U-matrix - A U-matrix, or unified distance matrix, is a visualization of distances between neighboring prototype vectors in a trained self-organizing map.
U-Net - U-Net is a convolutional neural-network architecture that combines an image encoder, an image decoder, and connections between corresponding resolution levels.
UCB1 - UCB1 is a multi-armed bandit algorithm that selects an action using its average observed reward plus an exploration bonus.
UCT - UCT is a method for guiding Monte Carlo tree search by applying upper-confidence-bound ideas at decision nodes.
Ugly duckling theorem - The ugly duckling theorem is a result associated with Satosi Watanabe showing that, if all possible predicates are treated equally in a particular logical...
Łukasiewicz logic - Łukasiewicz logic is a family of many-valued logics associated with Jan Łukasiewicz.
Ultimate sampling unit - An ultimate sampling unit is a unit selected at the final stage of a sampling design.
Unary code - Unary code represents an integer using a repeated bit followed by a terminating bit.
Unary coding - Unary coding represents a nonnegative integer by repeating one bit a number of times equal to the integer and ending with the opposite bit.
Unary constraint - A unary constraint is a rule that restricts the allowed values of one variable in a constraint satisfaction problem.
Unavoidable Redundancy - Unavoidable redundancy is a descriptive term for repeated information that cannot simply be removed by a proposed normalization decomposition without losing...
Unbiased estimator - An unbiased estimator is a rule for estimating an unknown quantity whose expected value equals that quantity under the assumed sampling model.
Unbounded cost search - Unbounded-cost search seeks a valid solution without requiring its cost to fall below a specified threshold or within a specified factor of the best...
UNCANNY VALLEY - The uncanny valley is a proposed pattern in people's responses to humanlike artificial characters or robots: increasing human resemblance may initially...
Uncertain data - Uncertain data are data whose values, identities, relationships or existence are not known with complete confidence.
Uncertain database - An uncertain database represents information whose value, existence or interpretation is not fully settled.
Uncertain inference - Uncertain inference is reasoning in which the support for a conclusion is not treated as simply certain or absent.
Uncertainty - Uncertainty is the presence of unresolved possibilities about an outcome, quantity, explanation, or state of the world given the available information.
Uncertainty Bias - Uncertainty bias, in the supplied Artificial Intelligence Ontology sense, occurs when a predictive system favors groups represented more strongly in its...
Uncomfortable science - Uncomfortable science is an informal methodological expression for research situations where limited available evidence is used both to develop explanations...
Uncompressed video - Uncompressed video represents frames directly through their specified image samples rather than a video compression scheme that encodes spatial or temporal...
Unconditional probability - Unconditional probability is the probability of an event without restricting the calculation to a specified conditioning event.
Unconstrained minimization - Unconstrained minimization is the task of finding input values that make an objective function as small as possible without imposing separate equality...
Undercoverage Bias - Undercoverage bias is systematic distortion in an estimate caused by failing to cover part of the intended population, when the omitted part differs in ways...
Underdamped Langevin dynamics - Underdamped Langevin dynamics is a stochastic process that evolves both position and velocity under a potential force, friction and random noise.
Underfitting - Underfitting occurs when a model fails to capture useful patterns in its training data and consequently performs poorly.
Undersampling - Undersampling reduces the number of training examples from selected groups, commonly an overrepresented class, to change the balance of a dataset.
Undirected graph - An undirected graph is a collection of nodes joined by edges that have no orientation.
Unembedding - Unembedding is the mapping from a language model's hidden representation to scores for tokens in its output vocabulary.
Unevenly spaced time series - An unevenly spaced time series is a sequence of observations recorded at times whose successive gaps are not all equal.
Unicity (data analysis) - Unicity measures how often a limited set of observations singles out one individual's record or trace within a dataset.
Unicode - Unicode is a standard for representing and processing text across writing systems.
Unidirectional language model - A unidirectional language model predicts tokens using context from one direction in a sequence.
Unification - Unification is the process of finding substitutions for variables that make symbolic expressions identical.
Unifier - A unifier is a substitution that makes two symbolic expressions identical when applied consistently to both. It specifies replacements for variables.
Uniform binary search - Uniform binary search is a variant of binary search that uses a predetermined pattern of shrinking search steps.
Uniform convergence in probability - Uniform convergence in probability means that the largest error across an entire indexed collection of random quantities becomes small with high probability...
Uniform convergence theory - Uniform convergence theory studies when quantities estimated from a sample approach their population counterparts simultaneously across a class of functions.
Uniform-cost search - Uniform-cost search explores paths in order of their accumulated cost from the starting point.
Uniform distribution - A uniform distribution assigns equal probability to outcomes of equal size within its support.
Uniform memory access - Uniform memory access, or UMA, is a shared-memory architecture in which processors have broadly uniform access characteristics to main memory, rather than...
Uniform sampling fraction - A uniform sampling fraction means that the same proportion of units is selected from each stratum of a stratified population.
Uniformly most powerful test - A uniformly most powerful test is a hypothesis test whose power is at least as high as that of every competing test in a specified class, at every parameter...
Unimodal - Unimodal describes a distribution or data pattern with one mode, commonly understood as one principal peak.
Uninformative prior - An uninformative prior is a prior distribution intended to contribute little specific prior information to a Bayesian analysis, under a chosen definition of...
Uninformed search - Uninformed search explores a problem using its defined states, actions, goal test and, when relevant, action costs, without an additional heuristic...
Unintended side-effects - Unintended side-effects are consequences of an AI system's actions that fall outside the outcome people meant it to achieve.