Glassy behavior in neural network models of associative memory

Dasgupta, Chandan (2002) Glassy behavior in neural network models of associative memory Physica A: Statistical Mechanics and its Applications, 315 (1-2). pp. 137-149. ISSN 0378-4371

Full text not available from this repository.

Official URL: http://dx.doi.org//10.1016/S0378-4371(02)01246-3

Related URL: http://dx.doi.org/10.1016/S0378-4371(02)01246-3

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.

Item Type:Article
Source:Copyright of this article belongs to Elsevier Science.
Keywords:Neural Networks; Associative Memory; Hopfield Model; Spurious Attractors; Synaptic Asymmetry
ID Code:22882
Deposited On:25 Nov 2010 13:54
Last Modified:25 Nov 2010 13:54

Repository Staff Only: item control page