On An Optimal Learning Scheme For Bidirectional Associative Memories

Shanmukh, K and Venkatesh, YV (1993) On An Optimal Learning Scheme For Bidirectional Associative Memories. In: Proceedings of 1993 International Joint Conference on Neural Networks (IJCNN '93-Nagoya), 25-29 October, 1993, Japan, vol.3,2670-2673.

Preview

PDF optimal.pdf Download (267kB)

Abstract

An optimal learning scheme is proposed for a class of Bidirectional Associative Memories(BAM's). This scheme based on Perceptron Learning Algorithems, is motivated by the inadequacies/incompleteness of the weighted learning by global optimization as derived by wang et al[l]. It is shown that the new scheme has superior properties. [1]Convergence to correct solution, when it exits; [2]A larger basin of attraction for the given set of patterns.

Item Type:	Conference Paper
Publisher:	IEEE
Additional Information:	©1993 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Keywords:	optimal learning;bidirectional associative memories;perceptron learning algorithems
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	30 Jun 2004
Last Modified:	19 Sep 2010 04:13
URI:	http://eprints.iisc.ac.in/id/eprint/465

Actions (login required)

View Item