Some results on the stability of analog neural networks with time delays

Author

Liang, Xue-Bin ; He, Yong-Bao ; Wu, Li-De

Author_Institution

Dept. of Comput. Sci., Fudan Univ., Shanghai, China

Volume

2

fYear

1998

fDate

4-9 May 1998

Firstpage

1388

Abstract

This paper investigates the global asymptotic stability (GAS) independent of time delay for analog neural networks models whose self-feedback interconnections have and have no corresponding time delays respectively. By constructing two different Lyapunov functionals, some new sufficient conditions represented by M-matrices, which can guarantee the GAS independent of time delay for the analog neural network models with time delays, are derived. These sufficient conditions obtained for GAS are also compared with the existing ones in the literature

Keywords

Lyapunov methods; analogue processing circuits; asymptotic stability; circuit feedback; circuit stability; delays; neural nets; Lyapunov function; analog neural networks; global asymptotic stability; matrix algebra; self-feedback interconnections; sufficient conditions; time delays; Artificial neural networks; Computer science; Delay effects; Equations; Helium; Neural networks; Neurons; Recurrent neural networks; Stability; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on

Conference_Location

Anchorage, AK

ISSN

1098-7576

Print_ISBN

0-7803-4859-1

Type

conf

DOI

10.1109/IJCNN.1998.685978

Filename

685978