Show simple item record

dc.contributor.authorDavey, N.
dc.contributor.authorAdams, R.G.
dc.contributor.authorHunt, S.
dc.date.accessioned2011-11-21T15:01:08Z
dc.date.available2011-11-21T15:01:08Z
dc.date.issued2001
dc.identifier.citationDavey , N , Adams , R G & Hunt , S 2001 , High performance associative memory models and weight dilution . in Procs of Int Conf on Neural Information Processing : ICONIP'01 . vol. 2 , pp. 597-602 .
dc.identifier.otherPURE: 455208
dc.identifier.otherPURE UUID: 57faea69-222d-4004-8309-5b53c690ebe7
dc.identifier.otherdspace: 2299/824
dc.identifier.urihttp://hdl.handle.net/2299/7048
dc.description.abstractThe consequences of diluting the weights of the standard Hopfield architecture associative memory model, trained using perceptron like learning rules, is examined. A proportion of the weights of the network are removed; this can be done in a symmetric and asymmetric way and both methods are investigated. This paper reports experimental investigations into the consequences of dilution in terms of: capacity, training times and size of basins of attraction. It is concluded that these networks maintain a reasonable performance at fairly high dilution rates.en
dc.language.isoeng
dc.relation.ispartofProcs of Int Conf on Neural Information Processing
dc.titleHigh performance associative memory models and weight dilutionen
dc.contributor.institutionSchool of Computer Science
dc.contributor.institutionScience & Technology Research Institute
dc.contributor.institutionCentre for Computer Science and Informatics Research
rioxxterms.versionAM
rioxxterms.typeOther
herts.preservation.rarelyaccessedtrue


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record