Repeated game analysis on ART adaptive categorization game

Author

Fung, Wai-Keung ; Liu, Yun-Hui

Author_Institution

Dept. of Mech. & Autom. Eng., Chinese Univ. of Hong Kong, Shatin, China

Volume

5

fYear

2000

fDate

2000

Firstpage

535

Abstract

A new formulation of an adaptive categorization game of ART-type neural networks is described in this paper. Learning automata dynamics is introduced into the adaptive categorization game in ART-type networks so that the vigilance parameter ρ is adjusted to give variable-sized clusters. Moreover, repeated game analysis is also conducted on the learning automata-based adaptive categorization game in order to study the asymptotic behaviors of the game when data patterns are passed to the ART networks one after the other

Keywords

ART neural nets; game theory; learning automata; pattern classification; pattern clustering; ART-type neural networks; adaptive categorization game; asymptotic behavior; learning automata dynamics; repeated game analysis; sequential data-pattern passing; variable-sized clusters; vigilance parameter; Adaptive systems; Automation; Learning automata; Los Angeles Council; Neurons; Pattern analysis; Resonance; Shape; Subspace constraints; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on

Conference_Location

Como

ISSN

1098-7576

Print_ISBN

0-7695-0619-4

Type

conf

DOI

10.1109/IJCNN.2000.861524

Filename

861524