Machine Learning

Epsilon Greedy Policy

The epsilon-greedy policy (also written as ε-greedy) is a simple action-selection rule for reinforcement learning and multi-armed bandit problems: with probability 1 - ε the agent picks the action with the…

Reinforcement Learning

Equality of Opportunity

Equality of opportunity is a group-fairness criterion in machine learning that requires a classifier's true positive rate (TPR) to be equal across all groups defined by a sensitive attribute: qualified…

AI Ethics

Equalized Odds

Equalized odds is a group fairness criterion in machine learning that requires a classifier's true positive rate (TPR) and false positive rate (FPR) to be equal across all groups defined by a protected…

AI Ethics

Estimator

An estimator is a rule, function, or algorithm that takes observed data and produces a value intended to approximate some unknown quantity, typically a parameter of a probability distribution or a function…

Statistics

Estimator (tf.estimator)

tf.estimator is a high-level TensorFlow API that encapsulates the complete lifecycle of a machine learning model, including training, evaluation, prediction, and export for serving.

Deep LearningDeveloper Tools

Evol-Instruct

Evol-Instruct is a method for automatically generating large instruction tuning datasets by prompting a large language model to rewrite

Reinforcement Learning

Example

In machine learning, an example is a single data point that a model trains on or makes a prediction about: in supervised settings it is a pair $(x, y)$ where $x$ is a vector of features and $y$ is a label, and…

Expectation-Maximization (EM) Algorithm

The Expectation-Maximization (EM) algorithm is an iterative method for finding maximum likelihood or maximum a posteriori (MAP) estimates of the parameters of statistical models that involve latent…

Statistics

Expected calibration error

Expected calibration error (ECE) is a metric that measures how well a classifier's predicted confidence matches its observed accuracy.

Model EvaluationStatistics

Experience Replay

Experience 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

Reinforcement Learning

Experimenter's Bias

Experimenter's bias (also called the observer-expectancy effect, experimenter expectancy effect, or experimenter effect) is a type of cognitive bias in which a researcher's expectations or beliefs about the…

AI EthicsStatistics

Exploding Gradient Problem

The 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…

Deep LearningNeural Networks

F1 score

The F1 score (also written as F1-score, F-score, or F-measure) is the harmonic mean of precision and recall, calculated as $$F_1 = \frac{2 \cdot (\text{Precision} \cdot \text{Recall})}{\text{Precision} +…

Model EvaluationStatistics

Fairness Constraint

A fairness constraint is an explicit mathematical condition imposed on a machine learning model during training, evaluation, or post-processing that forces its predictions to satisfy a specified group-fairness…

AI Ethics

Fairness Metric

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

AI EthicsModel Evaluation

False Negative Rate

The false negative rate (FNR), also known as the miss rate, is the proportion of actual positive instances that a model or test incorrectly classifies as negative, computed as FNR = FN / (FN + TP).

Model EvaluationStatistics

False Positive Rate (FPR)

The false positive rate (FPR) is the proportion of actual negative cases that a test, model, or decision process incorrectly classifies as positive, defined as FPR = FP / (FP + TN) where FP is the number of…

Model EvaluationStatistics

False negative

A false negative (FN), also called a Type II error or a miss, is an instance whose true label is positive but that a classification model or test predicts as negative: a real positive case that the model fails…

Model EvaluationStatistics

False positive

A false positive (FP), also called a Type I error or a false alarm, is an instance whose true label is negative but whose predicted label is positive: the classifier raises an alarm where none was warranted.

Model EvaluationStatistics

Feature

In machine learning and statistics, a feature is an individual measurable property or characteristic of a phenomenon being observed, used as an input variable from which a model learns patterns and makes…

Data & Datasets

Feature Cross

A feature cross (also called a crossed feature or feature interaction) is a synthetic feature created by combining two or more existing features so that a model can learn their joint effect on a prediction.

Data & Datasets

Feature Engineering

Feature engineering is the process of using domain knowledge to create, transform, and select features from raw data so that machine learning models can learn more effectively.

Data & Datasets

Feature Extraction

Feature extraction is the process of transforming raw data into a smaller set of derived, informative numerical variables called features that capture the essential structure of the input while discarding…

Data & Datasets

Feature Importances

Feature importances are numeric scores that quantify how much each input feature contributes to the predictions of a machine learning model.

InterpretabilityModel Evaluation

Feature Selection

Feature selection is the process of choosing a subset of the most relevant input variables (features) from a larger candidate pool for use in a machine learning model, with the goal of finding the smallest set…

AlgorithmsData & Datasets

Feature Set

A feature set is the complete collection of input variables (features, attributes, or predictors) that a machine learning model uses to learn patterns and make predictions.

Data & DatasetsData Science

Feature Vector

A feature vector is an n-dimensional, ordered list of numerical values that represents the measurable properties of an object, data point, or observation in a format suitable for processing by machine learning…

Data & Datasets

Feature spec

A feature spec (short for feature specification) is a declarative description of the input features used by a machine learning model: the name of each feature, its data type, its shape, whether it is required…

Federated Learning

Federated learning is a machine learning technique that trains a shared model across many decentralized devices or servers without moving their raw data to a central location.

AI EthicsDeep Learning

Feedback Loop

A feedback loop in machine learning is a cycle in which a deployed model's predictions influence the real world, and the resulting data is then collected and used to retrain the same model

AI Ethics

Feedforward Neural Network (FFN)

A feedforward neural network (FFN), also called a multilayer perceptron (MLP) when it has multiple layers, is a type of artificial neural network in which information flows in one direction only, from the…

Deep LearningNeural Networks

Few-Shot Learning

Few-shot learning is a branch of machine learning in which a model learns to recognize new classes or perform new tasks from only a very small number of labeled examples, typically one to five per class .

Deep Learning

Fine Tuning

Fine-tuning is the process of adapting a pretrained machine-learning model by continuing to optimize some or all of its parameters on data selected for a target task, domain, behavior, or population.

Deep LearningTraining & Optimization

FineWeb

FineWeb is a large-scale, open pretraining dataset for large language models (LLMs) created by Hugging Face.

Data & DatasetsNatural Language Processing

FineWeb-2

FineWeb-2 (also written FineWeb2) is a massively multilingual web pretraining dataset released by Hugging Face in December 2024.

Data & Datasets

FineWeb-Edu

FineWeb-Edu is an open, English-language pretraining dataset of roughly 1.3 trillion tokens

Data & DatasetsLarge Language Models

Flash Attention

FlashAttention is a family of exact, input/output-aware algorithms and GPU kernels for scaled dot-product attention.

Focal loss

Focal loss is a loss function that reshapes standard cross-entropy loss by adding a (1 - p_t)^gamma modulating factor, which down-weights well-classified (easy) examples so that training concentrates on hard

Computer VisionDeep Learning

Forget Gate

The forget gate is a sigmoid layer inside a Long Short-Term Memory (LSTM) recurrent neural network that decides, element by element, how much of the previous cell state to keep and how much to discard at each…

Neural Networks

Frontis-MA1

Frontis-MA1 is a family of open-weight large language models post-trained to act as agents for machine learning engineering (MLE), released in late July 2026 by FrontisAI

AI AgentsAI Models

Full Softmax

Full softmax (also called the standard softmax or exact softmax) is the softmax computation that calculates a probability for every possible output class in a classification model

Deep LearningNatural Language Processing

Fully Connected Layer

A fully connected layer (also called a dense layer or linear layer) is a layer in an artificial neural network in which every input value connects to every output value through a learned weight

Deep LearningNeural Networks

GEM (Meta)

GEM (Generative Ads Recommendation Model) is a proprietary foundation model for advertising recommendation developed by Meta Platforms.

AI InfrastructureAI Models

GGML

GGML is an open-source tensor library written in pure C that runs machine learning inference efficiently on consumer hardware

Developer ToolsOpen Source AI

GGUF

GGUF (GPT-Generated Unified Format) is the standard binary file format for storing large language models for local inference, bundling a model's weights, tokenizer, and metadata into a single self-contained…

Developer ToolsLarge Language Models

GLUE benchmark

The General Language Understanding Evaluation (GLUE) benchmark is a collection of nine natural language understanding (NLU) tasks designed to evaluate and compare the performance of language models across a…

AI BenchmarksNatural Language Processing

GPU computing

GPU computing is the use of a graphics processing unit (GPU) to perform general-purpose computation that was traditionally handled by the central processing unit (CPU).

AI HardwareAI Infrastructure

GSM8K

GSM8K (Grade School Math 8K) is an English-language benchmark of grade-school arithmetic word problems released by OpenAI researchers in 2021.

AI BenchmarksLarge Language Models

GaLore (Gradient Low-Rank Projection)

GaLore (Gradient Low-Rank Projection) is a memory-efficient training strategy for large neural networks that projects each weight matrix's gradient into a low-rank subspace, computes the Adam-style optimizer…

Training & Optimization

Gated SAE

A Gated sparse autoencoder (Gated SAE) is a sparse-autoencoder architecture for mechanistic interpretability that splits the encoder into a gating path, which decides which features are active, and a magnitude…

AI Safety

Gaussian Mixture Model

A Gaussian Mixture Model (GMM) is a probabilistic model that represents a dataset as a weighted mixture of a finite number of Gaussian distributions with unknown parameters

Gaussian Process

A Gaussian process (GP) is a probabilistic machine learning model defined as a collection of random variables, any finite number of which have a joint Gaussian distribution.

Statistics

Gemma Scope

Gemma Scope is an open, comprehensive suite of sparse autoencoders (SAEs) released by Google DeepMind in 2024 to support mechanistic interpretability research on its open-weight Gemma 2 language models.

AI Safety

Generalization

Generalization in machine learning is the ability of a trained model to perform accurately on new, unseen data drawn from the same distribution as its training set

Deep LearningModel Evaluation

Generalization Curve

A generalization curve (also called a learning curve) is a plot that visualizes how a machine learning model's performance on training data and unseen data changes as a function of some varying quantity, such…

Model Evaluation

Generalized Linear Model

A generalized linear model (GLM) is a flexible extension of ordinary linear regression that allows the response variable to follow any distribution from the exponential family, not just the normal distribution

Statistics

Generative AI

Generative AI is a class of artificial intelligence systems that produces new data instances, such as text, software code, images, audio, video, molecular structures, or other representations, by learning…

Artificial IntelligenceGenerative AI

Generative Model

A generative model is a class of statistical and machine learning model that learns the joint probability distribution P(X) of the observed data, or the joint distribution P(X, Y) of inputs and labels

Deep LearningGenerative AI

Generative adversarial network

Generative adversarial networks (GANs) are a family of generative models trained through competition between two learned functions.

Deep LearningGenerative AI

Generator

A generator is a neural network within a generative adversarial network (GAN) that learns to produce synthetic data samples from random noise.

Generative AINeural Networks