Learning method of parameters for fuzzy rules in universal learning network

Mitsuo Ikeuchi; Kotaro Hirasawa; Masanao Ohbayashi; Jinglu Hu; Junichi Murata

Learning method of parameters for fuzzy rules in universal learning network

Mitsuo Ikeuchi^*, Kotaro Hirasawa, Masanao Ohbayashi, Jinglu Hu, Junichi Murata

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper, a new method which can alter the values of the parameters in neural networks is proposed in order to enhance the representation abilities of the networks. As an example, a fuzzy reference network is used to modify the parameters in this article, even though any kind of networks such as radial basis function networks and neural networks can be adopted to realize varying parameters. From simulations, it is shown that the network using the proposed method is better than the conventional neural networks in terms of representation abilities of the networks.

Original language	English
Pages (from-to)	225-231
Number of pages	7
Journal	Research Reports on Information Science and Electrical Engineering of Kyushu University
Volume	3
Issue number	2
Publication status	Published - 1998 Sept 1
Externally published	Yes

ASJC Scopus subject areas

Computer Science(all)
Electrical and Electronic Engineering

Cite this

@article{cdd354dc4d164d8597fda6daa27ae33a,

title = "Learning method of parameters for fuzzy rules in universal learning network",

abstract = "In this paper, a new method which can alter the values of the parameters in neural networks is proposed in order to enhance the representation abilities of the networks. As an example, a fuzzy reference network is used to modify the parameters in this article, even though any kind of networks such as radial basis function networks and neural networks can be adopted to realize varying parameters. From simulations, it is shown that the network using the proposed method is better than the conventional neural networks in terms of representation abilities of the networks.",

author = "Mitsuo Ikeuchi and Kotaro Hirasawa and Masanao Ohbayashi and Jinglu Hu and Junichi Murata",

year = "1998",

month = sep,

day = "1",

language = "English",

volume = "3",

pages = "225--231",

journal = "Research Reports on Information Science and Electrical Engineering of Kyushu University",

issn = "1342-3819",

publisher = "Kyushu University, Faculty of Science",

number = "2",

}

TY - JOUR

T1 - Learning method of parameters for fuzzy rules in universal learning network

AU - Ikeuchi, Mitsuo

AU - Hirasawa, Kotaro

AU - Ohbayashi, Masanao

AU - Hu, Jinglu

AU - Murata, Junichi

PY - 1998/9/1

Y1 - 1998/9/1

N2 - In this paper, a new method which can alter the values of the parameters in neural networks is proposed in order to enhance the representation abilities of the networks. As an example, a fuzzy reference network is used to modify the parameters in this article, even though any kind of networks such as radial basis function networks and neural networks can be adopted to realize varying parameters. From simulations, it is shown that the network using the proposed method is better than the conventional neural networks in terms of representation abilities of the networks.

AB - In this paper, a new method which can alter the values of the parameters in neural networks is proposed in order to enhance the representation abilities of the networks. As an example, a fuzzy reference network is used to modify the parameters in this article, even though any kind of networks such as radial basis function networks and neural networks can be adopted to realize varying parameters. From simulations, it is shown that the network using the proposed method is better than the conventional neural networks in terms of representation abilities of the networks.

UR - http://www.scopus.com/inward/record.url?scp=0032154396&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032154396&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0032154396

SN - 1342-3819

VL - 3

SP - 225

EP - 231

JO - Research Reports on Information Science and Electrical Engineering of Kyushu University

JF - Research Reports on Information Science and Electrical Engineering of Kyushu University

IS - 2

ER -

Learning method of parameters for fuzzy rules in universal learning network

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this