Sliding mode backpropagation: control theory applied to neural network learning

This paper shows two different methodologies, both based on sliding mode control to train multilayer perceptron. These two methods are compared with standard back propagation, momentum and RPROP algorithms. The results show that the use of this control theory can reduce the time to train multilayer...

Full description

Saved in:
Bibliographic Details
Published inIJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339) Vol. 3; pp. 1774 - 1778 vol.3
Main Authors Parma, G.G., Menezes, B.R., Braga, A.P.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1999
Subjects
Backpropagation algorithms
Control systems
Control theory
Error correction
Multilayer perceptrons
Neural networks
Optimization methods
Sliding mode control
Stability
Variable structure systems
Online AccessGet full text

Cover

More Information
Summary:This paper shows two different methodologies, both based on sliding mode control to train multilayer perceptron. These two methods are compared with standard back propagation, momentum and RPROP algorithms. The results show that the use of this control theory can reduce the time to train multilayer perceptron and also provide an interesting tool to analyze the limits for the parameters involved in the algorithm.
ISBN:0780355296
9780780355293
ISSN:1098-7576
1558-3902
DOI:10.1109/IJCNN.1999.832646