Artificial Intelligence

← Back to Domain-Specific Abstractions by Domain

8 domain-specific abstractions whose origin domain is Artificial Intelligence.

• AI-complete — An informal label for tasks believed to require capabilities as broad as artificial general intelligence rather than a narrow specialized method.
• Argumentation framework — A formal model representing arguments and attack relations so admissible, preferred, stable or grounded sets of jointly defensible arguments can be computed.
• Automated planning and scheduling — Computational construction and temporal-resource organization of action sequences that move an agent system from an initial state toward specified goals.
• Distributed artificial intelligence — The design and analysis of intelligent behavior produced by multiple computational agents or processes distributed across resources, knowledge and control.
• Knowledge representation and reasoning — The AI discipline of encoding knowledge in formal structures whose semantics and inference procedures support machine reasoning about a domain.
• Model-based reasoning — An inference approach deriving explanations, predictions or diagnoses by combining observations with an explicit declarative model of how a system works.
• Open-Source Artificial Intelligence — An AI-system release whose terms and modifiable materials jointly let recipients use, study, modify, and share the system, including sufficient data information, complete training-and-operation code, and model parameters.
• Qualification problem — The knowledge-representation problem that real-world actions have indefinitely many exceptional preconditions, making a complete list of conditions for their intended effects impossible to state in advance.