Artificial intelligence and data

GPipe

GPipe is a pipeline parallelism library introduced by Google researchers in 2018 for training deep neural networks too large to fit on a single accelerator.

GeneralOct 26, 2026

GQL (Graph Query Language) is the ISO/IEC 39075:2024 standard declarative language for property graph databases, descended from Cypher and sharing its GPML pattern matching with SQL/PGQ; the first new ISO database language since SQL.

GrabCut

GrabCut is an interactive image segmentation algorithm designed at Microsoft Research Cambridge and published in 2004, which extracts a foreground object given minimal user input such as a rectangle.

Gracenote

Gracenote is an American entertainment metadata and content identification company owned by Nielsen, which acquired it in 2017; it began in the 1990s as CDDB.

Grad-CAM

Grad-CAM (Gradient-weighted Class Activation Mapping) is a visualization technique producing heatmaps of the image regions a convolutional neural network relied on for a prediction, introduced in 2016.

Gradient boosting

Gradient boosting is a machine learning method that builds predictive models by fitting simple learners to the gradient of a loss, formalized by Jerome Friedman in 2001.

Gradient clipping

Gradient clipping is a modification to gradient descent that caps the gradient's norm at a chosen threshold each iteration, used to stabilize training and enforce differential privacy.

Gradient compression

Gradient compression is a set of techniques that reduces the volume of data exchanged between workers in distributed machine learning training, chiefly by sparsification or quantization to relieve the communication bottleneck.

Gradient descent

Gradient descent, also called steepest descent, is an iterative optimization method that minimizes a differentiable function by repeatedly stepping in the direction of the negative gradient.

Gradient Episodic Memory (GEM)

Gradient Episodic Memory (GEM) is a continual learning algorithm that stores examples from past tasks and projects gradients to prevent catastrophic forgetting, introduced in 2017.

Gradient projection method

The gradient projection method is a first-order constrained optimization algorithm that minimizes a differentiable objective over a convex set by projecting each gradient step back onto it.

Gradient-boosted decision tree

A gradient-boosted decision tree (GBDT) is an ensemble machine learning method for tabular data that fits a sequence of small regression trees, each correcting the previous trees' errors.

Gradio

Gradio is an open-source Python library for building and sharing web demos of machine learning models, created in 2019 by Abubakar Abid and acquired by Hugging Face in December 2021.

Gram–Schmidt process

The Gram–Schmidt process, also called Gram–Schmidt orthogonalization, is an algorithm that turns a linearly independent set of vectors into an orthonormal one spanning the same subspace.

Grammar checker

A grammar checker is a program that detects and suggests corrections for grammatical, spelling, and word choice errors, embedded in word processors and used widely in education.

Grammar induction

Grammar induction, also called grammatical inference or grammar inference, is the process of learning a formal grammar from example data such as sentences instead of hand-written rules.

Grammatical error correction

Grammatical error correction (GEC) is the task of automatically detecting and correcting grammatical, orthographic, and semantic errors in text, progressing from rule-based methods to neural machine translation.

Grammatical evolution

Grammatical evolution is an evolutionary algorithm introduced in 1998 by Ryan, Collins, and O'Neill at the University of Limerick, which evolves programs in arbitrary languages using BNF grammars.

Granular computing

Granular computing is an umbrella term for theories and techniques that solve complex problems using information granules, collections of similar objects, an approach introduced by Lotfi Zadeh in 1979.

Graph (abstract data type)

A graph, also known as a graph data structure, is an abstract data type that stores vertices and edges, supporting traversal algorithms like breadth-first and depth-first search.

Graph attention network

A graph attention network (GAT) is a neural network architecture for machine learning on graphs that weights neighbor features with learned attention, introduced at ICLR 2018.

Graph autoencoder

A graph autoencoder (GAE) is a neural network that encodes graphs into node embeddings and reconstructs the adjacency matrix, supporting unsupervised tasks like link prediction and node clustering.

Graph coloring

Graph coloring assigns colors to a graph's vertices so adjacent vertices get different colors, a central problem from map coloring; the four color theorem and scheduling are key examples.

Graph contrastive learning

Graph contrastive learning is a self-supervised method that learns node and graph representations without labels by contrasting augmented views, feeding tasks like node classification, graph classification, and drug discovery.

Graph convolutional network

A graph convolutional network (GCN) is a neural network architecture that applies convolution over graph-structured data, introduced by Kipf and Welling in 2016 and used chiefly for node classification and recommendation.

Graph database

A graph database is a database management system that stores data as nodes connected by edges and queries it by traversing connections rather than joining tables.

Graph filter

A graph filter is a linear operator that processes signals on graph vertices, typically a polynomial of the graph shift operator, and is the basic building block of graph signal processing.

Graph isomorphism network

A graph isomorphism network (GIN) is a graph neural network architecture that updates each node by summing neighbor features through an MLP, matching the 1-WL isomorphism test's power.

Graph kernel

A graph kernel is a positive semidefinite similarity function between graphs, letting kernel methods such as support vector machines classify graph-structured data like molecules and proteins.