Computer vision dazzle - Computer vision dazzle is a visual camouflage approach that explores whether changes in appearance can disrupt particular computer vision systems while...
Computerized adaptive testing - Computerized adaptive testing (CAT) is assessment in which a computer selects later questions using information from a person's earlier responses.
Concentration inequality - A concentration inequality bounds the probability that a random quantity differs substantially from a reference value, commonly its expectation.
Concept activation vector - A concept activation vector, or CAV, is a direction in a neural network's internal activation space associated with a concept defined through example inputs.
Concept drift - Concept drift is the gradual or sudden change in the relationship between a model's inputs and its target, so that patterns the model learned stop matching...
Concept map - A concept map is a diagram that represents concepts and the meaningful relationships between them.
Concept mining - Definition: Concept mining is the computational identification of meaningful concepts in material such as documents, queries or other data.
Conceptual clustering - Conceptual clustering groups examples while also developing descriptions of the resulting groups.
Conceptual data model - A conceptual data model is a high-level description of the important kinds of information in a business domain and the relationships between them.
Conceptual dependency - Conceptual dependency is a historical approach to representing the meaning of language through networks of concepts, primitive acts and their participants.
Conceptual graph - A conceptual graph is a graph-based form of knowledge representation with defined logical meaning. In the tradition developed by John F.
Conceptualization (information science) - In information science, a conceptualization is an abstract view of a domain: the kinds of things considered relevant and the relationships understood to...
Concordant pairs - Concordant pairs are pairs of observations whose ordering agrees on two variables.
Concrete word - A concrete word is a word whose meaning is closely connected to something perceptible through the senses or to a directly experienced action.
Concurrency control - Concurrency control is the set of techniques used to coordinate operations that overlap in time so they do not violate the required rules for shared data.
Concurrent action list - A concurrent action list specifies actions that must or must not occur alongside a particular action for its modeled effects to apply.
Concurrent logic programming - Concurrent logic programming is a family of programming approaches that express interacting computations using logic-programming constructs.
Condensation algorithm - The Condensation algorithm is a probabilistic visual-tracking method that represents uncertainty with a collection of weighted samples.
Condition-action rule - A condition-action rule connects a recognized situation to an action: if a specified condition holds, select or perform the associated response.
Condition number - A condition number measures how sensitive a mathematical problem's solution can be to changes in its input.
Conditional average treatment effect - The conditional average treatment effect, or CATE, is the average causal effect of a treatment among units with specified characteristics.
Conditional diffusion model - A conditional diffusion model is a generative model that uses a diffusion-style noise-removal process to produce outputs in response to supplied information.
Conditional distribution - A conditional distribution describes how a variable is distributed when specified information about another variable or event is given.
Conditional effect - A conditional effect is an outcome of an action that occurs only when an additional condition holds.
Conditional entropy - Conditional entropy measures the average uncertainty remaining about one random variable after another is known.
Conditional expectation - Conditional expectation is the average value of a random quantity given specified information.
Conditional Gaussian - A conditional Gaussian model describes continuous variables with a Gaussian distribution once specified conditioning information is fixed.
Conditional generation - Conditional generation is the production of an output using specified input or context as a condition.
Conditional means - Conditional means are the expected values of a variable for specified values or conditions of another variable or set of variables.
Conditional odds - Conditional odds express the probability of an event relative to the probability of its complement, given specified information.
Conditional plan - A conditional plan specifies an action and alternative continuations chosen according to information obtained during execution.
Conditional probability - Conditional probability is the probability of an event or statement given specified information.
Conditional probability distribution - A conditional probability distribution specifies the probabilities of possible outcomes after particular information is given.
Conditional probability table - A conditional probability table, or CPT, is a tabular representation of a discrete variable's probability distribution for each specified combination of...
Conditional random field - A conditional random field, or CRF, is a probabilistic model for predicting related output variables given observed inputs.
Conditioning - Conditioning is the operation of evaluating a probability distribution given specified information.
Conditioning case - A conditioning case is one combination of values assigned to a Bayesian-network node's parents.
Confabulation (neural networks) - Confabulation in neural-network discussions can refer to generated patterns that resemble learned material but are not faithful reconstructions of a...
Confidence interval - A confidence interval is a range calculated from data by a procedure designed to cover an unknown population quantity at a stated rate over repeated...
Confidence values - Confidence values are scores that an AI or statistical system attaches to predictions, extracted information, or other outputs to express estimated...
Configuration - Configuration is the set of choices and settings that control how an AI system runs, from model options and thresholds to file paths, limits and...
Configuration space - Configuration space is the set of possible configurations of a robot or mechanical system.
Confirmation bias - Confirmation bias is a tendency to seek, interpret, favor or remember information in ways that support an existing belief or hypothesis.
Conflict-directed backjumping - Conflict-directed backjumping is a constraint-search method that uses explanations of failure to choose where to backtrack.
Conflict set - A conflict set records earlier assignments implicated in a failure during constraint-satisfaction search.
Conformal prediction - Conformal prediction is a framework for constructing prediction sets or intervals with finite-sample coverage guarantees under specified conditions...
Conformalized quantile regression - Conformalized quantile regression, or CQR, combines estimated lower and upper conditional quantiles with a conformal calibration step to produce prediction...