Generalization characteristics of complex-valued feedforward neural networks in relation to signal coherence

Akira Hirose, Shotaro Yoshida

研究成果: Article査読

158 被引用数 (Scopus)

抄録

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.

本文言語English
論文番号6138313
ページ(範囲)541-551
ページ数11
ジャーナルIEEE Transactions on Neural Networks and Learning Systems
23
4
DOI
出版ステータスPublished - 2012
外部発表はい

ASJC Scopus subject areas

  • ソフトウェア
  • コンピュータ サイエンスの応用
  • コンピュータ ネットワークおよび通信
  • 人工知能

フィンガープリント

「Generalization characteristics of complex-valued feedforward neural networks in relation to signal coherence」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