Adjective - An adjective is a word class whose members typically express properties of nouns or the things those nouns refer to. In “a quiet room,” quiet modifies room.
Adjoint state method - The adjoint state method computes how a chosen objective changes when the parameters of a mathematical model change.
Adjusted correlation ( r adj ) - Adjusted correlation, in the source glossary's regression sense, is a correlation measure corrected for the number of predictors relative to the sample size.
Adjusted means - Adjusted means are model-based group averages calculated after accounting for specified covariates or other predictors.
Adjusting or controlling for a variable - Adjusting or controlling for a variable means accounting for that variable when assessing the relationship between other variables.
Administrative data - Administrative data are records created as organizations carry out routine operations, deliver services or administer programs.
Administrative data collection - Administrative data collection is the organized acquisition and processing of data from administrative sources for statistical purposes.
Admissible decision rule - An admissible decision rule is a statistical rule that is not dominated by another allowed rule under a specified model and loss function.
Admissible heuristic - An admissible heuristic is a search estimate that never overestimates the true minimum remaining cost of reaching a goal.
Advantage actor-critic - Advantage actor-critic is a reinforcement-learning approach in which an actor learns a policy and a critic helps estimate whether an action performed better...
Advantage function - The advantage function measures how much better or worse an action's expected return is than the expected return from following a particular policy at the...
Adverb - An adverb is a word class whose members commonly modify verbs, adjectives, other adverbs, or a wider proposition.
Adversarial Autoencoders - Adversarial autoencoders are autoencoders trained both to reconstruct their inputs and to make their collective latent codes resemble a chosen probability...
Adversarial Domain Adaptation - Adversarial domain adaptation is a family of methods that trains a useful predictive representation while making it harder to identify which domain supplied...
Adversarial example - An adversarial example is an input deliberately modified to cause a machine-learning model to produce an incorrect prediction or other unintended behavior.
Adversarial inverse reinforcement learning - Adversarial inverse reinforcement learning, commonly abbreviated AIRL, is a method for learning a reward function from expert demonstrations using an...
Adversarial loss - Adversarial loss is a training objective derived from a competition between models or model components.
Adversarial machine learning - Adversarial machine learning studies deliberate attempts to manipulate machine-learning systems and methods for evaluating or reducing those risks.
Adversarial search - Adversarial search is decision-making by exploring possible actions and the responses of other agents whose interests conflict with yours.
Adversarial stylometry - Definition: Adversarial stylometry studies deliberate changes to writing intended to disrupt automated inferences about its author.
Adversarial Training - Adversarial training is a model-training approach that uses deliberately challenging, permitted modifications of training inputs to improve resistance to...
Adversary argument - An adversary argument is a proof technique that demonstrates a limitation of an algorithm or class of algorithms by constructing difficult inputs or responses.
Adverse impact ratio - An adverse impact ratio compares the selection rate for one group with the selection rate for a reference group.
AED - AED stands for attention-based encoder-decoder in the speech-recognition context of this glossary.
Affine bilateral grid (HDRnet) - An affine bilateral grid in HDRnet stores local color-transformation coefficients in a compact grid indexed by image position and a guidance value.
Affine calibration - Affine calibration, in the source glossary's computer-experiment sense, improves agreement between simulated and observed responses by applying an affine...
Affine transformation - An affine transformation maps coordinates using a linear transformation followed by a translation.
Affinity - In image processing, affinity is a numerical weight describing how strongly two pixels or image elements should influence one another.
Affinity analysis - Affinity analysis examines which items, actions or attributes tend to occur together in a dataset.
Affix - An affix is a bound word-forming element attached to a base to contribute grammatical information or help create a new word.
Affix grammar over a finite lattice - Definition: An affix grammar over a finite lattice, usually abbreviated AGFL, is a grammar formalism that enriches context-free rules with features whose...
Afterstate - An afterstate is the situation immediately after the known effects of an agent's action have occurred, before the remaining environment response is resolved.
Age adjustment - Age adjustment is a statistical method for comparing populations while accounting for differences in their age distributions.
Age progression - Age progression is the creation of an image showing how a person's appearance might change as they become older.
Agent - In AI, an agent is anything that perceives its environment and takes actions in it to achieve a goal.
Agent experience - Agent experience, often shortened to AX, concerns how effectively AI agents discover, understand and use a product or service on a user's behalf.
Agent function - An agent function is the mathematical description of an agent's behavior: the complete mapping from everything the agent has perceived so far to the action...
Agent harness - An agent harness is the software surrounding an AI model that enables it to work through tasks.
Agent mining - Agent mining is a research area that combines autonomous agents and multi-agent systems with data mining.
Agent orchestration - Agent orchestration is the coordination of multiple AI agents or tool-using steps so they work together on a larger task: deciding which agent does what, in...
Agent program - An agent program is the actual running software that implements an agent: the code that takes the current percepts and produces the next action.
Agent verification - Agent verification is the examination of whether an autonomous software agent satisfies specified requirements.
Agentic loop - An agentic loop is the repeating cycle at the heart of an AI agent: observe the current state, decide the next step, act, read the result, and repeat until...
Agentic workflow - An agentic workflow is a business process in which an AI system moves through several steps toward a goal, choosing some of the steps itself, rather than...
Agentive logic - Agentive logic is a family of formal approaches for reasoning about what agents do, can bring about or are responsible for bringing about.
Agglomerative clustering - Agglomerative clustering is a method that groups data by merging: it starts with every item as its own tiny cluster, then repeatedly joins the two closest...
Aggregate (data warehouse) - An aggregate in a data warehouse is a summary of more detailed records, usually stored to answer common analytical queries efficiently.