A generic tool for distributed AI with matching as message passing

Author

Eberbach, Eugene

Author_Institution

Jodrey Sch. of Comput. Sci., Acadia Univ., Wolfville, NS, Canada

fYear

1997

Firstpage

11

Lastpage

18

Abstract

The paper concentrates on the problem of integrating genetic programming, neural networks, autonomous agents with some symbolic AI techniques. For this purpose, it introduces and employs the S-calculus, which is a general model of computation with a quantitative aspect (cost) allowing naturally to express optimization and modification in dynamic parallel AI systems. The papers presents basic operators of the calculus, and a basic inference engine, so called modifying algorithm, used for problem solving. Next the approach is illustrated through a series of examples from various domains, including symbolic and subsymbolic systems

Keywords

cooperative systems; genetic algorithms; inference mechanisms; message passing; neural nets; problem solving; software agents; symbol manipulation; S-calculus; autonomous agents; computation model; cost; distributed AI; dynamic parallel AI systems; genetic programming; inference engine; matching; message passing; modifying algorithm; neural networks; optimization; problem solving; subsymbolic systems; symbolic AI; symbolic systems; Artificial intelligence; Autonomous agents; Calculus; Computational modeling; Concurrent computing; Cost function; Engines; Genetic programming; Message passing; Neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Tools with Artificial Intelligence, 1997. Proceedings., Ninth IEEE International Conference on

Conference_Location

Newport Beach, CA

ISSN

1082-3409

Print_ISBN

0-8186-8203-5

Type

conf

DOI

10.1109/TAI.1997.632230

Filename

632230