On the problem of spurious patterns in neural associative memory models

Athithan, G and Dasgupta, C (1997) On the problem of spurious patterns in neural associative memory models. In: IEEE Transactions on Neural Networks, 8 (6). pp. 1483-1491.

PDF On_the_Problem_of_Spurious.pdf - Published Version Restricted to Registered users only Download (244kB) | Request a copy

Abstract

The problem of spurious patterns in neural associative memory models is discussed, Some suggestions to solve this problem from the literature are reviewed and their inadequacies are pointed out, A solution based on the notion of neural self-interaction with a suitably chosen magnitude is presented for the Hebb learning rule. For an optimal learning rule based on linear programming, asymmetric dilution of synaptic connections is presented as another solution to the problem of spurious patterns, With varying percentages of asymmetric dilution it is demonstrated numerically that this optimal learning rule leads to near total suppression of spurious patterns. For practical usage of neural associative memory networks a combination of the two solutions with the optimal learning rule is recommended to be the best proposition.

Item Type:	Journal Article
Publication:	IEEE Transactions on Neural Networks
Publisher:	IEEE
Additional Information:	Copyright 1997 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:	Associative memory;asymmetric dilution;basin of attraction;learning rule;neural network;optimal learning; self-interaction;spurious pattern.
Department/Centre:	Division of Physical & Mathematical Sciences > Physics
Date Deposited:	17 Jun 2011 05:20
Last Modified:	17 Jun 2011 05:20
URI:	http://eprints.iisc.ac.in/id/eprint/38339

Actions (login required)

View Item