QUALITY AND EFFICIENCY OF RETRIEVAL FOR WILLSHAW-LIKE AUTOASSOCIATIVENETWORKS .2. RECOGNITION

Authors
FROLOV A KARTASHOV A GOLTSEV A FOLK R
Citation
A. Frolov et al., QUALITY AND EFFICIENCY OF RETRIEVAL FOR WILLSHAW-LIKE AUTOASSOCIATIVENETWORKS .2. RECOGNITION, Network, 6(4), 1995, pp. 535-549
Citations number
14
Categorie Soggetti
Mathematical Methods, Biology & Medicine",Neurosciences,"Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence
Journal title
Network → ACNP
ISSN journal
0954898X
Volume
6
Issue
4
Year of publication
1995
Pages
535 - 549
Database
ISI
SICI code
0954-898X(1995)6:4<535:QAEORF>2.0.ZU;2-H
Abstract
We study the recognition properties of a modification of the Willshaw associative memory with a Boating threshold analytically for the asymp totic case of large networks and single-step retrieval. The number of spurious stable states and the size of their attraction basins are cal culated. Comparison is made with simulations for single- and multistep dynamics. The appropriateness of the recognition procedure based on t he remanent overlap is demonstrated.