Learning method of parameters for fuzzy rules in universal learning network

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

Research output: Contribution to journalArticlepeer-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 languageEnglish
Pages (from-to)225-231
Number of pages7
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Volume3
Issue number2
Publication statusPublished - Sep 1998

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Engineering (miscellaneous)
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Learning method of parameters for fuzzy rules in universal learning network'. Together they form a unique fingerprint.

Cite this