A new learning algorithm for bidirectional associative memory neural networks

Author

Khorasani, K. ; Cuffaro, A. ; Grigoriu, T.

Author_Institution

Dept. of Electr. & Comput. Eng., Concordia Univ., Montreal, Que., Canada

Volume

2

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

1115

Abstract

A new algorithm is proposed for improving the learning capability of bidirectional associative memory (BAM) neural networks. The proposed approach, unlike other methods in the literature, is not based on minimizing the energy function of the stored patterns. The proposed technique is the generalization of an auto-associative learning algorithm that has been developed for Hopfield networks. The BAM network is extremely robust to noise, almost guaranteeing perfect recall of all stored patterns with as much as 49% noise. The learning algorithm when applied to a number of test patterns used by other researchers provided satisfying results

Keywords

content-addressable storage; generalisation (artificial intelligence); learning (artificial intelligence); neural net architecture; neural nets; BAM neural networks; Hopfield networks; autoassociative learning algorithm; bidirectional associative memory neural networks; energy function; learning algorithm; noise; perfect recall; robust; stored patterns; test patterns; Associative memory; Computer networks; Cost function; Current measurement; Magnesium compounds; Matrices; Neural networks; Neurons; Noise robustness; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374339

Filename

374339