Approximation of dynamical time-variant systems by continuous-time recurrent neural networks

Author

Li, Xiao-Dong ; Ho, John K L ; Chow, Tommy W S

Author_Institution

Dept. of Manuf. Eng. & Eng. Manage., City Univ. of Hong Kong, China

Volume

52

Issue

10

fYear

2005

Firstpage

656

Lastpage

660

Abstract

This paper studies the approximation ability of continuous-time recurrent neural networks to dynamical time-variant systems. It proves that any finite time trajectory of a given dynamical time-variant system can be approximated by the internal state of a continuous-time recurrent neural network. Given several special forms of dynamical time-variant systems or trajectories, this paper shows that they can all be approximately realized by the internal state of a simple recurrent neural network.

Keywords

T invariance; approximation theory; continuous time systems; recurrent neural nets; continuous-time recurrent neural networks; dynamical time-variant system approximation; Automatic control; Control systems; Intelligent systems; Manufacturing; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Recurrent neural networks; Research and development management; System identification; Approximation; dynamical time-variant systems; recurrent neural networks;

fLanguage

English

Journal_Title

Circuits and Systems II: Express Briefs, IEEE Transactions on

Publisher

ieee

ISSN

1549-7747

Type

jour

DOI

10.1109/TCSII.2005.852006

Filename

1519654