Machine Learning

Pruning

Pruning is a family of techniques used in machine learning and artificial intelligence to remove parts of a model or search space that are estimated to be unnecessary for accuracy or optimality.

AI InferenceTraining & Optimization

PyTorch

PyTorch is an open-source software library for tensor computation and machine learning.

Deep LearningDeveloper Tools

Q-Function

The Q-function, also called the action-value function or state-action value function and written $$Q(s, a)$$, is the function in reinforcement learning (RL) that returns the expected cumulative discounted…

Reinforcement Learning

Q-Learning

Q-learning is a model-free, off-policy reinforcement learning algorithm that learns the value of taking a given action in a given state by iteratively updating an action-value function Q(s, a), the expected…

Reinforcement Learning

QuIP / QuIP#

QuIP (Quantization with Incoherence Processing) is a family of weight-only post-training quantization methods for large language models developed in the RelaxML group at Cornell University

AI Infrastructure

Quantile

A quantile is a cut point that divides a probability distribution or a sorted dataset into intervals containing equal portions of the probability or the observations.

Statistics

Quantile bucketing

Quantile bucketing, also called quantile binning, equal-frequency binning, or quantile discretization

Data & Datasets

Quantization

Quantization is the representation of values from a large or continuous set by values from a smaller, usually finite set.

AI InferenceDeep Learning

Quantization-Aware Training (QAT)

Quantization-aware training (QAT) is a model compression technique in which the effects of quantization are simulated during the training or fine-tuning of a neural network, so that the model learns parameter…

AI Infrastructure

Quantum machine learning

Quantum machine learning (QML) is a research field that sits at the intersection of quantum computing and machine learning.

Artificial IntelligenceComputer Science

Question answering

Question answering (QA) is the task of producing an answer to a question, usually expressed in natural language.

Information RetrievalNatural Language Processing

Queue

A queue in machine learning is a First-In-First-Out (FIFO) data structure that stages and buffers data between an input/output stage and a compute stage so that elements are processed in the order they were…

Quiet-STaR

Quiet-STaR is a self-supervised training method that teaches a large language model to generate short, token-level internal "thoughts," or rationales, that help it predict the text that follows

Reinforcement Learning

R (programming language)

R is a free, open-source programming language and software environment for statistical computing and graphics.

Programming LanguagesStatistics

RAPTOR

RAPTOR (Recursive Abstractive Processing for Tree-Organized Retrieval) is a retrieval method for retrieval-augmented generation introduced in a 2024 paper by researchers at Stanford University.

AI Agents

RLAIF

Reinforcement 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

AI SafetyReinforcement Learning

ROC (Receiver Operating Characteristic) Curve

A Receiver Operating Characteristic (ROC) curve is a graph that measures how well a binary classification system separates two classes by plotting its true positive rate (TPR, also called sensitivity or…

Model Evaluation

ROUGE

ROUGE (Recall-Oriented Understudy for Gisting Evaluation) is a set of automatic metrics that score the quality of a machine-generated text summary by counting how many overlapping units (n-grams, word…

Model EvaluationNatural Language Processing

RWKV

RWKV (pronounced "RwaKuv") is an open-source neural network architecture that combines the parallelizable training of Transformers with the constant-time

Deep LearningModel Architecture

Random Forest

A random forest is an ensemble learning method that combines many randomized decision trees. Each tree is built from a randomized view of the training data, and the ensemble aggregates the trees' predictions.

Random Policy

A random policy is a reinforcement learning policy that chooses actions from a fixed probability distribution, most commonly the uniform distribution, independent of the current state and of any learned value…

Reinforcement Learning

Rank (Tensor)

In machine learning and deep learning frameworks, the rank of a tensor is the number of dimensions (axes) it has: the count of indices you must supply to pick out a single scalar element.

Ranking

Ranking in machine learning, often called learning to rank (LTR), is the supervised task of ordering a set of items by relevance to a query

Information Retrieval

Ray (framework)

Ray is an open-source distributed computing framework, developed at the University of California, Berkeley's RISELab and commercialized by Anyscale, that lets developers scale Python and artificial…

AI InfrastructureDeveloper Tools

ReLU

ReLU, short for rectified linear unit, is an activation function that maps a real input to its positive part:

Deep LearningNeural Networks

ReST / ReST-EM (Reinforced Self-Training)

ReST (Reinforced Self-Training) is a family of self-training algorithms for large language models that improve a model by fine-tuning it on its own filtered outputs instead of on additional human-written data.

Reinforcement Learning

Reasoning (artificial intelligence)

Reasoning 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.

Artificial IntelligenceLarge Language Models

Reasoning models

Reasoning models are large language models that are post-trained or configured to spend additional inference-time computation on intermediate steps before returning an answer.

Artificial IntelligenceLarge Language Models

Recall (metric)

Recall is a classification and retrieval metric that measures the proportion of actual positive instances a model correctly identifies, defined as TP / (TP + FN)

Model Evaluation

Recommendation System

A recommendation system (also called a recommender system) is an information filtering system that predicts a user's preferences and ranks the items most likely to interest that user, such as the movies…

Recommender System

A recommender system (also called a recommendation system or recommendation engine) is an information filtering system that predicts the preference a user would give to an item and uses those predictions to…

AI Tools & ProductsInformation Retrieval

Rectified Linear Unit (ReLU)

The Rectified Linear Unit (ReLU) is the most widely used activation function in deep learning, defined mathematically as $$f(x) = \max(0, x)$$: it returns the input directly when positive and outputs zero…

Deep LearningNeural Networks

Recurrent Neural Network

A recurrent neural network (RNN) is a neural network whose computation includes a state that is passed from one step to the next.

Deep LearningModel Architecture

Recursive self-improvement

Recursive self-improvement (RSI) is a process in which an artificial intelligence system improves its own intelligence or its ability to improve itself, so that each enhancement increases its capacity for…

AI SafetyArtificial Intelligence

RedPajama

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

Data & DatasetsNatural Language Processing

Reflection AI

Reflection AI is an American artificial intelligence company that builds autonomous coding agents and frontier open-weight foundation models, founded in March 2024 by former Google DeepMind researchers Misha…

AI Companies

Reflexion

Reflexion is a 2023 framework for reinforcing language agents through verbal self-reflection rather than weight updates: the agent reflects in natural language on feedback from failed attempts, stores those…

AI AgentsReasoning Models

Regression (statistics and machine learning)

Regression is a family of statistical and machine learning methods for modelling the relationship between a numeric outcome variable and one or more explanatory variables (often called predictors, features, or…

Statistics

Regularization

Regularization is any deliberate change to a learning problem or training algorithm intended to improve performance on data that were not used to fit the model.

Deep LearningTraining & Optimization

Regularization Rate

The regularization rate (commonly denoted as $$\lambda$$ or alpha) is a hyperparameter that controls the strength of the penalty applied to a model's parameters during training.

Training & Optimization

Reinforcement Learning from Human Feedback (RLHF)

Reinforcement learning from human feedback (RLHF) is a family of methods in which judgments supplied by people are converted into a reward signal and a policy is optimized with reinforcement learning against…

AI AlignmentDeep 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 cumulative reward signal, discovering good behavior…

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 hard-to-sample target distribution p(x) by…

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 transitions, each a tuple of state, action…

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 reflect their real-world frequency, because people…

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 pixels, a list of hand-designed measurements, or a…

Deep Learning

Representation learning

Representation learning is the area of machine learning concerned with getting a system to discover the features it needs for a task, instead of having people specify those features by hand.

Deep LearningTraining & Optimization

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 directly to its output

Deep Learning

Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) is a family of methods that retrieves information from an external collection and conditions a generative model on that information when producing an output.

Large Language ModelsNatural Language Processing

Return (Reinforcement Learning)

In reinforcement learning, the return (commonly denoted $$G_t$$) is the total cumulative reward an agent receives from time step $$t$$ onward, usually with future rewards discounted by a factor $$\gamma$$.

Reinforcement Learning

Reward

In reinforcement learning (RL), a reward is a scalar feedback signal that an environment sends to an agent after each action, quantifying how desirable that action's outcome was

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 through unintended shortcuts, exploits, or…

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 (the squared L2 norm) to the ordinary least squares…

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 penalty to a model's loss function.

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 (now Meta AI) and the University of Washington…

Deep LearningNatural Language Processing

Robot learning

Robot learning studies how robots acquire or improve behavior from data and experience.

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 condition the tree evaluates, at depth 0.

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 the squared differences between predicted and…

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 produces and a serving run later reads: checkpoints…

Rotational invariance

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