Show simple item record

dc.contributor.authorCalcraft, L.
dc.contributor.authorAdams, R.G.
dc.contributor.authorDavey, N.
dc.date.accessioned2009-10-14T13:14:09Z
dc.date.available2009-10-14T13:14:09Z
dc.date.issued2009
dc.identifier.citationCalcraft , L , Adams , R G & Davey , N 2009 , Connection strategy and performance in sparsely connected 2D associative memory models with non-random images . in In: Proceedings of ESANN 2009 . vol. 17 , pp. 397-402 .
dc.identifier.otherdspace: 2299/3957
dc.identifier.urihttp://hdl.handle.net/2299/3957
dc.descriptionOriginal paper can be found at: http://www.dice.ucl.ac.be/esann/proceedings/papers.php?ann=2009
dc.description.abstractA sparsely connected associative memory model is tested with different pattern sets, and it is found that pattern recall is highly dependent on the type of patterns used. Performance is also found to depend critically on the connection strategy used to build the networks. Comparisons of topology reveal that connectivity matrices based on Gaussian distributions perform well for all pattern types tested, and that for best pattern recall at low wiring costs, the optimal value of Gaussian used in creating the connection matrix is dependent on properties of the pattern set.en
dc.format.extent96804
dc.language.isoeng
dc.relation.ispartofIn: Proceedings of ESANN 2009
dc.titleConnection strategy and performance in sparsely connected 2D associative memory models with non-random imagesen
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