Disappearance of Spurious States in Analog Associative Memories

Abstract

We show that symmetric n-mixture states, when they exist, are almost never stable in autoassociative networks with threshold-linear units. Only with a binary coding scheme we could find a limited region of the parameter space in which either 2-mixtures or 3-mixtures are stable attractors of the dynamics.

5 pages, 3 figures, accepted for publication in Phys Rev E

Cited by in corpus (4)

• An associative network with spatially organized connectivity
• Localized activity profiles and storage capacity of rate-based autoassociative networks
• Efficiency of local learning rules in threshold-linear associative networks
• Encoding binary neural codes in networks of threshold-linear neurons