Show simple item record

dc.contributor.authorCalcraft, L.
dc.contributor.authorAdams, R.G.
dc.contributor.authorDavey, N.
dc.date.accessioned2011-10-26T14:01:07Z
dc.date.available2011-10-26T14:01:07Z
dc.date.issued2006
dc.identifier.citationCalcraft , L , Adams , R G & Davey , N 2006 , Gaussian and Exponential Architectures in Small-World Associative Memories . in Procs of the European Symposium on Artificial Neural Networks, ESANN'06 . pp. 617-622 , 2006 European Symposium on Artificial Neural Networks, ESANN '06 , Bruges , Belgium , 26/04/06 .
dc.identifier.citationconference
dc.identifier.isbn2-930307-06-4
dc.identifier.otherPURE: 430974
dc.identifier.otherPURE UUID: b8b4bd8b-52bc-439a-82f3-80041587fbf6
dc.identifier.otherdspace: 2299/2237
dc.identifier.otherScopus: 78650724683
dc.identifier.urihttp://hdl.handle.net/2299/6803
dc.description.abstractThe performance of sparsely-connected associative memory models built from a set of perceptrons is investigated using different patterns of connectivity. Architectures based on Gaussian and exponential distributions are compared to networks created by progressively rewiring a locally-connected network. It is found that while all three architectures are capable of good pattern-completion performance, the Gaussian and exponential architectures require a significantly lower mean wiring length to achieve the same results. In the case of networks of low connectivity, relatively tight Gaussian and exponential distributions achieve the best overall performance.en
dc.language.isoeng
dc.relation.ispartofProcs of the European Symposium on Artificial Neural Networks, ESANN'06
dc.titleGaussian and Exponential Architectures in Small-World Associative Memoriesen
dc.contributor.institutionScience & Technology Research Institute
dc.contributor.institutionSchool of Computer Science
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