...
  • OpenPIv3OpenPI (stylized openpi) is the open-source repository of robot foundation models, training code, and inference utilities published by Physical Intelligence,...
  • Kinisi 01v6--- General information Kinisi Robotics Parent company KR1 Type July 2025 Country of origin In production; pilot deployments Price kinisi.com ...
  • LLM inference enginev3An LLM inference engine (also called an LLM serving engine or LLM inference server) is the systems software stack that loads trained large language model...
  • CosyVoicev3CosyVoice is a family of open-source multilingual neural text-to-speech (TTS) and voice cloning models developed by the Tongyi Speech Lab (Tongyi SpeechTeam)...

Sunday, July 12, 2026

  • AI in transportationv3AI in transportation refers to the application of artificial intelligence techniques to the movement of people and goods across road, rail, air, sea, and the...
  • Synthetic Featurev5A synthetic feature (also called a constructed feature or derived feature) is a variable created by transforming, combining, or otherwise manipulating one or...
  • Prior beliefv3See also: Bayes' theorem, Bayesian inference, Posterior, Likelihood A prior belief, also called the prior distribution or simply the prior, is the probability...
  • Model stealingv3Model stealing (also known as model extraction, model functionality extraction, or model theft) is an adversarial machine learning attack in which an adversary...
  • Context cachingv3Context caching is a large-language-model API feature that stores parts of a request's input (system prompts, instructions, attached documents, or earlier...
NewerPage 7 of 41Older
  • Technologyv6Technology is one of the largest application domains for artificial intelligence, spanning enterprise IT operations, cloud computing, cybersecurity, software...
  • Refusal directionv2The refusal direction is a finding from mechanistic interpretability research that the refusal behavior of safety fine-tuned chat language models is mediated...
  • Pipecatv3Pipecat is an open-source Python framework for building real-time voice and multimodal conversational AI agents.[2] Created by Daily, a WebRTC infrastructure...
  • Novelty Detectionv5Novelty detection is a branch of machine learning concerned with identifying test data that differ in some meaningful way from the data available during...
  • ARIA (UK)v3The Advanced Research and Invention Agency (ARIA) is a United Kingdom government research funding body, established by Act of Parliament in 2022 and made...
  • Gradientv5In machine learning, the gradient is the vector of partial derivatives of a loss function with respect to every model parameter, and it points in the direction...
  • Machine learning terms/Fundamentalsv6See also: Machine learning terms Machine learning (ML) is the branch of artificial intelligence concerned with building systems that learn patterns from data...
  • Layerv5A layer is the fundamental building block of a neural network: an organized group of neurons (also called nodes or units) that together apply one mathematical...
  • K-Medianv7K-median clustering (also written k-medians) is a partitioning-based clustering algorithm that divides a dataset of objects into groups by minimizing the...
  • Generatorv6A generator is a neural network within a generative adversarial network (GAN) that learns to produce synthetic data samples from random noise. It maps a point...
  • Implicit Biasv6Implicit bias is an umbrella term that, in artificial intelligence and machine learning, refers to systematic tendencies operating below the surface of...
  • GANv6GAN stands for generative adversarial network, a class of deep learning generative models in which two neural networks are trained against each other: a...
  • GPT-2v10GPT-2 is a 1.5 billion parameter language model released by OpenAI in February 2019, and the second model in the GPT (Generative Pre-trained Transformer)...
  • Dynamic modelv6See also: Machine learning terms A dynamic model in machine learning is a model that is retrained frequently or continuously as new data arrives, so that its...
  • False negativev8A false negative (FN), also called a Type II error or a miss, is an instance whose true label is positive but that a classification model or test predicts as...
  • Checkpointv7See also: Machine learning terms In machine learning, a checkpoint is a saved snapshot of a model's state captured at a specific point during the training...
  • Environmentv5See also: Machine learning terms, Environment ChatGPT Plugins In reinforcement learning (RL), an environment is the external system that an agent interacts...
  • Centroid-based clusteringv5See also: Machine learning terms Centroid-based clustering is a family of machine learning algorithms that group data by representing each cluster with a...
  • Calibration Layerv6A calibration layer is a post-prediction adjustment appended to a trained machine learning model that rescales its raw output scores or predicted probabilities...
  • Data Parallelismv9Data parallelism is a distributed training technique in which the same neural network model is replicated across multiple processing units (typically GPUs),...
  • Convex Setv6A convex set is a set of points in which the line segment connecting any two points of the set lies entirely within the set [1][3]. Formally, a set in a real...
  • Boostingv6Boosting is an ensemble learning method in machine learning that trains a sequence of weak learners, each one correcting the errors of its predecessors, and...
  • Co-Trainingv4Co-training is a semi-supervised learning algorithm that leverages both labeled and unlabeled data by training two classifiers on two distinct "views" of the...
  • Early Stoppingv6Early stopping is a regularization technique that halts the training of an iterative machine learning model as soon as its performance on a held-out validation...
  • Convolutional Neural Networkv7A convolutional neural network (CNN or ConvNet) is a type of neural network that processes grid-like data such as images by sliding small learnable filters...
  • Context windowv6A context window (also called context length) is the maximum number of tokens that a large language model (LLM) can process at once, spanning both the input...
  • Classification (machine learning)v7Classification in machine learning is the supervised learning task of training an algorithm to assign discrete category labels to input data, in contrast to...
  • Spatial Poolingv5Spatial pooling is a downsampling operation in convolutional neural networks (CNNs) that replaces a local region of a feature map with a single summary...
  • AudioCraftv8See also: Generative AI, Meta AI, and Deep Learning AudioCraft is an open-source generative-audio library released by Meta AI (Fundamental AI Research, FAIR)...
  • Bidirectionalv6See also: Machine learning terms Bidirectional describes a sequence model in which the representation at every position depends on the entire input sequence,...
  • Bidirectional language modelv6See also: Machine learning terms A bidirectional language model is a language model that, when computing a representation for a token, conditions on both the...
  • Splitv4See also: Machine learning terms A split in machine learning is a partitioning operation, and the word names two distinct things. As a data operation, a split...
  • Bias (Math) or Bias Termv5See also: Machine learning terms The bias term is a learnable additive constant b added to the weighted sum of a neuron's inputs before an activation function...
  • Sparsityv4See also: Machine learning terms Sparsity is the property of a data structure, model, or representation in which most values are zero or near-zero, so that...
  • Bag of Wordsv6The bag of words (BoW) model is a text representation method that converts a document into a fixed-length numeric vector by counting how often each word from a...
  • L1 Regularizationv5L1 regularization is a regularization technique in machine learning and statistics that prevents overfitting by adding the sum of the absolute values of a...
  • Area under the curvev6Area under the curve (AUC) is a single scalar metric that summarizes the performance of a binary classifier or diagnostic test across all possible decision...
  • Binary Classificationv10See also: Classification model, Multi-class classification Binary classification is a supervised learning task in which a model assigns each input to exactly...
  • Universal Approximation Theoremv3The universal approximation theorem states that a feedforward neural network with a single hidden layer of finite width and a suitable nonlinear activation...
  • MoE load-balancing lossv2The MoE load balancing loss is an auxiliary training objective used in sparse mixture of experts (MoE) neural networks to keep work spread evenly across the...
  • Contrastive decodingv2Contrastive decoding (CD) is a decoding strategy for text generation from a large language model that selects tokens by contrasting two models of different...
  • Model soupsv2Model soups is a weight-averaging technique (a form of model merging) that combines several independently fine-tuned neural networks into a single model by...
  • Expected calibration errorv3Expected calibration error (ECE) is a metric that measures how well a classifier's predicted confidence matches its observed accuracy. A model is well...
  • Longformerv3Longformer is a transformer architecture for processing long documents, introduced by Iz Beltagy, Matthew E. Peters, and Arman Cohan of the Allen Institute for...
  • Sliding window attentionv3Sliding window attention (SWA) is a sparse attention pattern in which each query token attends only to a fixed-size window of nearby tokens instead of to every...
  • DINOv2v6DINOv2 is a family of self-supervised Vision Transformer models released by Meta AI Research in April 2023 that produces general-purpose visual features...
  • SigLIPv5SigLIP (Sigmoid Loss for Language-Image Pre-training) is a family of vision-language encoders developed by researchers at Google DeepMind that pre-trains image...
  • Patchscopesv3Patchscopes is an interpretability framework for inspecting hidden representations of large language models by patching an internal activation from a source...
  • Rectified Flowv4Rectified Flow is a generative modeling framework that learns a transport ordinary differential equation between two probability distributions by regressing a...
  • Representation Engineeringv5Representation Engineering (often abbreviated RepE) is a top-down approach to artificial-intelligence transparency and control that reads and manipulates...
  • Ring Attentionv6Ring Attention, formally Ring Attention with Blockwise Transformers, is a distributed algorithm for computing the self-attention operation of transformer...
  • AdamWv3AdamW is a variant of the Adam optimizer that decouples weight decay from the gradient-based update rule, applying the decay directly to the weights instead of...
  • Latent semantic analysis (LSA)v3Latent semantic analysis (LSA), called latent semantic indexing (LSI) in information retrieval contexts, is an unsupervised technique that maps both terms and...
  • MuZerov4MuZero is a model-based reinforcement learning algorithm developed by DeepMind that masters Go, chess, shogi, and 57 Atari video games at superhuman or state...
  • Texas Responsible AI Governance Actv4The Texas Responsible Artificial Intelligence Governance Act (TRAIGA), enacted as House Bill 149 of the 89th Texas Legislature, Regular Session, is a Texas...
  • SambaNova SN40Lv5The SambaNova SN40L is a reconfigurable dataflow AI accelerator designed by SambaNova Systems and unveiled on September 19, 2023.[1][2] Marketed as a...
  • PR AUCv4See also: precision, recall, ROC curve, AUC, F1 score, confusion matrix, precision-recall curve PR AUC (Precision-Recall Area Under the Curve), also referred...
  • Qinglong V3.0v5--- Developer China Year introduced Active development; open-source platform Height 85 kg (187 lb) Degrees of freedom 400 Nm Computational power...
  • Authors Guild v. OpenAIv2Authors Guild et al. v. OpenAI, Inc., et al. is a putative class action copyright lawsuit filed in the United States District Court for the Southern District...
  • Automatic Differentiationv3Automatic differentiation (abbreviated AD, also called algorithmic differentiation, autodiff, or autograd) is a family of techniques for computing exact...
  • InstructGPTv4InstructGPT is a family of language models released by OpenAI in January 2022 that take the base GPT-3 and fine-tune it to follow user instructions more...
  • Top-p and top-k samplingv5Top-p sampling, also called nucleus sampling, is a text-generation decoding method for large language models (LLMs) that, at each step, samples the next token...
  • Variational Autoencoderv8A variational autoencoder (VAE) is a generative model that learns a probabilistic latent space representation of data using an encoder-decoder architecture...
  • Diffusion policyv5Diffusion policy is a robot imitation-learning method, introduced in 2023 by Cheng Chi, Shuran Song, and collaborators at Columbia University, the Toyota...
  • Scaling Laws for Neural Language Modelsv7Scaling Laws for Neural Language Models is a landmark research paper published by OpenAI on January 23, 2020 (arXiv:2001.08361) that established that the test...
  • AlphaZerov7AlphaZero is a general-purpose reinforcement learning algorithm developed by DeepMind that taught itself to play chess, shogi (Japanese chess), and Go at a...
  • Mixtralv9Mixtral is a family of open-weight Sparse Mixture of Experts (SMoE) large language models developed by Mistral AI, a French artificial intelligence company...
  • DETRv8DETR (DEtection TRansformer) is an end-to-end object detection model that reframes detection as a direct set prediction problem solved with a transformer...
  • Embeddingsv7Embeddings are dense vector representations of data in a continuous vector space, where semantically similar items are mapped to nearby points. An embedding...
  • Mambav11See also: transformer, attention mechanism, recurrent neural network, large language model, Mamba-2, state space model Mamba is a neural network architecture...
  • DeBERTav10DeBERTa (Decoding-enhanced BERT with Disentangled Attention) is a family of pre-trained language models developed by Microsoft Research that improves BERT and...
  • Chromav8Chroma is an open-source embedding database designed for artificial intelligence applications. It stores vector embeddings alongside their associated documents...
  • Latent diffusion modelv7A latent diffusion model (LDM) is a type of diffusion model that runs the denoising diffusion process in a compressed latent space learned by a pretrained...
  • Temperature (artificial intelligence)v6Temperature is a hyperparameter that controls the randomness of a large language model's output by scaling the model's raw scores, called logits, before they...
  • Semantic searchv5Semantic search is an information retrieval approach that finds results based on the meaning and intent behind a query rather than relying solely on exact...
  • Word Embeddingv7A 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...
  • Self-trainingv6See also: Machine learning terms Self-training is a semi-supervised learning procedure in which a model trained on a small labeled set is used to generate...
  • Unidirectional language modelv4See also: Machine learning terms A unidirectional language model is a language model that predicts each token using only the tokens that come before it in the...
  • Test Setv9A test set is a portion of data held back from model development and used only once, after all training and tuning is complete, to give an unbiased estimate of...