A new adaptive backpropagation algorithm based on Lyapunov stability theory for neural networks

Man, Z, Wu, H, Liu, S and Yu, X 2006, 'A new adaptive backpropagation algorithm based on Lyapunov stability theory for neural networks', IEEE Transaction on Neural Networks, vol. 17, no. 6, pp. 1580-1591.


Document type: Journal Article
Collection: Journal Articles

Attached Files
Name Description MIMEType Size
n2006001753.pdf Published version application/pdf 1016.54KB
Title A new adaptive backpropagation algorithm based on Lyapunov stability theory for neural networks
Author(s) Man, Z
Wu, H
Liu, S
Yu, X
Year 2006
Journal name IEEE Transaction on Neural Networks
Volume number 17
Issue number 6
Start page 1580
End page 1591
Total pages 11
Publisher IEEE
Abstract A new adaptive backpropagation (BP) algorithm based on Lyapunov stability theory for neural networks is developed in this paper. It is shown that the candidate of a Lyapunov function V(k) of the tracking error between the output of a neural network and the desired reference signal is chosen first, and the weights of the neural network are then updated, from the output layer to the input layer, in the sense that DeltaV(k)=V(k)-V(k-1)<0. The output tracking error can then asymptotically converge to zero according to Lyapunov stability theory. Unlike gradient-based BP training algorithms, the new Lyapunov adaptive BP algorithm in this paper is not used for searching the global minimum point along the cost-function surface in the weight space, but it is aimed at constructing an energy surface with a single global minimum point through the adaptive adjustment of the weights as the time goes to infinity. Although a neural network may have bounded input disturbances, the effects of the disturbances can be eliminated, and asymptotic error convergence can be obtained. The new Lyapunov adaptive BP algorithm is then applied to the design of an adaptive filter in the simulation example to show the fast error convergence and strong robustness with respect to large bounded input disturbances
Subject Optimisation
Keyword(s) adaptive filtering
backpropagation
convergence
feedforward neural networks
Lyapunov stability
DOI - identifier 10.1109/TNN.2006.880360
Copyright notice © 2006 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
ISSN 1045-9227
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 75 times in Scopus Article | Citations
Altmetric details:
Access Statistics: 380 Abstract Views, 765 File Downloads  -  Detailed Statistics
Created: Wed, 18 Feb 2009, 09:53:18 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us