HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Oohori, T. Articles by Watanabe, K. Search for Related Content PubMed Articles by Oohori, T. Articles by Watanabe, K.

A New Backpropagation Learning Algorithm for Layered Neural Networks with Nondifferentiable Units

oohori{at}hit.ac.jp Department of Information Design, Hokkaido Institute of Technology, Sapporo 006-8585, Japan

Hidenori Naganuma

q04305{at}hit.ac.jp Division of Electrical Engineering, Graduate School of Engineering, Hokkaido Institute of Technology, Sapporo 006-8585, Japan

Kazuhisa Watanabe

nabek{at}hit.ac.jp Department of Information Network Engineering, Hokkaido Institute of Technology, Sapporo 006-8585, Japan

We propose a digital version of the backpropagation algorithm (DBP) for three-layered neural networks with nondifferentiable binary units. This approach feeds teacher signals to both the middle and output layers, whereas with a simple perceptron, they are given only to the output layer. The additional teacher signals enable the DBP to update the coupling weights not only between the middle and output layers but also between the input and middle layers. A neural network based on DBP learning is fast and easy to implement in hardware. Simulation results for several linearly nonseparable problems such as XOR demonstrate that the DBP performs favorably when compared to the conventional approaches. Furthermore, in large-scale networks, simulation results indicate that the DBP provides high performance.