Qualitative limitations incurred in implementations of recurrent neural networks

Author

Michel, Anthony N. ; Wang, Kaining ; Liu, Derong ; Ye, Hui

Author_Institution

Dept. of Electr. Eng., Notre Dame Univ., IN, USA

Volume

15

Issue

3

fYear

1995

fDate

6/1/1995 12:00:00 AM

Firstpage

52

Lastpage

65

Abstract

During the implementation process of artificial neural networks, deviations from the desired ideal neural network are frequently introduced. These include parameter perturbations, transmission delays, and interconnection constraints. In the present article, we study the effects of these realities of imperfection on the qualitative behavior of artificial feedback neural networks. To accomplish this, we utilize a specific class of neural networks (Hopfield-like neural networks) with a specific application (the realization of associative memories) as a vehicle for our study. The principal issues which we address concern the effects of parameter perturbations, transmission delays, and interconnection constraints on the accuracy and on the qualitative properties of the network memories

Keywords

Hopfield neural nets; content-addressable storage; Hopfield-like neural networks; artificial feedback neural networks; associative memories; interconnection constraints; parameter perturbations; qualitative limitations; recurrent neural network implementation; transmission delays; Artificial neural networks; Associative memory; Delay effects; Delay estimation; Hopfield neural networks; Intelligent networks; Neural networks; Neurofeedback; Recurrent neural networks; Very large scale integration;

fLanguage

English

Journal_Title

Control Systems, IEEE

Publisher

ieee

ISSN

1066-033X

Type

jour

DOI

10.1109/37.387618

Filename

387618