dc.contributor.author | Davey, N. | |
dc.contributor.author | Hunt, S. | |
dc.date.accessioned | 2008-02-05T12:13:21Z | |
dc.date.available | 2008-02-05T12:13:21Z | |
dc.date.issued | 1999 | |
dc.identifier.citation | Davey , N & Hunt , S 1999 , ' The capacity and attractor basins of associative memory models ' , Lecture Notes in Computer Science (LNCS) , vol. 1606 , pp. 330-339 . https://doi.org/10.1007/BFb0098189 | |
dc.identifier.issn | 0302-9743 | |
dc.identifier.other | dspace: 2299/1564 | |
dc.identifier.uri | http://hdl.handle.net/2299/1564 | |
dc.description | The original publication is available at www.springerlink.com . Copyright Springer | |
dc.description.abstract | The performance characteristics of five variants of the Hopfield network are examined. Two performance metrics are used: memory capacity, and a measure of the size of basins of attraction. We find that the posttraining adjustment of processor thresholds has, at best, little or no effect on performance, and at worst a significant negative effect. The adoption of a local learning rule can, however, give rise to significant performance gains. | en |
dc.format.extent | 41285 | |
dc.language.iso | eng | |
dc.relation.ispartof | Lecture Notes in Computer Science (LNCS) | |
dc.title | The capacity and attractor basins of associative memory models | en |
dc.contributor.institution | School of Computer Science | |
dc.contributor.institution | Science & Technology Research Institute | |
dc.description.status | Peer reviewed | |
rioxxterms.versionofrecord | 10.1007/BFb0098189 | |
rioxxterms.type | Journal Article/Review | |
herts.preservation.rarelyaccessed | true | |