Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
10
pubmed:dateCreated
2004-4-19
pubmed:abstractText
Networks of coupled periodic oscillators (similar to the Kuramoto model) have been proposed as models of associative memory. However, error-free retrieval states of such oscillatory networks are typically unstable, resulting in a near zero capacity. This puts the networks at disadvantage as compared with the classical Hopfield network. Here we propose a simple remedy for this undesirable property and show rigorously that the error-free capacity of our oscillatory, associative-memory networks can be made as high as that of the Hopfield network. They can thus not only provide insights into the origin of biological memory, but can also be potentially useful for applications in information science and engineering.
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:status
MEDLINE
pubmed:month
Mar
pubmed:issn
0031-9007
pubmed:author
pubmed:issnType
Print
pubmed:day
12
pubmed:volume
92
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
108101
pubmed:dateRevised
2006-11-15
pubmed:meshHeading
pubmed:year
2004
pubmed:articleTitle
Capacity of oscillatory associative-memory networks with error-free retrieval.
pubmed:affiliation
Department of Mathematics, Center for Systems Science and Engineering Research, Arizona State University, Tempe, Arizona 85287, USA. tnishi@chaos6.la.asu.edu
pubmed:publicationType
Journal Article, Research Support, U.S. Gov't, Non-P.H.S.