Determination of the appropriate node function of NNs by using the cascade-correlation algorithms

Weishui Wan*, Kotaro Hirasawa, Junichi Murata, Chunzhi Jin, Jinglu Hu

*この研究の対応する著者

研究成果査読

抄録

How to determine the appropriate or optimal activation function in the neural networks for a specific learning samples remains open. In this paper the cascade-correlation algorithm which is an efficient constructive algorithm is used after implementation of some kinds of clustering algorithms to produce a modular network structure as a surrogate of activation node functions in the radial basis function (RBF) networks. In this way great improvement on the convergence rate of training algorithms and better approximation are achieved. Simulations with the two-spiral data sets proved the above assertion.

本文言語English
ページ1177-1182
ページ数6
出版ステータスPublished - 2000 12 1
外部発表はい
イベント26th Annual Conference of the IEEE Electronics Society IECON 2000 - Nagoya, Japan
継続期間: 2000 10 222000 10 28

Conference

Conference26th Annual Conference of the IEEE Electronics Society IECON 2000
国/地域Japan
CityNagoya
Period00/10/2200/10/28

ASJC Scopus subject areas

  • 制御およびシステム工学
  • 電子工学および電気工学

フィンガープリント

「Determination of the appropriate node function of NNs by using the cascade-correlation algorithms」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