Machine Learning

Reinforcement learning

Reinforcement learning (RL) is a branch of machine learning in which an agent learns to make decisions by taking actions in an environment to maximize a...

Artificial IntelligenceDeep Learning

Rejection sampling

Rejection sampling, also called the accept-reject method or the acceptance-rejection method, is a Monte Carlo technique that draws independent samples from a...

Statistics

Replay Buffer

A replay buffer (also called an experience replay buffer or replay memory) is a fixed-size memory that stores an off-policy reinforcement learning agent's past...

Deep LearningReinforcement Learning

Reporting Bias

Reporting bias is a type of data bias in machine learning that occurs when the frequency of events, properties, or outcomes captured in a dataset does not...

AI EthicsData & Datasets

Representation

A representation in machine learning is the format in which a data example is encoded before a model processes it: the same image can be represented as raw...

Deep Learning

Residual connection

A residual connection (also called a skip connection or shortcut connection) is a structural element in neural networks that adds the input of a layer or block...

Deep Learning

Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) is a technique in natural language processing that augments a generative model with an information-retrieval component, so...

Large Language ModelsNatural Language Processing

Return (Reinforcement Learning)

In reinforcement learning, the return (commonly denoted ) is the total cumulative reward an agent receives from time step onward, usually with future...

Reinforcement Learning

Reward

See also: Reinforcement Learning, Policy, Q-Learning, Bellman Equation In reinforcement learning (RL), a reward is a scalar feedback signal that an environment...

Reinforcement Learning

Reward hacking

Reward hacking (also called specification gaming) is a failure mode in artificial intelligence in which a system maximizes its given objective or reward signal...

AI AlignmentAI Safety

Ridge Regression

Ridge regression is a method of estimating the coefficients of a linear regression model by adding a penalty proportional to the sum of squared coefficients...

Training & Optimization

Ridge Regularization

Ridge regularization, also known as L2 regularization or Tikhonov regularization, is a technique in statistics and machine learning that adds a squared L2-norm...

StatisticsTraining & Optimization

RoBERTa

RoBERTa (Robustly Optimized BERT Pretraining Approach) is an open-source natural language processing model released in July 2019 by researchers at Facebook AI...

Deep LearningNatural Language Processing

Robot learning

Robot learning is a field at the intersection of robotics and machine learning in which robots acquire new skills, adapt to new environments, and improve their...

Deep LearningReinforcement Learning

Root

In machine learning, the root is the starting node of a decision tree: the single topmost node that holds the entire training set and encodes the first...

Root Mean Squared Error (RMSE)

Root Mean Squared Error (RMSE), also known as root mean square deviation (RMSD), is a regression evaluation metric equal to the square root of the average of...

Model EvaluationStatistics

Root directory

In machine learning, a root directory is the top level folder, on a local disk or in object storage, under which a training run writes the artifacts it...

Rotational invariance

Rotational invariance is the property of a model, function, or feature whose output does not change when the input is rotated. Formally, a function f is...

SARSA (State-Action-Reward-State-Action)

SARSA (State-Action-Reward-State-Action) is an on-policy temporal-difference (TD) control algorithm that learns the action-value function Q^pi(s, a) of the...

Reinforcement Learning

SGLang

SGLang (short for Structured Generation Language) is a high-performance, open-source serving framework for large language models and multimodal models,...

AI Tools & ProductsLarge Language Models

SMOTE (Synthetic Minority Over-sampling Technique)

SMOTE (Synthetic Minority Over-sampling Technique) is a data preprocessing algorithm that fixes class imbalance by creating new synthetic minority-class...

Algorithms

STaR (Self-Taught Reasoner)

STaR (Self-Taught Reasoner) is a self-training method that teaches a large language model to reason by having it generate its own chain-of-thought rationales,...

Reinforcement Learning

SUPERB

SUPERB, which stands for Speech processing Universal PERformance Benchmark, is a comprehensive evaluation framework designed to measure how well...

AI BenchmarksSpeech & Audio AI

Safetensors

Safetensors is an open-source tensor serialization format developed by Hugging Face that stores machine learning model weights as raw tensor data plus a small...

Developer ToolsOpen Source AI

Sam McCandlish

Sam McCandlish is an American AI researcher and a co-founder of Anthropic, the artificial intelligence company behind the Claude family of language models....

AI CompaniesPeople

Sampling Bias

Sampling bias is a systematic error in statistics and machine learning that occurs when a sample is collected so that some members of the intended population...

AI EthicsData & Datasets

Saver

In machine learning, a Saver is a utility or class that persists and restores the state of a model, its variables, and its optimizer to disk, so training can...

Scalar

See also: vector, matrix, tensor, linear algebra, gradient descent A scalar is a single numerical value, a quantity with magnitude but no direction, and the...

Mathematics

Scaling

In machine learning and artificial intelligence, scaling is an umbrella term for several distinct practices: (1) feature scaling, the data-preprocessing step...

Data & Datasets

Scaling Laws

Neural scaling laws are empirical, power-law relationships that describe how the performance of neural networks in artificial intelligence improves predictably...

Deep LearningLarge Language Models

Scaling Laws for Neural Language Models

Scaling 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...

AI ResearchLarge Language Models

Scikit-learn

Scikit-learn (also known as sklearn) is a free, open-source machine learning library for the Python programming language. It provides simple and efficient...

Score matching

Score matching is a method for fitting a probabilistic model by matching the gradient of its log-density, the so-called score function , to the same gradient...

Diffusion ModelsStatistics

Scoring

See also: Machine learning terms Scoring is the process of applying a trained machine learning model to data so it produces an output number, either a...

Selection Bias

Selection bias is a systematic error that occurs when the data used for analysis, training, or evaluation does not accurately represent the population or...

AI EthicsData & Datasets

Selective Language Modeling (Rho-1)

Selective Language Modeling (SLM) is a pretraining objective for language models that applies the training loss to only a chosen subset of tokens rather than...

Reinforcement Learning

Self-RAG

Self-RAG (Self-Reflective Retrieval-Augmented Generation) is a framework that trains a single large language model to adaptively decide when to retrieve...

AI Agents

Self-Supervised Learning

Self-supervised learning (SSL) is a machine learning approach in which a model learns representations from unlabeled data by generating its own supervisory...

Deep Learning

Self-attention

Self-attention is a mechanism that lets a neural network weigh how much every element of a single input sequence should influence every other element,...

Deep LearningModel Architecture

Self-speculative decoding (LayerSkip)

Self-speculative decoding is a family of speculative decoding methods that accelerate large language model (LLM) inference by using the target model itself,...

AI Infrastructure

Self-training

See 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...

Deep Learning

Semantic search

Semantic search is an information retrieval approach that finds results based on the meaning and intent behind a query rather than relying solely on exact...

Natural Language Processing

Semi-Supervised Learning

See also: Machine learning terms Semi-supervised learning is a machine learning approach that trains a model on a small amount of labeled data together with a...

Sensitive Attribute

A sensitive attribute (also called a protected attribute or protected characteristic) is any feature in a dataset that corresponds to a legally or ethically...

AI Ethics

Sensor fusion

Sensor fusion is the process of combining data from multiple sensors, often of different types, to produce information that is more accurate, complete, or...

Robotics

SentencePiece

SentencePiece is an open-source, language-agnostic subword tokenization library and detokenizer developed at Google and introduced by Taku Kudo and John...

Natural Language ProcessingOpen Source AI

Sentiment Analysis

Sentiment analysis, also called opinion mining or emotion AI, is the use of natural language processing to automatically determine the sentiment, emotion, or...

Natural Language Processing

Sequence Model

A sequence model is a class of machine learning models that processes, generates, or predicts ordered data where the position and surrounding context of each...

Deep LearningNatural Language Processing

Sequence-to-Sequence Task

See also: Machine learning terms, Natural language processing, Recurrent neural network A sequence-to-sequence (seq2seq) task is any machine learning problem...

Deep LearningNatural Language Processing

Serving

In machine learning, serving (also called model serving or inference serving) is the process of deploying a trained model into a production environment so it...

MLOps

Shape (Tensor)

In machine learning, the shape of a tensor is the tuple of integers giving the size of the tensor along each of its axes. For a tensor of rank r, the shape is...

Shrinkage

See also: Machine learning terms Shrinkage in machine learning and statistics is a regularization technique that deliberately pulls model coefficient estimates...

Training & Optimization

Sigmoid Function

See also: Machine learning terms The sigmoid function is a mathematical function that maps any real number to a value between 0 and 1 using the formula ,...

Deep LearningMathematics

SimCLR

SimCLR (Simple Framework for Contrastive Learning of Visual Representations) is a self-supervised learning method for computer vision in which a network is...

Computer VisionDeep Learning

Similarity Measure

A similarity measure (also called a similarity function or similarity metric) is a real-valued function that quantifies the degree of resemblance between two...

Information RetrievalMathematics

Singular value decomposition

See also: principal component analysis, eigenvalue decomposition, linear algebra, matrix factorization, pseudoinverse, low-rank adaptation, Eckart-Young...

Mathematics

Sleep-time compute

Sleep-time compute is a technique for large language model inference in which a model uses idle periods, before any user query has arrived, to "think" about a...

AI Agents

Small language model

A small language model (SLM) is a compact large language model, typically under about 10 billion parameters, built to run efficiently on a single consumer GPU,...

Large Language Models

Snorkel

Snorkel is an open-source software framework and methodology for programmatic data labeling that started at Stanford University in 2015 and is licensed under...

Data & DatasetsOpen Source AI

Social Media

See also: Social Media ChatGPT Plugins Artificial intelligence shapes nearly every part of modern social media, from the order of posts in a feed to the...

AI Tools & Products