Nonlinear dynamical systems control using a new RNN temporal learning strategy

Author

Fang, Yong ; Chow, Tommy W S

Author_Institution

Dept. of Electron. Eng., City Univ. of Hong Kong, China

Volume

52

Issue

11

fYear

2005

Firstpage

719

Lastpage

723

Abstract

The ability of recurrent neural networks (RNN) to handle time-varying input/output through its own temporal operation is discussed. A new class of continuous-time (CT) RNN is proposed and it is proved that any finite time trajectory of a given n-dimensional dynamical CT system with input can be approximated by the internal state of the output units of an RNN. The proposed RNNs are extended for temporal processing.

Keywords

continuous time systems; learning (artificial intelligence); multidimensional systems; nonlinear dynamical systems; recurrent neural nets; temporal reasoning; time-varying systems; 2D system theory; continuous-time recurrent neural networks; finite time trajectory; n-dimensional dynamical continuous-time system; nonlinear dynamical systems control; temporal learning; temporal operation; temporal processing; time-varying input; time-varying output; Control systems; Iterative algorithms; Network topology; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems; Recurrent neural networks; Time varying systems; Two dimensional displays; Continuos-time recurrent neural networks (RNNs); temporal processing; two-dimensional (2-D) system theory;

fLanguage

English

Journal_Title

Circuits and Systems II: Express Briefs, IEEE Transactions on

Publisher

ieee

ISSN

1549-7747

Type

jour

DOI

10.1109/TCSII.2005.852191

Filename

1532442