Continuous-time recurrent multilayer perceptrons for nonlinear system identification

Author

Yu, Wen ; Li, XiaoOu

Author_Institution

Departamento de Control Automatico, CINVESTAV-IPN, Mexico

fYear

2005

fDate

28-31 Aug. 2005

Firstpage

1636

Lastpage

1641

Abstract

In this paper continuous-time recurrent multilayer perceptrons (RMLP) are proposed to identify nonlinear systems. Using the function approximation theorem for multilayer perceptrons(MLP), we conclude that RMLP can approximate any dynamic system in any degree of accuracy. By means of a Lyapunov-like analysis, a stable learning algorithm for RMLP is determined. The suggested learning algorithm is similar to the well-known backpropagation rule of the multilayer perceptrons but with an additional term which assure the stability of identification error

Keywords

Lyapunov methods; backpropagation; continuous time systems; function approximation; identification; multilayer perceptrons; nonlinear systems; stability; Lyapunov-like analysis; backpropagation rule; continuous-time recurrent multilayer perceptron; dynamic system; function approximation theorem; identification error; learning algorithm; nonlinear system identification; Backpropagation algorithms; Function approximation; Least squares approximation; Multilayer perceptrons; Neural networks; Nonhomogeneous media; Nonlinear dynamical systems; Nonlinear systems; Recurrent neural networks; Stability;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Applications, 2005. CCA 2005. Proceedings of 2005 IEEE Conference on

Conference_Location

Toronto, Ont.

Print_ISBN

0-7803-9354-6

Type

conf

DOI

10.1109/CCA.2005.1507367

Filename

1507367