Absolute stability conditions for discrete-time recurrent neural networks

Author

Jin, Liang ; Nikiforuk, Peter N. ; Gupta, Madan M.

Author_Institution

Intelligent Syst. Res. Lab., Saskatchewan Univ., Saskatoon, Sask., Canada

Volume

5

Issue

6

fYear

1994

fDate

11/1/1994 12:00:00 AM

Firstpage

954

Lastpage

964

Abstract

An analysis of the absolute stability for a general class of discrete-time recurrent neural networks (RNN´s) is presented. A discrete-time model of RNN´s is represented by a set of nonlinear difference equations. Some sufficient conditions for the absolute stability are derived using Ostrowski´s theorem and the similarity transformation approach. For a given RNN model, these conditions are determined by the synaptic weight matrix of the network. The results reported in this paper need fewer constraints on the weight matrix and the model than in previously published studies

Keywords

difference equations; nonlinear differential equations; recurrent neural nets; stability; Ostrowski´s theorem; absolute stability conditions; discrete-time recurrent neural networks; nonlinear difference equations; similarity transformation; sufficient conditions; synaptic weight matrix; Biological neural networks; Brain modeling; Difference equations; Mathematical model; Neurons; Recurrent neural networks; Stability analysis; Stability criteria; Sufficient conditions; Symmetric matrices;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.329693

Filename

329693