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 wavelet transform - A discrete wavelet transform, or DWT, represents sampled data through coefficients associated with localized patterns at different scales.
Dispersive flies optimization - Dispersive flies optimization is a population-based stochastic search algorithm inspired by the gathering and dispersal of flies.
Distance - Distance is a numerical measure of separation between two objects.
Distributed algorithm - A distributed algorithm is a procedure carried out by multiple computing participants that perform local work and coordinate through communication.
Distributed constraint optimization - Distributed constraint optimization coordinates decisions controlled by different agents so that their combined assignment optimizes a shared objective...
Distributed source coding - Distributed source coding compresses statistically related sources using separate encoders and reconstructs them at a decoder that can use their relationship.
Divide-and-conquer algorithm - A divide-and-conquer algorithm solves a problem by splitting it into smaller instances, solving those instances, and combining their answers.
Dormand - Prince method - The Dormand - Prince method is an explicit Runge - Kutta method for numerically solving ordinary differential equations with initial values.
Dual norm - The dual norm associated with a norm measures the largest inner product a vector can achieve against any vector in that norm's unit ball.
Dual problem - A dual problem is an optimization problem constructed from another problem, called the primal, to obtain bounds on its best objective value.
Dual total correlation - Dual total correlation (DTC) is an information-theoretic measure of dependence among several random variables.
Duality gap - The duality gap is the difference between the optimal values of a primal optimization problem and its associated dual.
Dykstra's projection algorithm - Dykstra's projection algorithm finds the point nearest to a given starting point within an intersection of closed convex sets.
Dynamical system - A dynamical system describes how a state changes over time according to a rule.
Early exit - Early exit is a deep-learning inference strategy that produces a prediction before an input has passed through every layer of a network.
Earth mover's distance - Earth mover's distance, or EMD, measures how much work is needed to transform one distribution of mass into another when moving mass has a specified cost.
Edge device - An edge device is a computing device operating at or near the part of a network where data is produced or first processed.
Edge weight - An edge weight is a numerical value associated with a connection between two nodes in a graph.
Edit distance - Edit distance measures the minimum cost of changing one sequence into another using a specified set of edit operations.
Effective dimension - Effective dimension is a measure of how many independent directions or degrees of freedom substantially contribute to a model or learning problem.
Eigenvalue - An eigenvalue is a number that describes how a square matrix scales a corresponding nonzero eigenvector.
Eigenvector - An eigenvector is a nonzero vector that a square matrix transforms into a scalar multiple of itself.
Elementary matrix - An elementary matrix is a square matrix obtained by applying one elementary row operation to an identity matrix.
Empirical gradient - In the local-search terminology used by Artificial Intelligence: A Modern Approach, an empirical gradient is an estimate of how an objective changes...
Energy distance - Energy distance is a measure of difference between probability distributions built from expected distances between independent observations.
Entropic vector - An entropic vector records the joint entropies of all nonempty subsets of a collection of discrete random variables with finite entropies.
Entropy estimation - Entropy estimation is the statistical task of estimating a probability distribution's entropy from observed data.
Entropy power inequality - The entropy power inequality is an information-theoretic result bounding the entropy power of a sum of independent continuous random variables or vectors.
Entropy rate - Entropy rate is the limiting average uncertainty per observation in a stochastic process.
Euclidean distance - Euclidean distance is the straight-line distance between two points in a Euclidean space.
Euclidean norm - The Euclidean norm is the usual length of a real vector, calculated as the square root of the sum of its squared coordinates.
Euclidean space - A Euclidean space is a space of points or vectors equipped with the familiar geometry of lengths, angles and perpendicularity.
Event - In probability, an event is a collection of possible outcomes to which the probability model assigns a probability.
Event calculus - The event calculus is a family of logic-based formalisms for representing events, their effects and what holds at different times.
Exact algorithm - An exact algorithm is an algorithm that solves the specified problem correctly rather than returning an approximation.
Excursion probability - An excursion probability is the probability that a random process exceeds a specified level somewhere within a defined observation domain.
Exploding gradient problem - The exploding gradient problem occurs when gradients become excessively large during model training, making parameter updates unstable or numerically...
Explore-then-commit algorithm - The explore-then-commit algorithm is a strategy for a stochastic multi-armed bandit problem that separates learning from exploitation.
Exponential family - An exponential family is a class of probability distributions whose probability mass or density can be written in a shared mathematical form: p(x; η) = h(x)...
FAIR principles - FAIR principles are guidelines for making digital resources Findable, Accessible, Interoperable and Reusable.
False precision - False precision occurs when a numerical statement appears more finely determined than the supporting evidence justifies.
Fast multipole method - The fast multipole method, or FMM, is a family of algorithms for rapidly evaluating large sums of interactions between sources and targets.
Federated learning network - A federated learning network is a representation of the participants and collaboration relationships in a federated learning application.
Federated learning system - A federated learning system is the complete arrangement of participants, local data, computing resources, communication and software used to train models...