Show simple item record

dc.contributor.authorTurvey, S.P.
dc.contributor.authorHunt, S.
dc.contributor.authorDavey, N.
dc.contributor.authorFrank, R.
dc.contributor.editorLotfi, A.
dc.contributor.editorGaribaldi, J.M.
dc.date.accessioned2009-10-20T08:49:05Z
dc.date.available2009-10-20T08:49:05Z
dc.date.issued2004
dc.identifier.citationTurvey , S P , Hunt , S , Davey , N & Frank , R 2004 , High Performance Associative Memories and Structured Weight Dilution . in A Lotfi & J M Garibaldi (eds) , Applications and Science in Soft Computing - Advances in Intelligent and Soft Computing , Vol. 24 . Springer , pp. 23-30 .
dc.identifier.isbn978-3-540-40856-7
dc.identifier.otherPURE: 85959
dc.identifier.otherPURE UUID: f3e1e9cc-0c8e-45a0-8a26-3fc03b33427f
dc.identifier.otherdspace: 2299/3973
dc.identifier.urihttp://hdl.handle.net/2299/3973
dc.descriptionCopyright Springer
dc.description.abstractThe consequences of two techniques for symmetrically diluting the weights of the standard Hopfield architecture associative memory model, trained using a non-Hebbian learning rule, are examined. This paper reports experimental investigations into the effect of dilution on factors such as: pattern stability and attractor performance. It is concluded that these networks maintain a reasonable level of performance at fairly high dilution rates.en
dc.language.isoeng
dc.publisherSpringer
dc.relation.ispartofApplications and Science in Soft Computing - Advances in Intelligent and Soft Computing , Vol. 24
dc.subjectHopfield Networks
dc.subjectBasins of Attraction
dc.titleHigh Performance Associative Memories and Structured Weight Dilutionen
dc.contributor.institutionSchool of Computer Science
dc.contributor.institutionScience & Technology Research Institute
rioxxterms.typeOther
herts.preservation.rarelyaccessedtrue


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record