Absolute error - Absolute error is the size of the difference between a predicted or estimated numerical value and its reference value, without regard to direction.
Abstraction - Abstraction is the deliberate representation of something using selected features while leaving out other details.
Abstraction hierarchy - An abstraction hierarchy is an arrangement of representations at different levels of detail, connected so that a problem can be considered broadly and then...
Accessibility relations - Accessibility relations are connections between possible worlds or states in a formal model, specifying which alternatives are relevant from a given world.
Action cost function - An action cost function assigns a numerical cost to taking an action in a planning or search problem.
Actor - An actor, in planning, is an entity that performs actions within the modeled environment.
Adaptive utility - Adaptive utility is a decision-theoretic approach in which uncertainty about preferences can be reduced through experience or information.
Add list - An add list is the part of a STRIPS-style planning action that specifies the facts to be made true in the resulting state.
Additive value function - An additive value function evaluates an option by adding separate contributions from its attributes.
Admissible heuristic - An admissible heuristic is a search estimate that never overestimates the true minimum remaining cost of reaching a goal.
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.
Aggregation - Aggregation, in planning, is the representation of multiple relevantly interchangeable objects or resources as a quantity or group instead of distinguishing...
Alpha-beta pruning - Alpha-beta pruning is an optimization of minimax search that skips branches proven unable to improve the relevant decision.
Ambiguity - Ambiguity is the presence of more than one plausible meaning or interpretation in an expression or representation.
Ambiguity aversion - Ambiguity aversion is a preference for options with better-specified probabilities over otherwise comparable options whose probabilities are uncertain or...
Analogical reasoning - Analogical reasoning uses a structured comparison with a familiar situation to generate insights about another situation.
Analysis of algorithms - Analysis of algorithms is the study of an algorithm's behavior, especially the resources it requires as the size and characteristics of its input change.
Anchoring effect - The anchoring effect is a tendency for a judgment, especially a numerical estimate, to be influenced by an initial value or reference point.
And-Elimination - And-Elimination is a rule of logical inference that allows either component of an established conjunction to be concluded separately.
Angelic nondeterminism - Angelic nondeterminism interprets an unresolved choice as one that can be made in favor of achieving a specified objective.
Angelic semantics - Angelic semantics gives a high-level planning action meaning in terms of the states reachable by at least one permitted refinement into primitive actions.
Answer literal - An answer literal is a specially introduced logical literal that carries the values of query variables through a resolution proof.
Answer set programming - Answer set programming, or ASP, is a declarative approach to solving problems by describing acceptable solutions with logical rules and constraints.
Answer sets - Answer sets are the stable models of a logic program used in answer set programming.
Anytime A* - Anytime A* is a form of heuristic search that retains a solution once one is found and continues searching for better solutions when more computation time...
Anytime algorithm - An anytime algorithm is designed to provide a usable result within a flexible computation budget and improve result quality when more computation is available.
Apprenticeship Learning - Apprenticeship learning is learning to perform a task from demonstrations of an expert's behavior.
Approximate near-neighbors - Approximate near-neighbors are data points found under a relaxed closeness requirement rather than an exact nearest-point requirement.
Architecture - In the intelligent-agent context, architecture is the underlying computing and interaction platform on which an agent program runs.
Arity - Arity is the number of arguments that a function, predicate, relation, or operation takes.
Artificial life - Artificial life, often shortened to ALife, studies life-like processes by constructing and examining artificial systems.
Asilomar AI Principles - The Asilomar AI Principles are a set of 23 principles developed in connection with the 2017 Beneficial AI conference at Asilomar and coordinated by the...
Assignment - An assignment gives values to variables. In a constraint-satisfaction problem, it selects a value from the domain of each variable it covers.
Associative memory - Associative memory retrieves stored information from a cue related to its content, rather than requiring an exact storage address.
Assortativity - Assortativity describes how strongly connected nodes in a network resemble one another on a chosen property.
Asymptotic analysis - Asymptotic analysis studies how an algorithm's resource requirements grow as its input size becomes large.
Asymptotic bounded optimality - Asymptotic bounded optimality is a formal way to assess an intelligent agent's program while accounting for limited computational resources.
ATMS - ATMS stands for assumption-based truth maintenance system.
Atom - An atom is a basic logical formula that is not built by combining simpler formulas with logical connectives or quantifiers.
Atomic representation - An atomic representation describes each state as a single indivisible unit for the reasoning method using it.
Atomic sentence - An atomic sentence is a basic statement in a formal logical language that is not built by combining other statements with logical connectives or quantifiers.
Attribute-based extraction - Attribute-based extraction is the identification of selected properties, such as price, date or color, in source material and their conversion into...
Augmented grammar - An augmented grammar is a grammar extended with information or conditions beyond simple phrase-building rules.
Authority - In link analysis, an authority is a page or node that receives strong endorsement through incoming links from useful hub nodes.
Automated reasoning - Automated reasoning is the use of computer procedures to derive conclusions, find satisfying assignments or establish contradictions from formally...
Automatic assembly sequencing - Automatic assembly sequencing is the computer-assisted determination of an order for joining parts into a finished product.
Automatic differentiation - Automatic differentiation, often shortened to autodiff or AD, computes derivatives of functions expressed as computer programs by combining derivative rules...
Average degree connectivity - Average degree connectivity describes the average degree of neighbors of nodes that share a particular degree.