CtrlK

Explore AI Wiki

AI Wiki site footer

Browse by topic

All topics Random article

Machine Learning
AI Companies
Large Language Models
Robotics
Open Source AI
AI Models
Deep Learning
Humanoid Robots
AI Hardware
Generative AI
AI Compute

A free, source-backed encyclopedia with 4,000+ articles about artificial intelligence.

Help keep AI knowledge accurate

Start contributing

Contribute

Updates
Requested articles
Missing pages
Corrections log

Standards & trust

About AI Wiki
How we verify
Sourcing standards
AI transparency
Neutral point of view
Editorial policy
Content license

Tools & data

Free AI tools
AI comparisons
API, MCP & open data
Site statistics
RSS feed

From the AI Wiki team

View companion projects

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

Contact
Privacy
Terms

HomeUpdates

Updates

2,489 articles changed in the last 30 days; 52 are new in the last 7 days. Dates show when an article's text last changed, so link and formatting passes do not move it up the list. Page 43 of 50.

All updates New articles

RSS

Tuesday, June 23, 2026

Sundar Pichaiv10Sundar Pichai (Pichai Sundararajan, born June 10, 1972) is the chief executive officer of Google and its parent holding company Alphabet Inc., and the executive who led Google's pivot from a "mobile-first" to…
Instance segmentationv6Instance segmentation is the computer vision task of detecting every object instance in an image and producing a pixel-precise mask for each one
Two-Tower Modelv7The two-tower model, also known as the dual encoder, bi-encoder, or Siamese network for retrieval, is a neural network architecture that encodes a query and a candidate item with two separate sub-networks…
PASCAL VOCv5PASCAL VOC (Pattern Analysis, Statistical Modelling and Computational Learning Visual Object Classes) is a long-running benchmark dataset and annual challenge for object recognition, object detection…
Grounding (artificial intelligence)v10Grounding in artificial intelligence is the process of anchoring an AI system's outputs to verifiable
AutoML (Automated Machine Learning)v5AutoML (Automated Machine Learning) is the automation of the end-to-end pipeline of applying machine learning to real-world data, replacing manual trial and error with a formal search over data preprocessing…
Goodhart's lawv8Goodhart's law states that "when a measure becomes a target, it ceases to be a good measure": any statistical regularity or metric tends to break down once it is used as a target for control or decision-making.
International Conference on Computer Visionv6The International Conference on Computer Vision (ICCV) is one of the three top-tier academic conferences in computer vision, held every two years in odd-numbered years since 1999 and first staged in London in…
Mesa-optimizationv8Mesa-optimization is the situation in AI alignment research in which a learned model, typically a neural network produced by a machine-learning training process, is itself an optimizer that internally searches…
Layerv8A 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 transformation to their input and pass the result…
Area under the curvev9Area under the curve (AUC) is a single scalar metric that summarizes the performance of a binary classifier or diagnostic test across all possible decision thresholds by integrating the area beneath a…
Expert systemv7An expert system is a computer program that emulates the decision-making ability of a human expert in a narrow domain by reasoning over an explicit base of IF-THEN rules and facts rather than learning from…
Convergencev8Convergence in machine learning is the point at which an iterative optimization algorithm reaches a stable solution, meaning the loss function stops decreasing meaningfully and further parameter updates yield…
Mean Absolute Error (MAE)v8Mean Absolute Error (MAE) is a regression accuracy metric and loss function that measures the average absolute difference between predicted values and actual observed values
DQNv9The Deep Q-Network (DQN) is a model-free, off-policy reinforcement learning algorithm that combines Q-learning with a deep neural network function approximator, learning to act directly from raw pixels.
NVIDIA Holoscanv5NVIDIA Holoscan is a domain-agnostic, multimodal AI sensor processing platform and software development kit (SDK) built by NVIDIA for real-time
Precision-Recall Curvev10A precision-recall curve (PR curve) is a graph that plots precision on the y-axis against recall on the x-axis at every possible classification threshold for a binary classification model.
NLUv10Natural Language Understanding (NLU) is the subfield of artificial intelligence and natural language processing that turns unstructured human language into structured representations a computer can act on…
Batchv10A batch in machine learning is the set of training examples processed together in one forward and backward pass before the model's parameters are updated once.

Monday, June 22, 2026

Logitsv10In machine learning and statistics, logits refer to the raw, unnormalized scores output by a model before they are converted into probabilities.
Megatron-LMv7Megatron-LM is NVIDIA's open-source framework for training very large transformer language models across GPU clusters
Categorical Datav9Categorical data, also called qualitative data, is data whose values are discrete labels or groups (such as colors, country names, or blood types) rather than measurable quantities, so they cannot be…
Open weightsv8Open weights is the practice of publishing the trained parameter tensors of a neural network so that anyone can download, run, fine-tune, and redistribute the model without obtaining a separate inference…
Gradient clippingv8Gradient clipping is a training technique that caps the magnitude of gradient values before they update model weights

Sunday, June 21, 2026

HNSWv6Hierarchical Navigable Small World (HNSW) is an approximate nearest-neighbor search algorithm that indexes high-dimensional vectors in a multi-layer proximity graph and answers similarity queries in expected…
AWQ (Activation-aware Weight Quantization)v7Activation-aware Weight Quantization (AWQ) is a post-training quantization method for large language models that compresses weights to 4-bit (and optionally 3-bit) integers while keeping near-FP16 task…
Image Classification Modelsv8Image classification models are machine learning systems that assign one or more category labels to a whole input image, the task that drove the modern wave of deep learning in computer vision.
Labelv7In machine learning, a label is the target output value associated with a single training example: the correct answer that a supervised learning model is trained to predict.
Artificial intelligence terms

NewerPage 43 of 50Older

Edge computingv7Edge computing is a distributed computing paradigm that runs computation and data storage close to where data is generated, at the "edge" of the network

Digital twinv9A digital twin is a virtual replica of a physical object, process, or system that is continuously updated with real-time data from its physical counterpart, so the digital copy mirrors the structure, context…

Service robotv7A service robot is a robot "in personal use or professional use that performs useful tasks for humans or equipment," according to the international vocabulary standard ISO 8373:2021.

Individual Fairnessv7Individual fairness is the principle in machine learning that any two individuals who are similar with respect to a task should receive similar algorithmic outcomes.

Tabninev12Tabnine is a privacy-focused, enterprise artificial intelligence code assistant that provides inline code completions, chat-based assistance, test generation, and code review inside a developer's integrated…

YouTubev8YouTube is an American online video sharing platform owned by Google LLC, a subsidiary of Alphabet Inc., and one of the most important sites in modern artificial intelligence: its recommender system is among…

OpenAI Responses APIv11The OpenAI Responses API is OpenAI's agent-oriented HTTP API, launched on March 11, 2025, that unifies the simplicity of the Chat Completions API with the stateful

Preprocessingv7Preprocessing is the stage of a machine learning workflow that transforms raw data into a clean, consistent, numerical format that learning algorithms can use.

π0v7π0 (pronounced "pi-zero") is a vision-language-action model for general-purpose robot control developed by Physical Intelligence, a San Francisco-based robotics startup, and introduced on October 31, 2024.

Multi-agent systemv13A multi-agent system (MAS) is a system composed of multiple interacting intelligent agents that collaborate, compete, or negotiate to accomplish tasks that would be difficult or impossible for a single agent.

C4 (Colossal Clean Crawled Corpus)v6C4 (Colossal Clean Crawled Corpus) is a roughly 750 GB, cleaned, English-language web text dataset of about 365 million documents and 156 billion tokens that Google created from the April 2019 Common Crawl…

Bias (Math) or Bias Termv8The bias term is a learnable additive constant b added to the weighted sum of a neuron's inputs before an activation function is applied.

Unsupervised Machine Learningv10Unsupervised 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.

Termsv10Terms 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.

Labeled examplev7A labeled example is a single data point used to train a machine learning model that consists of one or more input features paired with the correct answer, called the label.

Autoregressive Modelv5An autoregressive model predicts each element of a sequence from the elements that precede it, feeding its own earlier outputs back in as context for every later prediction.

Markov Chain Monte Carlov6Markov Chain Monte Carlo (MCMC) is a class of algorithms for drawing samples from a probability distribution by constructing a Markov chain whose stationary distribution equals the target distribution.

Exploding Gradient Problemv17The exploding gradient problem is a training failure in deep neural networks where the gradients of the loss function grow exponentially large as they propagate backward through layers during backpropagation…

Bayesian Neural Networkv10A Bayesian neural network (BNN) is a neural network in which the weights and biases are represented as probability distributions rather than fixed point estimates.

Fraud Detection (AI)v6Fraud detection is the application of statistical analysis, machine learning, and rules-based logic to identify illegitimate activity inside payment systems, customer accounts, insurance claims, advertising…

RLAIFv8Reinforcement Learning from AI Feedback (RLAIF) is a family of alignment techniques for large language models in which the preference labels used to fine-tune a model are produced by another AI system

UMAP (Uniform Manifold Approximation and Projection)v8UMAP (Uniform Manifold Approximation and Projection) is a nonlinear dimensionality reduction technique that compresses high-dimensional data into a low-dimensional map (typically 2 or 3 dimensions) while…

CuDNNv10NVIDIA cuDNN (CUDA Deep Neural Network library) is a proprietary GPU-accelerated library of primitives for deep learning, first released by NVIDIA on September 7, 2014, that provides highly tuned…

ConvNeXtv11ConvNeXt is a family of pure convolutional neural network (CNN) models that match or beat Vision Transformers on standard vision benchmarks

Mask R-CNNv6Mask R-CNN is a deep convolutional neural network for instance segmentation, introduced in 2017 by Kaiming He, Georgia Gkioxari, Piotr Dollar, and Ross Girshick at Facebook AI Research (FAIR).

JD.comv6JD.com, Inc. (Chinese: 京东; pinyin: Jīngdōng) is a Beijing-headquartered Chinese e-commerce and technology company that has become one of China's most aggressive corporate adopters of artificial intelligence

Voice AIv5Voice AI is the umbrella term for artificial intelligence systems that listen to, understand, and generate human speech.

European Conference on Computer Visionv5The European Conference on Computer Vision (ECCV) is the biennial top-tier academic conference on computer vision, held in even-numbered years at locations across Europe, and is one of the three most…

GAIA benchmarkv8GAIA (General AI Assistants) is a benchmark for evaluating general-purpose AI agents and assistants on real-world tasks that require reasoning, web browsing, file handling, and multimodal understanding.

LG Electronics (robotics)v10LG Electronics is a South Korean multinational electronics company and a subsidiary of LG Corporation whose artificial intelligence work centers on the EXAONE family of foundation models, built by LG AI…

Experience Replayv9Experience replay is a reinforcement learning technique in which an agent stores its past transitions in a memory called a replay buffer and samples random mini-batches of those stored transitions to train on

Decoderv9A decoder is the component of a neural network that turns an internal, compressed, or abstract representation into a desired output, such as a translated sentence, a generated image, a reconstructed input, or…

Linear Attentionv7Linear attention is a family of sub-quadratic attention mechanisms that replaces the softmax dot-product operation of standard Transformer self-attention with a feature-map-based factorization

Apple Siliconv9Apple silicon is the family of ARM architecture system on a chip (SoC) and system in a package (SiP) processors that Apple Inc. designs for its own products

Classification Thresholdv9A classification threshold (also called a decision threshold or cut-off point) is a numeric value used to convert the continuous probability output of a classification model into a discrete class label.

Noam Shazeerv11Noam Shazeer (born 1975 or 1976) is an American computer scientist and software engineer who is one of the most prolific and influential researchers in the modern era of deep learning, best known as a…

ELECTRAv11ELECTRA, which stands for Efficiently Learning an Encoder that Classifies Token Replacements Accurately

AlphaStarv11AlphaStar is an artificial intelligence system built by Google DeepMind that in 2019 became the first AI to reach Grandmaster level in the real-time strategy game StarCraft II

John Schulmanv9John Schulman is an American artificial intelligence researcher, one of the eleven original co-founders of OpenAI, and the inventor of Proximal Policy Optimization (PPO), the reinforcement-learning algorithm…

GELU (Gaussian Error Linear Unit)v8The Gaussian Error Linear Unit (GELU) is a smooth, non-monotonic activation function defined as GELU(x) = x · Φ(x), where Φ(x) is the cumulative distribution function of the standard normal distribution.

ControlNetv6ControlNet is a neural network architecture that adds spatial and structural control to large pretrained text-to-image diffusion models.

Self-consistencyv6Self-consistency is a decoding strategy for large language models that samples multiple chain-of-thought reasoning paths for the same question and returns the answer that the majority of those paths agree on

Environmentv8In reinforcement learning (RL), an environment is the external system that an agent interacts with: it receives the agent's actions, transitions to a new state, and returns an observation together with a…

Data Analysisv8Data analysis is the process of inspecting, cleaning, transforming, and modeling data to discover useful information, draw conclusions, and support decision-making.

Dan Hendrycksv8Dan Hendrycks (born 1994 or 1995) is an American machine learning researcher who serves as executive director of the Center for AI Safety, the San Francisco nonprofit he co-founded in 2022, and is the lead…

Code Interpreter (Advanced Data Analysis)v5Code Interpreter, later renamed Advanced Data Analysis, is a feature of ChatGPT developed by OpenAI that lets the model write and run Python code inside a sandboxed execution environment to analyze uploaded…

Temperature samplingv8Temperature sampling is the most common decoding control in large language models: a single hyperparameter, written T, that divides the model's output logits before the softmax function so that the formula…

AI chip export controlsv11AI chip export controls are a set of United States regulations that restrict the export, reexport, and in-country transfer of advanced artificial intelligence accelerators (graphics processing units, tensor…

Claude Skillsv10Claude Skills (also marketed as Agent Skills) are a feature developed by Anthropic that lets users package repeatable workflows, instructions, reference materials, and optional executable scripts into…

Adversarial attackv11An 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.

Toyota (robotics)v9Toyota Motor Corporation is a Japanese multinational automotive manufacturer that, through the Toyota Research Institute (TRI) and its Large Behavior Models program

DETRv12DETR (DEtection TRansformer) is an end-to-end object detection model that reframes detection as a direct set prediction problem solved with a transformer encoder-decoder and bipartite matching, removing the…

Conversational Modelsv8Conversational models are computational systems designed to carry on a dialogue with human users in natural language

Wav2Vecv9Wav2Vec is a family of self-supervised learning models from Meta AI (formerly Facebook AI Research) that learn speech representations directly from raw audio waveforms

ACM A.M. Turing Awardv7The ACM A.M. Turing Award is an annual prize given by the Association for Computing Machinery (ACM) for, in the words of the official citation, "contributions of lasting and major technical importance to the…

SentencePiecev7SentencePiece is an open-source, language-agnostic subword tokenization library and detokenizer developed at Google and introduced by Taku Kudo and John Richardson in their 2018 EMNLP system demonstration…

Automatic Differentiationv7Automatic differentiation (abbreviated AD, also called algorithmic differentiation, autodiff, or autograd) is a family of techniques for computing exact derivatives of a function specified by a computer program

Cloud computingv7Cloud computing is the on-demand availability of computer system resources, especially data storage and computing power, delivered over the internet without active management by the end user.

This glossary defines 173 common artificial intelligence terms across 11 categories: foundational concepts, models and architectures, training and adaptation, prompting and interaction, AI agents and…

Lossv11In machine learning, loss (sometimes called error) is a single non-negative number that measures how far a model's prediction is from the correct answer

NeRFv12Neural Radiance Fields (NeRF) is a method for synthesizing photorealistic novel views of a 3D scene by encoding the scene as a continuous 5D function (3D position plus 2D viewing direction) inside a single…

Needle in a Haystack (NIAH)v9Needle in a Haystack (NIAH) is a long-context evaluation that measures whether a large language model can retrieve a single fact (the "needle") inserted at a controlled position inside a long body of text (the…

Harveyv9Harvey is an artificial intelligence platform built for the legal industry, developed by Counsel AI Corporation and headquartered in San Francisco.

AdaGradv9AdaGrad (short for Adaptive Gradient Algorithm) is an optimizer for gradient descent-based machine learning that gives every parameter its own learning rate

Zero shot, one shot and few shot learningv7Zero-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…

TF-IDF (Term Frequency-Inverse Document Frequency)v7TF-IDF (term frequency-inverse document frequency) is a numerical statistic that measures how important a word is to a single document within a larger collection or corpus, computed as the product of two…

Gym (OpenAI Gym / Gymnasium)v10Gym, often written as OpenAI Gym, is an open source Python toolkit for developing and comparing reinforcement learning algorithms, originally released by openai on April 27, 2016.

RedPajamav9RedPajama is a family of large-scale, openly available datasets for training large language models (LLMs), created by Together AI with academic and open-source partners to reproduce, in fully open form

Fairness Metricv9A fairness metric is a quantitative, mathematical measure used to evaluate whether a machine learning model's predictions or decisions treat different demographic groups equitably.

Algorithmic fairnessv7Algorithmic fairness is the study of how automated decision systems can be made to produce decisions that are equitable across protected attributes such as race, gender, age, religion, and disability.

Encoderv10An encoder in machine learning is a neural network component that transforms input data (text, an image, audio, or code) into a compressed, structured representation, often called a latent representation…

DARPA Robotics Challengev7The DARPA Robotics Challenge (commonly abbreviated DRC) was a prize competition organised by the United States Defense Advanced Research Projects Agency (DARPA) that ran from October 2012 through June 2015