Agent swarm classification network ASCN

Author

Chow, Chi-Kin ; Tsui, Hung-Tat

Author_Institution

Dept. of Electron. Eng., Chinese Univ. of Hong Kong, China

Volume

6

fYear

2004

fDate

10-13 Oct. 2004

Firstpage

5604

Abstract

In this paper we introduced a new RBF classification network - "agent swarm classification network ASCN", which is trained by a multi-agent system (MAS) approach. MAS can be regarded as a swarm of independent software agents interact with each other to achieve common goals, complete concurrent distributed tasks under autonomous control. By treating each neuron as an agent, the weights of neurons can be determined through a set of pre-defined simple agent behavior. Three sets of experiments are examined to observe the effectiveness of the proposed method.

Keywords

multi-agent systems; pattern classification; radial basis function networks; software agents; RBF classification network; agent swarm classification network; autonomous control; complete concurrent distributed task; independent software agent swarm; multi-agent systems; pre-defined simple agent behavior; Image processing; Image recognition; Laboratories; Low earth orbit satellites; Multiagent systems; Neural networks; Neurons; Radial basis function networks; Signal processing; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2004 IEEE International Conference on

ISSN

1062-922X

Print_ISBN

0-7803-8566-7

Type

conf

DOI

10.1109/ICSMC.2004.1401086

Filename

1401086