Stability analysis of recurrent neural networks with time-varying activation functions

Author

Mostafa, Mahjabeen ; Teich, Werner G. ; Lindner, Jurgen

Author_Institution

Inst. of Inf. Technol., Univ. of Ulm, Ulm, Germany

fYear

2011

fDate

25-27 July 2011

Firstpage

1

Lastpage

6

Abstract

The dynamical behavior of a single layer recurrent neural network without hidden neurons has been investigated intensively and its stability has been analyzed using the Lyapunov method. Since the pioneering work of Hopfield many modified versions of the original Hopfield network have been suggested and their stability has been proven. In this paper we generalize these results to the case of a time-varying activation function, which is very useful in the field of parameter estimation and communications.

Keywords

Hopfield neural nets; Lyapunov methods; stability; Lyapunov method; original Hopfield network; recurrent neural networks; stability analysis; time-varying activation functions; Asymptotic stability; Biological neural networks; Lyapunov methods; Neurons; Recurrent neural networks; Stability criteria; Lyapunov function; Recurrent neural network; stability analysis; time-varying activation function;

fLanguage

English

Publisher

ieee

Conference_Titel

Nonlinear Dynamics and Synchronization (INDS) & 16th Int'l Symposium on Theoretical Electrical Engineering (ISTET), 2011 Joint 3rd Int'l Workshop on

Conference_Location

Klagenfurt

Print_ISBN

978-1-4577-0759-9

Type

conf

DOI

10.1109/INDS.2011.6024816

Filename

6024816