Machine Learning

A/B Testing

A/B testing (also called split testing, bucket testing, or an online controlled experiment) is a randomized controlled experiment that compares two variants, a control (A) and a treatment (B), by randomly…

Data ScienceStatistics

AI Agents

An AI agent is a software system that selects and performs actions in an environment in pursuit of an objective.

AI AgentsArtificial Intelligence

AI Alignment

AI alignment is the study and practice of making artificial intelligence systems behave in ways that accord with intended goals, preferences, constraints, or institutions. The term is used at several levels.

AI EthicsAI Safety

AI for Science

AI for science is the use of artificial intelligence, particularly deep learning and large language models, to accelerate scientific discovery across biology, chemistry, physics, materials science…

Artificial Intelligence

AI in drug discovery

AI in drug discovery (also called AI drug discovery) is the application of artificial intelligence, machine learning, deep learning, generative models, and natural language processing across the pharmaceutical…

AI Tools & ProductsAI for Science

AQLM (Additive Quantization of Language Models)

AQLM, short for Additive Quantization of Language Models, is a weight-only post-training quantization method that compresses the weights of a large language model to roughly 2 to 3 bits per parameter while…

AI Infrastructure

ARC-AGI-2

ARC-AGI-2 (Abstraction and Reasoning Corpus for Artificial General Intelligence 2) is an abstract reasoning benchmark for artificial intelligence, released on March 24, 2025 by the ARC Prize Foundation

2025 in artificial intelligenceAI Benchmarks

ARIMA

ARIMA (Autoregressive Integrated Moving Average) is a class of statistical models for analyzing and forecasting time series data, specified by three non-negative integer orders written as ARIMA(p, d, q): p is…

Statistics

AUC (Area Under the ROC Curve)

AUC (Area Under the ROC Curve) is a classifier evaluation metric equal to the probability that a model ranks a randomly chosen positive instance higher than a randomly chosen negative instance.

Model Evaluation

AUC-ROC

AUC (Area Under the Curve), most often the area under the ROC curve (AUC-ROC), is a threshold-independent evaluation metric that measures how well a binary classification model ranks positive cases above…

Model EvaluationStatistics

Abacus.AI

Abacus.AI is an American enterprise artificial intelligence and machine learning platform company headquartered in San Francisco, California.

AI CompaniesDeveloper Tools

Absolute Zero Reasoner

Absolute Zero Reasoner (AZR) is a research system for post-training a pretrained language model through self-play on machine-generated Python reasoning tasks.

Deep Learning

Accuracy

Accuracy is a classification metric that measures the fraction of predictions a model gets right: the number of correct predictions divided by the total number of predictions.

Model Evaluation

Action (Reinforcement Learning)

In reinforcement learning (RL), an action is a decision or move made by an agent that affects the state of the environment.

Reinforcement Learning

Action Chunking with Transformers (ACT)

Action Chunking with Transformers (ACT) is an imitation learning algorithm for fine-grained robotic manipulation that predicts a short sequence (a "chunk") of future actions at once instead of a single next…

RoboticsTransformer Models

Activation Function

An activation function is a nonlinear mathematical function applied to the output of each neuron in an artificial neural network, and it is what gives the network the ability to learn complex

Deep LearningNeural Networks

Active Learning

Active learning is a subfield of machine learning in which the learning algorithm interactively chooses which data points it wants labeled

Actor-critic methods

Actor-critic methods are a family of reinforcement learning algorithms that learn two things at once: a parameterized policy, called the actor, which chooses actions, and a value function, called the critic

AlgorithmsDeep Learning

AdaBoost

AdaBoost (short for Adaptive Boosting) is a machine learning ensemble algorithm that combines many weak classifiers into a single strong classifier through a weighted majority vote, training the weak learners…

AdamW

AdamW 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 folding it into the loss as an L2 penalty.

Training & Optimization

Agentic Context Engineering

Agentic Context Engineering (ACE) is a framework for scalable and efficient context adaptation in large language models (LLMs) that lets an AI system improve itself by treating its own context as an evolving

AI AgentsArtificial Intelligence

Agentic video understanding

Agentic video understanding is an approach to video analysis in which a reasoning model chooses which parts of a video to inspect for a particular question.

Computer VisionMultimodal AI

Agglomerative clustering

Agglomerative clustering is a bottom-up form of hierarchical clustering used in unsupervised learning in which each data point starts in its own singleton cluster and the algorithm repeatedly merges the two…

AlexNet

AlexNet is a deep learning convolutional neural network, built by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton at the University of Toronto, that won the ImageNet Large Scale Visual Recognition…

Computer VisionDeep Learning

Algorithmic bias

Algorithmic bias is the tendency of a computer system to produce systematic, repeatable errors that advantage some groups of people over others.

AI EthicsAI Policy & Regulation

Algorithmic fairness

Algorithmic 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.

AI EthicsAI Safety

AlphaFold

AlphaFold is an artificial intelligence system developed by Google DeepMind that predicts the three-dimensional structure of a protein directly from its amino acid sequence.

Artificial IntelligenceGoogle

Amazon SageMaker

Amazon SageMaker is Amazon Web Services' fully managed machine learning platform for building, training, and deploying models at scale, first launched at AWS re:Invent on November 29, 2017 and rebranded in…

AI InfrastructureAI Tools & Products

Andrew Barto

Andrew Barto is an American computer scientist and one of the founders of modern reinforcement learning, the branch of machine learning in which an agent learns by trial and error from rewards.

PeopleReinforcement Learning

Andrew Ng

Andrew Ng is a British-American computer scientist and entrepreneur who is one of the most influential figures in modern artificial intelligence, best known for co-founding Google Brain and Coursera, serving…

Artificial Intelligence

Anomaly Detection

In machine learning, anomaly detection is the process of identifying data points, events, or observations that deviate significantly from normal patterns in a dataset.

Data Science

Approximate Nearest-Neighbor Search

Approximate nearest-neighbor search (ANN or ANNS) finds points close to a query while allowing some error relative to an exact nearest-neighbor result. It is a family of search methods, not a single algorithm.

AlgorithmsInformation Retrieval

Area under the PR curve

The area under the precision-recall curve (AUPRC), also known as average precision (AP) or PR-AUC, is a scalar summary of a binary classifier's performance across every decision threshold.

Area under the curve

Area 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…

Model EvaluationStatistics

Artificial Intelligence

Artificial intelligence (AI) is the field of computer science dedicated to creating systems that perform tasks normally requiring human intelligence, such as learning, reasoning, recognizing patterns…

Artificial IntelligenceComputer Science

Attention

Attention is a family of operations in neural networks that computes an output by assigning data-dependent weights to a collection of representations and combining them.

Deep LearningNeural Networks

Attention Is All You Need

"Attention Is All You Need" is the 2017 research paper that introduced the transformer, the neural network architecture that underpins virtually every modern large language model.

Deep LearningNatural Language Processing

Attention-FFN disaggregation

Attention-FFN disaggregation (AFD), also written attention-feedforward disaggregation or A/F disaggregation, is a large language model serving architecture that runs the attention sublayers and the…

AI InferenceAI Infrastructure

Attribute

In machine learning and data mining, an attribute is an individual measurable property of an object, observation, or example that describes the instance being analyzed, and it forms one column of a tabular…

Attribute sampling

Attribute sampling is a randomization technique in which a decision tree considers only a small, randomly drawn subset of the available input features when searching for the best split at each node

Audio Classification Models

Audio classification models are machine learning systems for audio classification, the task of assigning one or more labels to an audio recording or to short fragments of it.

Deep LearningSpeech & Audio AI

Automatic Differentiation

Automatic 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

AI InfrastructureMathematics

Automation Bias

Automation bias is the tendency for humans to favor suggestions and outputs from automated decision-making systems over contradictory information from non-automated sources

AI Ethics

Autoregressive Model

An 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.

Large Language Models

Average Precision

Average precision (AP) is an evaluation metric that summarizes the precision-recall curve of a ranked list into a single number between 0 and 1, equal to the area under that curve.

Computer VisionInformation Retrieval

Axis-aligned condition

In a decision tree, an axis-aligned condition is a split test at an internal node that involves only a single feature, comparing that one feature against a threshold (for example, "is feature_j greater than or…

BERTScore

BERTScore is an automatic, reference-based metric for evaluating text generation that scores a candidate sentence against one or more references by comparing the contextual embeddings of their tokens rather…

Model EvaluationNatural Language Processing

BIG-Bench

BIG-Bench (Beyond the Imitation Game Benchmark) is a large-scale, collaborative benchmark of 204 tasks, contributed by 450 authors across 132 institutions, built to measure and extrapolate the capabilities of…

AI BenchmarksLarge Language Models

BIG-Bench Hard

BIG-Bench Hard (BBH) is a suite of 23 challenging tasks drawn from the BIG-Bench benchmark, selected because they are "the [tasks] for which prior language model evaluations did not outperform the average…

AI BenchmarksNatural Language Processing

BLEU (Bilingual Evaluation Understudy)

BLEU (Bilingual Evaluation Understudy) is an automatic evaluation metric that scores the quality of machine translation output by measuring how many word sequences (n-grams) it shares with one or more human…

Model EvaluationNatural Language Processing

Backpropagation

Backpropagation is an algorithm for computing derivatives of a scalar objective with respect to variables in a layered or otherwise composed computation.

Deep LearningNeural Networks

Bag of Words

The 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 predefined vocabulary appears, while discarding…

Natural Language Processing

Bagging

Bagging, short for bootstrap aggregating, is an ensemble learning technique in machine learning that trains many copies of the same base model on different random resamples of the training data and combines…

Baseline

In machine learning, a baseline is a simple reference model or method used as a point of comparison to judge whether a more complex model actually adds value.

Model Evaluation

Batch

A 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.

Deep Learning

Batch Normalization

Batch normalization (BatchNorm or BN) is a normalization method used inside some neural networks.

Deep LearningNeural Networks

Batch Size

In machine learning, batch size is the hyperparameter that sets how many training examples a model processes together before it updates its parameters with one step of gradient descent.

Deep Learning

Bayes' theorem

Bayes' theorem (also called Bayes' rule or Bayes' law) is a fundamental theorem of probability theory that describes how to update the probability of a hypothesis given new evidence.

MathematicsStatistics

Bayesian Neural Network

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

Deep LearningNeural Networks

Bayesian Optimization

Bayesian optimization is a sequential, model-based strategy for finding the global optimum of expensive black-box functions in as few evaluations as possible.

Training & Optimization