Avoiding the Local Minima Problem in Backpropagation Algorithm with Modified Error Function

Authors:
Weixing Bi;Xugang Wang;Zheng Tang;Hiroki Tamura
Affiliations:
The authors are with the Faculty of Engineering, Toyama University, Toyama-shi, 930-8555 Japan.,;The author is with Intelligence Engineering Laboratory, Institute of Software, The Chinese Academy of Sciences, China. E-mail: wxg@iel.iscas.ac.cn;The authors are with the Faculty of Engineering, Toyama University, Toyama-shi, 930-8555 Japan.,;The authors are with the Faculty of Engineering, Toyama University, Toyama-shi, 930-8555 Japan.,
Venue:
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Year:
2005

Citing 0
Cited 1

Urban stormwater runoff prediction using recurrent neural networks

ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

One critical "drawback" of the backpropagation algorithm is the local minima problem. We have noted that the local minima problem in the backpropagation algorithm is usually caused by update disharmony between weights connected to the hidden layer and the output layer. To solve this kind of local minima problem, we propose a modified error function with two terms. By adding one term to the conventional error function, the modified error function can harmonize the update of weights connected to the hidden layer and those connected to the output layer. Thus, it can avoid the local minima problem caused by such disharmony. Simulations on some benchmark problems and a real classification task have been performed to test the validity of the modified error function.