Comparative study between functions distributed network and ordinary neural network

Author

XIONG, Qingyu ; Hirasawa, Kotaro ; Hu, Jinglu ; Murata, Junichi

Author_Institution

Intelligent Control Lab., Kyushu Univ., Fukuoka, Japan

Volume

3

fYear

2001

fDate

2001

Firstpage

1548

Abstract

A functions distributed network, called universal learning networks with branch control of relative strength (ULNs with BR), is proposed. The point of the paper is to adjust the outputs of the intermediate nodes of the basic network using an additional branch control network. The adjustment multiplies the nodes outputs by the coefficients ranging from zero to one, which is obtained from the branch control network. Therefore, the following are characterized in ULNs with BR, (1) the branch is cut when the coefficient of its branch is zero, and (2) multiplication is carried out in the nodes outputs adjustment when the coefficient takes a nonzero value. ULNs with BR is applied to two-spirals problem. The simulation results show that ULNs with BR exhibits better performance than the conventional neural networks with comparable complexity

Keywords

fuzzy logic; fuzzy neural nets; inference mechanisms; learning (artificial intelligence); multilayer perceptrons; Universal Learning Networks; branch control; complexity; functions distributed network; ordinary neural network; relative strength; two-spirals problem; Artificial neural networks; Biological neural networks; Brain modeling; Information science; Intelligent control; Laboratories; Mathematics; Neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 2001 IEEE International Conference on

Conference_Location

Tucson, AZ

ISSN

1062-922X

Print_ISBN

0-7803-7087-2

Type

conf

DOI

10.1109/ICSMC.2001.973504

Filename

973504