論文

査読有り
2012年4月

Generalization Characteristics of Complex-Valued Feedforward Neural Networks in Relation to Signal Coherence

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
  • Akira Hirose
  • ,
  • Shotaro Yoshida

23
4
開始ページ
541
終了ページ
551
記述言語
英語
掲載種別
研究論文(学術雑誌)
DOI
10.1109/TNNLS.2012.2183613
出版者・発行元
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

Applications of complex-valued neural networks (CVNNs) have expanded widely in recent years-in particular in radar and coherent imaging systems. In general, the most important merit of neural networks lies in their generalization ability. This paper compares the generalization characteristics of complex-valued and real-valued feedforward neural networks in terms of the coherence of the signals to be dealt with. We assume a task of function approximation such as interpolation of temporal signals. Simulation and real-world experiments demonstrate that CVNNs with amplitude-phase-type activation function show smaller generalization error than real-valued networks, such as bivariate and dual-univariate real-valued neural networks. Based on the results, we discuss how the generalization characteristics are influenced by the coherence of the signals depending on the degree of freedom in the learning and on the circularity in neural dynamics.

リンク情報
DOI
https://doi.org/10.1109/TNNLS.2012.2183613
DBLP
https://dblp.uni-trier.de/rec/journals/tnn/HiroseY12
PubMed
https://www.ncbi.nlm.nih.gov/pubmed/24805038
Web of Science
https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000302705600001&DestApp=WOS_CPL
URL
http://dblp.uni-trier.de/db/journals/tnn/tnn23.html#journals/tnn/HiroseY12
ID情報
  • DOI : 10.1109/TNNLS.2012.2183613
  • ISSN : 2162-237X
  • eISSN : 2162-2388
  • DBLP ID : journals/tnn/HiroseY12
  • PubMed ID : 24805038
  • Web of Science ID : WOS:000302705600001

エクスポート
BibTeX RIS