Direct utility estimation - Direct utility estimation is a reinforcement-learning approach that estimates a state's value by averaging the observed returns following visits to that state.
Direct voice input - Definition: Direct voice input, or DVI, is a human - machine interaction method in which spoken commands provide input to a computer or control interface...
Directed acyclic graph - A directed acyclic graph, or DAG, is a graph whose edges have directions and which contains no directed cycle.
Directed cycle - A directed cycle is a sequence of directed edges that follows their arrow directions and returns to its starting vertex.
Directed graph - A directed graph, also called a digraph, represents objects as nodes and relationships as arrows from one node to another.
Directional arc consistency - Directional arc consistency, or DAC, is a constraint-satisfaction property defined relative to a fixed ordering of variables.
Directional-change intrinsic time - Directional-change intrinsic time is an event-based way to represent a time series in which the clock advances when an observed value reverses from a...
Directional component analysis - Directional component analysis, or DCA, is a statistical method for deriving patterns of variability that reflect a chosen linear impact measure as well as...
Directional derivative - A directional derivative measures the instantaneous rate at which a function changes at a point when its input moves in a specified direction.
Directional test - A directional test is a statistical hypothesis test whose rejection region lies in one specified direction, commonly called a one-sided or one-tailed test.
Directive speech act - A directive speech act is an utterance intended to get another person or system to do something.
Dirichlet boundary condition - A Dirichlet boundary condition specifies the value of an unknown function on a selected boundary of a mathematical domain.
Dirichlet distribution - The Dirichlet distribution is a probability distribution over vectors of proportions that sum to one.
Dirichlet-multinomial model - A Dirichlet-multinomial model combines a Dirichlet distribution over category probabilities with a multinomial distribution over counts.
Dirichlet process - A Dirichlet process is a probability distribution over probability distributions.
Dirty data - Dirty data is an informal name for data with quality problems that make it unreliable or unsuitable for an intended use.
Disambiguation - Disambiguation is the process of determining which interpretation of an expression is intended when more than one is possible.
Discordant pairs - Discordant pairs are pairs of observations whose order is reversed on two variables: the observation with the higher value on one variable has the lower...
Discount - In count-based language modeling, a discount reduces the probability mass assigned to observed events so that some mass can be allocated elsewhere...
Discount factor - A discount factor is a number used to reduce the weight of later rewards relative to earlier rewards in a sequential decision problem.
Discounted state-action occupancy measure - A discounted state-action occupancy measure describes how much a policy visits each state-action pair over time, with later visits receiving less weight.
Discourse - Discourse is connected language interpreted as a structured whole, such as a conversation, report, story, or article.
Discourse connectives - Discourse connectives are words or phrases that signal relationships between parts of a text or conversation.
Discourse deixis - Discourse deixis is reference to some aspect of a stretch of discourse, often using expressions such as “this” or “that.
Discourse model - A discourse model is a representation of the entities and relevant relationships established during an unfolding conversation or text.
Discourse-new - Discourse-new describes a referent that is being introduced into the current discourse rather than already being established in it.
Discourse-old - Discourse-old describes a referent that has already been established in the current discourse and is accessed again by a later expression.
Discourse parsing - Discourse parsing is the computational analysis of relationships and structure across parts of a text.
Discourse relation - Definition: A discourse relation is a meaning-based connection between stretches of text, such as explanation, contrast, elaboration or temporal sequence.
Discovery procedure - In the linguistic context of this glossary, a discovery procedure is a systematic method intended to derive a description of a language's structure from...
Discovery system (artificial intelligence) - A discovery system in AI is a system designed to generate or identify candidate scientific concepts, relationships or laws.
Discrete cosine transform - The discrete cosine transform, or DCT, represents a finite sequence of real numbers as weights of cosine patterns.
Discrete denoising diffusion probabilistic model - A discrete denoising diffusion probabilistic model, often abbreviated D3PM, generates discrete data by learning to reverse a gradual categorical corruption...
Discrete distribution - A discrete distribution assigns probabilities to a finite or countably infinite set of possible outcomes.
Discrete events - In knowledge representation, discrete events are occurrences with a definite structure and identifiable boundaries.
Discrete feature - A discrete feature is an input that takes one of a limited set of separate values, such as red, amber or green, rather than any value along a continuous scale.
Discrete Fourier transform - The discrete Fourier transform, or DFT, converts a finite sequence of samples into coefficients describing discrete frequency components.
Discrete optimization - Discrete optimization chooses the best feasible solution when some or all decisions must come from discrete sets, such as whole numbers, yes/no selections...
Discrete phase-type distribution - A discrete phase-type distribution describes the number of steps until a finite-state, discrete-time Markov chain reaches an absorbing state.
Discrete random variable - A discrete random variable is a numerical function of a random outcome that takes values in a finite or countably infinite set.
Discrete-time proportional hazards - Discrete-time proportional hazards models describe event occurrence when follow-up is divided into intervals and each interval's event probability is...
Discrete Uniform Distribution - A discrete uniform distribution assigns equal probability to each value in a specified finite set of possible outcomes.
Discrete variable - A discrete variable takes values from a finite or countably infinite set of distinct possibilities.
Discrete variational autoencoder - A discrete variational autoencoder is a variational generative model that uses discrete latent variables, such as categorical choices or binary states, to...
Discrete wavelet transform - A discrete wavelet transform, or DWT, represents sampled data through coefficients associated with localized patterns at different scales.
Discrete Weibull distribution - The discrete Weibull distribution is a family of distributions for nonnegative integer outcomes, often used for discrete lifetimes or count data.
Discretionary access control - Discretionary access control, or DAC, is an approach in which an object's owner or another authorized controller has some discretion to decide who can...