Machine Learning

KV Cache

A KV cache (key-value cache) is a memory optimization technique used during transformer inference that stores previously computed key and value tensors from...

AI InferenceDeep Learning

KV-cache quantization

KV cache quantization is a family of large language model inference optimizations that store the attention key and value (KV) cache in low-bit numeric formats,...

AI Infrastructure

Keras

Keras is an open-source, high-level neural network API written in Python that lets developers build, train, and deploy deep learning models with minimal code....

AI Tools & ProductsDeep Learning

Kernel Support Vector Machines (KSVMs)

See also: Machine learning terms A kernel support vector machine (kernel SVM, or KSVM) is a supervised learning algorithm that finds the maximum-margin...

Knowledge Distillation

Knowledge distillation (also known as model distillation) is a model compression technique in machine learning in which a smaller model, called the student, is...

AI InferenceDeep Learning

Knowledge Editing

Knowledge editing (also called model editing) is a family of techniques for updating or correcting specific factual associations stored in the weights of a...

Large Language ModelsNatural Language Processing

Kolmogorov-Arnold Network

A Kolmogorov-Arnold Network (KAN) is a type of neural network architecture proposed as an alternative to the traditional Multi-Layer Perceptron (MLP)....

Deep LearningNeural Networks

Kubeflow

Kubeflow is an open-source MLOps platform that runs the entire machine learning lifecycle on Kubernetes, described by its creators as a project "dedicated to...

Developer ToolsMLOps

L0 Regularization

L0 regularization is a regularization technique in machine learning and statistics that penalizes the number of nonzero parameters in a model, a quantity...

Training & Optimization

L1 Loss

L1 loss is a regression loss function equal to the average of the absolute differences between predicted values and target values, written as . It is also...

StatisticsTraining & Optimization

L1 Regularization

L1 regularization is a regularization technique in machine learning and statistics that prevents overfitting by adding the sum of the absolute values of a...

Training & Optimization

L2 Loss

L2 loss is the squared-error loss function: for a true value and a predicted value , it is the squared difference , and averaging it across a dataset gives...

StatisticsTraining & Optimization

L2 Regularization

See also: machine learning terms, regularization, L1 regularization, elastic net, overfitting L2 regularization is a technique in machine learning and...

Training & Optimization

LAION

LAION (Large-scale Artificial Intelligence Open Network) is a German non-profit organization, registered as LAION e.V. in Hamburg, that builds and releases...

Computer VisionData & Datasets

Label

In machine learning, a label is the target output value associated with a single training example: the correct answer that a supervised learning model is...

Data & Datasets

Labeled example

A 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,...

Lambda

See also: Machine learning terms Lambda (the Greek letter λ) is a symbol used across machine learning, statistics, and computer science to denote several...

Mathematics

Landmarks

Landmarks are reference points used as anchors in two largely separate areas of machine learning. In manifold learning and dimension reduction, landmarks are a...

Computer Vision

Language Model

A language model is a probabilistic model that assigns a probability to a sequence of words or tokens in a natural language, most often by estimating the...

Deep LearningNatural Language Processing

Large Behavior Model

A Large Behavior Model (LBM) is a single neural network for robotics that is pretrained on large, diverse datasets of robot demonstrations and outputs robot...

Embodied AIRobotics

Large Language Model

See also: Machine learning terms, Natural language processing, Transformer A large language model (LLM) is an artificial intelligence system built on a...

Artificial IntelligenceDeep Learning

Lasso Regression

Lasso regression (an acronym for Least Absolute Shrinkage and Selection Operator) is a linear regression method, introduced by Robert Tibshirani in 1996, that...

Training & Optimization

Latent Dirichlet allocation

Latent Dirichlet allocation (LDA) is a generative probabilistic model that discovers the hidden thematic structure in a collection of documents by treating...

Artificial IntelligenceNatural Language Processing

Latent reasoning via recurrent depth (Huginn)

Latent reasoning via recurrent depth is an approach to scaling a language model's test-time computation by iterating a recurrent transformer block in latent...

Deep Learning

Layer

A 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...

Deep LearningNeural Networks

Layer-wise Relevance Propagation (LRP)

Layer-wise Relevance Propagation (LRP) is an explainable AI method that explains the prediction of a deep neural network by propagating the model's output...

Deep LearningInterpretability

Leaf

See also: Machine learning terms A leaf (also called a terminal node) is a node in a decision tree that has no children and holds the model's prediction. Every...

Learning Rate

The learning rate is a hyperparameter in machine learning that controls how much a model's parameters change in response to the estimated error each time the...

Deep LearningTraining & Optimization

Least Squares Regression

Least squares regression is a statistical method that fits a model to data by choosing the parameters that minimize the sum of the squared residuals, the...

Statistics

LightGBM

LightGBM (short for Light Gradient-Boosting Machine) is a free and open-source gradient boosting framework that trains ensembles of decision trees on tabular...

AlgorithmsOpen Source AI

Lilian Weng

Lilian Weng is an artificial intelligence researcher known for her work at OpenAI, where she spent about seven years and led the Safety Systems team as Vice...

AI SafetyPeople

Linear

See also: Machine learning terms In machine learning and mathematics, linear describes a function or relationship in which the output is built from the inputs...

Mathematics

Linear Discriminant Analysis

Linear Discriminant Analysis (LDA) is a classical statistical method for classification and dimensionality reduction that finds the linear combination of...

Statistics

Linear Regression

Linear regression is a statistical method that models the relationship between one or more independent variables (the predictors or features) and a continuous...

Statistics

Linear model

A linear model is any statistics or machine learning model whose prediction is a linear function of its input features, of the form f(x) = g(w1 x1 + w2 x2 +...

Statistics

LiveBench

LiveBench Description 2024-06-12 Latest version 2026-01-08 Authors Abacus.AI, NYU, NVIDIA, University of Maryland, USC Technical Details Type Text...

AI BenchmarksNatural Language Processing

LiveCodeBench

LiveCodeBench is a holistic and contamination-free benchmark for evaluating large language models on code, first released in March 2024 by researchers at UC...

AI BenchmarksAI Code Generation

Llama 2

Llama 2 (Large Language Model Meta AI 2; sometimes stylized LLaMA 2 after the original paper's backronym) is a family of large language models developed and...

Large Language ModelsMeta AI

LoRA (Low-Rank Adaptation)

LoRA (Low-Rank Adaptation) is a parameter-efficient fine-tuning technique that freezes a pre-trained model's weights and trains small, injected low-rank...

Deep LearningNatural Language Processing

Log Loss

Log loss is the negative log-likelihood of the predicted probabilities and the standard loss function for probabilistic classification: for binary labels it is...

MathematicsTraining & Optimization

Log-Odds

Log-odds, also known as the logit, is a mathematical transformation that converts a probability value between 0 and 1 into a real number spanning from negative...

MathematicsStatistics

Logistic Regression

See also: Machine learning terms Logistic regression is a statistical method that models the probability of a binary (yes/no) outcome as a function of one or...

Statistics

Logits

In machine learning and statistics, logits refer to the raw, unnormalized scores output by a model before they are converted into probabilities. The term has...

Deep LearningNeural Networks

Long Short-Term Memory (LSTM)

Long Short-Term Memory (LSTM) is a specialized type of recurrent neural network (RNN) architecture designed to learn long-range dependencies in sequential...

Deep LearningModel Architecture

Loss

See also: Machine learning, Loss function, Gradient descent In machine learning, loss (sometimes called error) is a single non-negative number that measures...

Training & Optimization

Loss Curve

See also: Machine learning terms, Loss function A loss curve is a plot that shows the value of a loss function over the course of training a machine learning...

Deep LearningModel Evaluation

Loss Function

See also: Machine learning terms A loss function is a mathematical formula that measures how far a machine learning model's prediction is from the correct...

Deep LearningTraining & Optimization

Loss Surface

The loss surface (also called the loss landscape, the error surface, or the objective function surface) is the geometric representation of a loss function as a...

Deep LearningTraining & Optimization

MBPP

MBPP (Mostly Basic Python Problems) is a code generation benchmark of 974 crowd-sourced Python programming tasks designed to be solvable by entry-level...

AI BenchmarksAI Code Generation

METEOR (metric)

METEOR (Metric for Evaluation of Translation with Explicit ORdering) is an automatic evaluation metric for machine translation and other text-generation tasks...

Model EvaluationNatural Language Processing

MLPerf

MLPerf is the AI industry's standard suite of benchmarks for measuring how fast machine learning systems train and run models, developed and maintained by...

AI BenchmarksAI Hardware

MLflow

MLflow is an open-source platform for managing the end-to-end machine learning lifecycle, covering experiment tracking, model packaging, a model registry,...

Developer ToolsMLOps

MMLU-Pro

Massive Multitask Language Understanding Professional Abbreviation A more robust and challenging multi-task language understanding benchmark with 10-choice...

AI BenchmarksLarge Language Models

MMMU

MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark) is a multimodal AI benchmark of 11,550 college-level questions that pairs text...

AI BenchmarksMultimodal AI

MNIST

The Modified National Institute of Standards and Technology (MNIST) database is a collection of 70,000 grayscale images of handwritten digits (0 through 9)...

Computer VisionData & Datasets

Machine Learning

See also: Machine learning terms and artificial intelligence Machine learning (ML) is a branch of artificial intelligence that gives computers the ability to...

Artificial IntelligenceComputer Science

Machine learning terms

Machine learning terms are the standardized vocabulary used to describe how models learn from data, including concepts such as features, labels, loss, gradient...

Machine learning terms/All

See also: Machine learning terms This alphabetical glossary collects core terminology used across machine learning, deep learning, reinforcement learning,...

Machine learning terms/Clustering

See also: Machine learning terms Clustering is a class of unsupervised machine learning techniques that partition a set of objects into groups, called...

Machine learning terms/Computer Vision

The key machine learning terms for computer vision describe how neural networks turn pixels into predictions: a convolution slides a small learned filter...

Computer Vision