DocumentCode
1842869
Title
Sliding mode backpropagation: control theory applied to neural network learning
Author
Parma, G.G. ; Menezes, B.R. ; Braga, A.P.
Author_Institution
Dept. de Engenharia Eletronica, Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil
Volume
3
fYear
1999
fDate
1999
Firstpage
1774
Abstract
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
Keywords
backpropagation; multilayer perceptrons; variable structure systems; RPROP algorithms; back propagation; control theory; momentum algorithm; multilayer perceptron training; neural network learning; sliding mode backpropagation; Backpropagation algorithms; Control systems; Control theory; Error correction; Multilayer perceptrons; Neural networks; Optimization methods; Sliding mode control; Stability; Variable structure systems;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location
Washington, DC
ISSN
1098-7576
Print_ISBN
0-7803-5529-6
Type
conf
DOI
10.1109/IJCNN.1999.832646
Filename
832646
Link To Document