Novel Stability Analysis for Recurrent Neural Networks With Multiple Delays via Line Integral-Type L-K Functional

Author

Zhenwei Liu ; Huaguang Zhang ; Qingling Zhang

Author_Institution

Coll. of Inf. Sci. & Eng., Northeastern Univ., Shenyang, China

Volume

21

Issue

11

fYear

2010

Firstpage

1710

Lastpage

1718

Abstract

This paper studies the stability problem of a class of recurrent neural networks (RNNs) with multiple delays. By using an augmented matrix-vector transformation for delays and a novel line integral-type Lyapunov-Krasovskii functional, a less conservative delay-dependent global asymptotical stability criterion is first proposed for RNNs with multiple delays. The obtained stability result is easy to check and improve upon the existing ones. Then, two numerical examples are given to verify the effectiveness of the proposed criterion.

Keywords

Lyapunov methods; delays; matrix algebra; recurrent neural nets; Lyapunov-Krasovskii functional; RNN; line integral type L-K functional; matrix vector transformation; multiple delays; novel stability analysis; recurrent neural networks; Asymptotic stability; Delay; Linear matrix inequalities; Numerical stability; Recurrent neural networks; Stability criteria; Augmented matrix-vector transformation; global asymptotical stability; line integral-type Lyapunov-Krasovskii (L-K) functional; multiple delays; recurrent neural networks (RNNs); Algorithms; Computer Simulation; Mathematical Computing; Neural Networks (Computer); Nonlinear Dynamics; Time Factors;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/TNN.2010.2054107

Filename

5617347