Globally Exponentially Stability of Discrete-Time Recurrent Neural Networks with Unsaturating Linear Activation Functions

Abstract:

Article Preview

Globally exponentially stability (GES) of a class of discrete- time recurrent neural networks with unsaturating linear activation functions is studied. Based on matrix eigenvalue, a new definition of GES is presented. By applying matrix theory, some conditions for GES are obtained. Simultaneously, those conditions are proved without energy functions.

Info:

Periodical:

Key Engineering Materials (Volumes 467-469)

Edited by:

Dehuai Zeng

Pages:

731-736

DOI:

10.4028/www.scientific.net/KEM.467-469.731

Citation:

Z. B. Lin et al., "Globally Exponentially Stability of Discrete-Time Recurrent Neural Networks with Unsaturating Linear Activation Functions", Key Engineering Materials, Vols. 467-469, pp. 731-736, 2011

Online since:

February 2011

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.