Articulatory synthesis - Articulatory synthesis generates speech by modeling aspects of how the human vocal system produces sound.
Artificial brain - Artificial brain is a broad label for an engineered system intended to reproduce, simulate or draw inspiration from aspects of a biological brain.
Artificial consciousness - Artificial consciousness is the possibility or proposed creation of subjective experience in an artificial system, and the field that investigates it.
Artificial general intelligence - Artificial general intelligence, or AGI, is a hypothetical form of AI that could learn and perform any intellectual task a human can, across domains, rather...
Artificial intelligence - Artificial intelligence, or AI, is the field of building and studying computational systems that perform tasks involving abilities such as perception...
Artificial intelligence content detection - Artificial intelligence content detection is the use of technical methods to assess whether text, images, audio or video was generated or significantly...
Artificial intelligence of things - Artificial intelligence of things, often shortened to AIoT, combines AI capabilities with connected devices in the Internet of Things.
Artificial intimacy - Artificial intimacy is the experience of closeness, emotional connection or a relationship with an artificial system, such as a conversational AI companion.
Artificial life - Artificial life, often shortened to ALife, studies life-like processes by constructing and examining artificial systems.
Artificial narrow intelligence - Artificial narrow intelligence, or ANI, is AI whose capabilities are concentrated on a defined task or limited range of tasks.
Artificial neural network - An artificial neural network is a computational model made from connected units that transform numerical information using adjustable parameters.
Artificial precision - Artificial precision is the misleading appearance of certainty created by reporting more numerical detail than the evidence or measurement process supports.
ASCII - ASCII, the American Standard Code for Information Interchange, is a character encoding that assigns numeric values to a limited set of characters and...
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...
Aspect - Aspect is the way language represents the temporal organization of a situation: for example, as ongoing, completed, habitual, repeated, or possessing an...
Aspect ratio - Aspect ratio is the proportional relationship between width and height.
ASR-complete - ASR-complete is an informal expression for a task that brings together much of the difficulty of automatic speech recognition and related spoken-language...
Assignment - An assignment gives values to variables. In a constraint-satisfaction problem, it selects a value from the domain of each variable it covers.
Assignment problems - Assignment problems allocate items from one set to items in another while optimizing an objective and satisfying matching constraints.
Associative classifier - An associative classifier is a supervised learning model that predicts a class using association rules.
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.
Assumed-density filter - An assumed-density filter is a sequential Bayesian approximation method that keeps the evolving probability distribution within a chosen manageable family.
Asymmetric cointegration - Asymmetric cointegration describes long-run relationships between time series in which the adjustment process or the relationship itself permits different...
Asymmetric multiprocessing - Asymmetric multiprocessing, or AMP, is an arrangement in which processors or cores have different assigned roles or operate under separate management rather...
Asymmetric numeral systems - Asymmetric numeral systems (ANS) are a family of lossless entropy-coding methods that represent symbols by reversible changes to an integer state and a...
Asymmetric relationships - Asymmetric relationships, in the categorical-data terminology used by the supplied glossary, are relationships analyzed with designated predictor and...
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.
Asymptotically unbiased estimator - An asymptotically unbiased estimator is a sequence of statistical estimation rules whose bias approaches zero as the sample size grows without bound, under...
Asynchronous Advantage Actor-Critic - Asynchronous Advantage Actor-Critic (A3C) is a reinforcement-learning method in which multiple actor-learners interact with separate environment instances...
Asynchronous policy iteration - Asynchronous policy iteration is a family of dynamic-programming approaches that update policy and value information for selected states or portions of a...
ATMS - ATMS stands for assumption-based truth maintenance system.
ATN - ATN stands for augmented transition network in natural-language parsing.
Atom - An atom is a basic logical formula that is not built by combining simpler formulas with logical connectives or quantifiers.
Atomic data types - Atomic data types are types whose values are treated as individual units by a particular data model or type system, rather than as collections or records...
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.
Atomicity (database systems) - Atomicity in database systems is the property that a transaction's covered changes succeed as one unit or are discarded as one unit.
ATRANS - ATRANS is a primitive action in Roger Schank's conceptual dependency approach to representing language meaning.
Attachment ambiguity - Attachment ambiguity occurs when a phrase or other constituent can connect to more than one place in a sentence's grammatical structure.
Attack - An attack is a deliberate attempt to compromise a system, its information or its operation.
Attention - Attention is a neural-network mechanism that combines information using weights that depend on the current input or processing context.
Attention coverage mechanism - An attention coverage mechanism keeps a record of how much attention source positions have already received and uses that record during later decoding.
Attention head - An attention head is one attention computation within a multi-head attention mechanism.
Attention mask - An attention mask specifies which positions may participate in an attention calculation.
Attenuation - Attenuation is a weakening of an observed signal or statistical relationship.