Glassy behavior in neural network models of associative memory

Dasgupta, Chandan (2002) Glassy behavior in neural network models of associative memory. In: Physica A: Statistical Mechanics and its Applications, 315 (1-2). pp. 137-149.

PDF Glassy_behavior_in_neural.pdf - Published Version Restricted to Registered users only Download (134kB) | Request a copy

Abstract

Neural network models of associative memory exhibit a large number of spurious attractors of the network dynamics which are not correlated with any memory state. These spurious attractors, analogous to "glassy" local minima of the energy or free energy of a system of particles, degrade the performance of the network by trapping trajectories starting from states that are not close to one of the memory states. Different methods for reducing the adverse effects of spurious attractors are examined with emphasis on the role of synaptic asymmetry. (C) 2002 Elsevier Science B.V. All rights reserved.

Item Type:	Journal Article
Publication:	Physica A: Statistical Mechanics and its Applications
Publisher:	Elsevier Science
Additional Information:	Copyright of this article belongs to Elsevier Science.
Keywords:	Neural networks;Associative memory;Hop:eld model;Spurious attractors;Synaptic asymmetry
Department/Centre:	Division of Physical & Mathematical Sciences > Physics
Date Deposited:	19 Jul 2011 05:15
Last Modified:	19 Jul 2011 05:15
URI:	http://eprints.iisc.ac.in/id/eprint/39222

Actions (login required)

View Item