Some stability properties of dynamic neural networks with different time-scales

Author

Sandoval, Alejandro Cruz ; Yu, Wen ; Li, XiaoOu

Author_Institution

CINVESTAV-IPN, Mexico City

fYear

0

fDate

0-0 0

Firstpage

4218

Lastpage

4224

Abstract

Dynamic neural networks with different time-scales include the aspects of fast and slow phenomenons. Some applications require that the equilibrium points of these networks be stable. The objective of the paper is to develop sufficient conditions for stability of the dynamic neural networks with different time scales. Lyapunov function and singularly perturbed technique are combined to access several new stable properties of different time-scales neural networks. Exponential stability and asymptotic stability are obtained by sector and bound conditions. Compared to other papers, these conditions are simpler. Numerical examples are given to demonstrate the effectiveness of the theoretical results.

Keywords

Lyapunov methods; asymptotic stability; neurocontrollers; singularly perturbed systems; Lyapunov function; asymptotic stability; dynamic neural networks; equilibrium points; singularly perturbed technique; stability properties; time-scales neural networks; Asymptotic stability; Circuit stability; Convergence; Lyapunov method; Multi-layer neural network; Multilayer perceptrons; Neural networks; Nonlinear dynamical systems; Nonlinear systems; Stability analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2006. IJCNN '06. International Joint Conference on

Conference_Location

Vancouver, BC

Print_ISBN

0-7803-9490-9

Type

conf

DOI

10.1109/IJCNN.2006.246992

Filename

1716681