Deriving sufficient conditions for global asymptotic stability of delayed neural networks via nonsmooth analysis-II

Author

Qi, Houduo ; Qi, Liqun ; Yang, Xiaoqi

Author_Institution

Sch. of Math., Univ. of Southampton, UK

Volume

16

Issue

6

fYear

2005

Firstpage

1701

Lastpage

1706

Abstract

Following our recent approach of nonsmooth analysis, we report a new set of sufficient conditions and its implications for the global asymptotic stability of delayed cellular neural networks (DCNN). The new conditions not only unify a string of previous stability results, but also yield strict improvement over them by allowing the symmetric part of the feedback matrix positive definite, hence enlarging the application domain of DCNNs. Advantages of the new results over existing ones are illustrated with examples. We also compare our results with those related results obtained via LMI approach.

Keywords

Jacobian matrices; asymptotic stability; delays; neural nets; numerical stability; LMI approach; Lipschitzian function; delayed cellular neural network; equilibrium point; feedback matrix; global asymptotic stability; nonsmooth analysis; stability string unification; sufficient condition derivation; Asymptotic stability; Cellular neural networks; Delay effects; Mathematics; Neural networks; Neurofeedback; Output feedback; Stability analysis; State feedback; Sufficient conditions; Equilibrium point; Lipschitzian functions; global asymptotic stability; neural networks; nonsmooth analysis; Algorithms; Computer Simulation; Models, Theoretical; Neural Networks (Computer); Numerical Analysis, Computer-Assisted; Signal Processing, Computer-Assisted; Time Factors;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/TNN.2005.852975

Filename

1528546