Learning method of parameters for fuzzy rules in universal learning network

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

*この研究の対応する著者

研究成果: Article査読

抄録

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.

本文言語English
ページ(範囲)225-231
ページ数7
ジャーナルResearch Reports on Information Science and Electrical Engineering of Kyushu University
3
2
出版ステータスPublished - 1998 9月 1
外部発表はい

ASJC Scopus subject areas

  • コンピュータ サイエンス(全般)
  • 電子工学および電気工学

フィンガープリント

「Learning method of parameters for fuzzy rules in universal learning network」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル