A fault-tolerant Hopfield network for storing correlated patterns

Author

Vidyasagar, M. ; Ramesh, V.N.V.K.

Author_Institution

Centre for Artificial Intelligence & Robotics, Bangalore, India

Volume

2

fYear

1992

fDate

7-11 Jun 1992

Firstpage

160

Abstract

The use of Hopfield-type neural networks for storing a set of correlated (i.e. nonorthogonal) bipolar pattern vectors is considered. The sum of outer products is used as the weight matrix even when the patterns are correlated. It is shown that, provided that the correlation is sufficiently small in a precise sense, each of the given patterns is a stable state of the neural network. Each pattern is also attractive, in that each initial state that is sufficiently close to the specified pattern is mapped into that pattern. It is shown that, when the patterns are uncorrelated, the results given reduce exactly to the known results

Keywords

Hopfield neural nets; content-addressable storage; fault tolerant computing; bipolar pattern vectors; fault-tolerant Hopfield network; neural network; outer products; storing correlated patterns; weight matrix; Artificial intelligence; Artificial neural networks; Bipolar integrated circuits; Fault tolerance; Hamming distance; Hopfield neural networks; Image storage; Intelligent robots; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1992. IJCNN., International Joint Conference on

Conference_Location

Baltimore, MD

Print_ISBN

0-7803-0559-0

Type

conf

DOI

10.1109/IJCNN.1992.227014

Filename

227014