Graphical data editing - Graphical data editing is the use of graphs to identify potentially erroneous, inconsistent, or otherwise unusual data for investigation and possible...
Graphical degree sequence - A graphical degree sequence is a list of nonnegative integers that can be realized as the node degrees of a graph of the specified kind.
Graphical lasso - Graphical lasso is a statistical method for estimating a sparse inverse covariance matrix using an L1 penalty.
Graphical time warping - Graphical time warping is a framework for jointly aligning multiple pairs of time series while modeling relationships among their alignment paths.
Graphite graph generative model - Graphite is a graph generative modeling framework that combines latent node representations with an iterative graph-neural-network decoder.
Graphplan - Graphplan is an automated planning algorithm developed by Avrim Blum and Merrick Furst.
Grasping - Grasping is the process of establishing and maintaining physical contact that lets a robot hold or control an object.
Gray scale - Gray scale, commonly written grayscale, represents an image using a single intensity-related value at each pixel rather than separate color components.
Grey Wolf Optimization - Grey Wolf Optimization is a population-based numerical search method inspired by an abstract model of gray-wolf social roles and hunting.
Gray-world assumption - The gray-world assumption is the idea that the average surface color across a sufficiently varied scene is approximately neutral.
Great deluge algorithm - The Great deluge algorithm is a local-search optimization heuristic that accepts candidate solutions according to a changing quality threshold.
Greedy agent - A greedy agent is an agent that, at each decision, picks the action that looks best right now according to its immediate measure, without searching ahead...
Greedy algorithms - Greedy algorithms build a solution by repeatedly choosing the option that looks best according to a specified local rule.
Greedy best-first search - Greedy best-first search is a search strategy that expands the frontier node with the lowest estimated remaining cost to a goal.
Greedy decoding - Greedy decoding is a method for generating a sequence by choosing the highest-scoring available next token at each step.
Greedy embedding - A greedy embedding assigns graph vertices positions in a metric space so that a message can always move to a neighboring vertex that is strictly closer to...
Greedy policy - A greedy policy chooses an action with the highest current estimated value at each decision point.
Greedy search - Greedy search is an approach that repeatedly chooses the option that appears best according to a local rule.
Green-based demosaicking - Green-based demosaicking reconstructs a full-color image from a color-filter mosaic by using the green channel as a structural reference for estimating...
Gricean maxims - Gricean maxims are conversational expectations proposed by philosopher H. Paul Grice to help explain cooperative communication.
Grid sampling - Grid sampling, in the OECD glossary sense used here, is a form of cluster sampling whose clusters are grid areas composed of basic cells arranged in a...
Grid search - Grid search is a systematic way to evaluate every combination in a predefined set of candidate parameter values.
GRIM test - The GRIM test, short for granularity-related inconsistency of means, checks whether a reported mean is mathematically compatible with its stated sample...
Grokking - Grokking is a machine-learning phenomenon in which a model achieves strong performance on its training examples, remains poor on unseen examples for an...
Grossberg network - Grossberg network is a broad label associated with neural models developed by Stephen Grossberg, rather than one uniquely specified modern architecture.
Ground resolution theorem - The ground resolution theorem states that an unsatisfiable set of ground clauses has a resolution derivation of the empty clause.
Ground term - A ground term is a term in formal logic that contains no variables.
Ground truth - Ground truth is the verified, real-world answer for a case, used as the standard against which a model's predictions are trained, tested and judged.
Groundedness - Groundedness is the degree to which an AI system's output is anchored in checkable sources or real evidence, rather than generated freely from patterns the...
Grounding - Grounding is the practice of connecting a model's output to specific sources or real-world referents: the work done, in architecture and in process, so that...
Group - In mathematics, a group is a set together with a binary operation that is closed and associative, has an identity element, and gives every element an inverse.
Group attribution bias - Group attribution bias is the tendency, in this glossary's machine-learning sense, to assume that a characteristic observed in one individual also applies...
Group concept mapping - Group concept mapping is a structured participatory method for collecting people's ideas, organizing them through sorting and rating, and producing maps...
Group fairness - Group fairness assesses how an AI system's decisions, errors, or benefits compare across defined groups of people.
Group method of data handling - The group method of data handling, or GMDH, is a family of inductive modeling methods that generate candidate models, estimate their parameters from data...
Group testing - Group testing is a method for identifying items with a particular property by testing collections of items together.
Grouped Dirichlet distribution - The grouped Dirichlet distribution is an extension of the Dirichlet family used to represent probabilities for categories when some observations identify...
Grouped Query Attention - Grouped Query Attention, usually written grouped-query attention or GQA, is an attention design in which several query heads share a smaller set of key and...
Groupthink Bias - Groupthink Bias is a pattern in which pressure to agree with a group discourages independent criticism and contributes to poor decisions.
Grover's algorithm - Grover's algorithm is a quantum algorithm for finding a marked item in an unstructured search space.
Growing self-organizing map - A growing self-organizing map is an unsupervised neural-network method that expands its map of representative units as it learns the structure of data.
Growth curve (statistics) - A growth curve in statistics describes how an outcome changes over time, often using repeated measurements from the same individuals or other units.
Growth function - The growth function of a binary hypothesis class gives the largest number of distinct label patterns that its classifiers can produce on a set of a given size.
Grubbs's test - Grubbs's test is a statistical test for a single unusually extreme observation in a univariate sample whose ordinary observations are assumed to come from...
GTD2 - GTD2 is a gradient temporal-difference algorithm for learning a linear value-function approximation using a primary parameter vector and an auxiliary vector.
Guard (information security) - In information security, a guard is a trusted system or mechanism that mediates information transfer between systems operating under different security...
Guardrails - Guardrails are the constraints, checks and boundaries placed around an AI system to keep its behavior within acceptable limits: what it may say, do, spend...
Guidance field - A guidance field, in gradient-domain image editing, is a set of desired local intensity changes that guides reconstruction of an output image.