An improved backpropagation algorithm using absolute error function

Authors:
Jiancheng Lv;Zhang Yi
Affiliations:
Computational Intelligence Laboratory, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chegndu, China;Computational Intelligence Laboratory, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chegndu, China
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
Year:
2005

Citing 5
Cited 0

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
The roots of backpropagation: from ordered derivatives to neural networks and political forecasting

The roots of backpropagation: from ordered derivatives to neural networks and political forecasting
Premature saturation in backpropagation networks: mechanism and necessary conditions

Neural Networks
A modified back-propagation method to avoid false local minima

Neural Networks
Training neural networks with additive noise in the desired signal

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

An improved backpropagation algorithm is proposed by using the Lyapunov method to minimize the absolution error function. The improved algorithm can make both error and gradient approach zero so that the local minima problem can be avoided. In addition, since the absolute error function is used, this algorithm is more robust and faster for learning than the backpropagation with the traditional square error function when target signals include some incorrect data. This paper also proposes a method of using Lyapunov stability theory to derive a learning algorithm which directly minimize the absolute error function.