論文

査読有り 筆頭著者 責任著者
2003年

On the Inherent Property of the Decision Boundary in Complex-Valued Neural Networks.

Neurocomputing
  • Tohru Nitta

50
C
開始ページ
291
終了ページ
303
記述言語
英語
掲載種別
研究論文(学術雑誌)
DOI
10.1016/S0925-2312(02)00568-4
出版者・発行元
ELSEVIER SCIENCE BV

This paper shows the differences between the real-valued neural network and the complex-valued neural network by analyzing their fundamental properties from the view of architectures. The main results may be summarized as follows: (a) A single complex-valued neuron with n-inputs is equivalent to two real-valued neurons with 2n-inputs which have a restriction on a set of weight parameters. (b) The decision boundary of a single complex-valued neuron consists of two hypersurfaces which intersect orthogonally. (c) The decision boundary of a three-layered complex-valued neural network has the orthogonal structure. (d) The orthogonality of the decision boundary in the three-layered Complex-BP network can improve its generalization ability. (e) The average of the learning speed of the Complex-BP is several times faster than that of the Real-BP, and the standard deviation of the learning speed of the Complex-BP is smaller than that of the Real-BP. (C) 2002 Elsevier Science B.V. All rights reserved.

リンク情報
DOI
https://doi.org/10.1016/S0925-2312(02)00568-4
DBLP
https://dblp.uni-trier.de/rec/journals/ijon/Nitta03
Web of Science
https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000180567700017&DestApp=WOS_CPL
URL
https://dblp.uni-trier.de/db/journals/ijon/ijon50.html#Nitta03
ID情報
  • DOI : 10.1016/S0925-2312(02)00568-4
  • ISSN : 0925-2312
  • DBLP ID : journals/ijon/Nitta03
  • Web of Science ID : WOS:000180567700017

エクスポート
BibTeX RIS