Improved conditions for global exponential stability of recurrent neural networks with time-varying delays

Author

Zhigang Zeng ; Jun Wang

Author_Institution

Dept. of Autom. & Comput.-Aided Eng., Chinese Univ. of Hong Kong

Volume

17

Issue

3

fYear

2006

fDate

5/1/2006 12:00:00 AM

Firstpage

623

Lastpage

635

Abstract

This paper presents new theoretical results on global exponential stability of recurrent neural networks with bounded activation functions and time-varying delays. The stability conditions depend on external inputs, connection weights, and time delays of recurrent neural networks. Using these results, the global exponential stability of recurrent neural networks can be derived, and the estimated location of the equilibrium point can be obtained. As typical representatives, the Hopfield neural network (HNN) and the cellular neural network (CNN) are examined in detail

Keywords

Hopfield neural nets; asymptotic stability; cellular neural nets; delays; time-varying systems; transfer functions; Hopfield neural network; bounded activation functions; cellular neural network; connection weights; global exponential stability; recurrent neural networks; time-varying delays; Asymptotic stability; Automation; Cellular neural networks; Delay effects; Hopfield neural networks; Neural networks; Neurons; Recurrent neural networks; Stability analysis; Stability criteria; External inputs; neural networks (NNs); stability; time-varying delay; Algorithms; Animals; Artificial Intelligence; Computer Simulation; Humans; Information Storage and Retrieval; Nerve Net; Neural Networks (Computer); Pattern Recognition, Automated; Systems Theory; Time Factors;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/TNN.2006.873283

Filename

1629087