Perturbation analysis of a class of neural networks

Author

Meyer-Base, Anke

Author_Institution

Dept. of Comput. & Electr. Eng., Florida Univ., Gainesville, FL, USA

Volume

2

fYear

1997

fDate

9-12 Jun 1997

Firstpage

825

Abstract

We establish robustness stability results for a large class of artificial neural networks for associative memories under parameter perturbations and determine conditions that ensure the existence of asymptotically stable equilibria of the perturbed neural system that are near the asymptotically stable equilibria of the original unperturbed neural network. The proposed stability analysis tool is the sliding mode control and it facilitates the analysis by considering only a reduced-order system instead of the original one and time-dependent external stimuli

Keywords

asymptotic stability; content-addressable storage; neural nets; perturbation techniques; robust control; variable structure systems; associative memories; asymptotically stable equilibria; neural networks; parameter perturbations; perturbation analysis; perturbed neural system; reduced-order system; robustness stability results; sliding mode control; stability analysis tool; time-dependent external stimuli; Artificial neural networks; Computer networks; Matrix decomposition; Neural networks; Neurons; Reduced order systems; Robust stability; Sliding mode control; Stability analysis; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Conference_Location

Houston, TX

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.616130

Filename

616130