Chaos and Neural Network Learning. Some Observations

In this paper, we investigate the impact of chaos on the learning process of the XOR-boolean function by backpropagation neural networks. It has been shown previously that such networks exhibit chaotic behavior but it has never been studied whether chaos enhances or prohibits learning. We show that...

Full description

Saved in:
Bibliographic Details
Published inNeural processing letters Vol. 7; no. 2; pp. 69 - 80
Main Authors Bertels, K, Neuberg, L, Vassiliadis, S, Pechanek, D.G
Format Journal Article
LanguageEnglish
Published Dordrecht Springer Nature B.V 01.04.1998
Subjects
Algorithms
Back propagation networks
Boolean functions
Learning
Neural networks
Parameters
Online AccessGet full text

Cover

More Information
Summary:In this paper, we investigate the impact of chaos on the learning process of the XOR-boolean function by backpropagation neural networks. It has been shown previously that such networks exhibit chaotic behavior but it has never been studied whether chaos enhances or prohibits learning. We show that chaos (when learning the XOR-boolean function) does indeed allow learning but our findings do not indicate any positive role of chaos for learning. In particular, we found that the temperature parameter in the backpropagation algorithm causes the parameter regime, as represented by means of a bifurcation diagram, to shift to the right. We furthermore found that as less chaos appears during the learning process, the faster, on the average, a neural network learned the XOR-function.
ISSN:1370-4621
1573-773X
DOI:10.1023/A:1009680311307