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 Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Tang, Z. Articles by Ishii, M. Search for Related Content PubMed PubMed Citation Articles by Tang, Z. Articles by Ishii, M.

An Algorithm of Supervised Learning for Multilayer Neural Networks

tang{at}iis.toyama-u.ac.jp, Faculty of Engineering, Toyama University, 3190 Gofuku Toyama 930-8555, Japan

XuGang Wang

xugunw76{at}hotmail.com, Faculty of Engineering, Toyama University, 3190 Gofuku Toyama 930-8555, Japan

Hiroki Tamura

tamura{at}iis.toyama-u.ac.jp, Faculty of Engineering, Toyama University, 3190 Gofuku Toyama 930-8555, Japan

Masahiro Ishii

ishii{at}iis.toyama-u.ac.jp, Faculty of Engineering, Toyama University, 3190 Gofuku Toyama 930-8555, Japan

A method of supervised learning for multilayer artificial neural networks to escape local minima is proposed. The learning model has two phases: a backpropagation phase and a gradient ascent phase. The backpropagation phase performs steepest descent on a surface in weight space whose height at any point in weight space is equal to an error measure, and it finds a set of weights minimizing this error measure. When the backpropagation gets stuck in local minima, the gradient ascent phase attempts to fill up the valley by modifying gain parameters in a gradient ascent direction of the error measure. The two phases are repeated until the network gets out of local minima. The algorithm has been tested on benchmark problems, such as exclusive-or (XOR), parity, alphabetic characters learning, Arabic numerals with a noise recognition problem, and a realistic real-world problem: classification of radar returns from the ionosphere. For all of these problems, the systems are shown to be capable of escaping from the backpropagation local minima and converge faster when using the new proposed method than using the simulated annealing techniques.