Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/2965
Full metadata record
DC FieldValueLanguage
dc.contributor.authorVAN DEN BROECK, Christian-
dc.contributor.authorCopelli, M-
dc.contributor.authorOpper, M-
dc.date.accessioned2007-11-23T08:44:52Z-
dc.date.available2007-11-23T08:44:52Z-
dc.date.issued1999-
dc.identifier.citationJOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 32(50). p. L555-L560-
dc.identifier.issn0305-4470-
dc.identifier.urihttp://hdl.handle.net/1942/2965-
dc.description.abstractWe study a simple model of unsupervised learning where the single symmetry breaking vector has binary components +/-1. We calculate exactly the Bayes-optimal performance of an estimator which is required to lie in the same discrete space. We also show that, except for very special cases, such an estimator cannot be obtained by minimization of a class of variationally optimal potentials.-
dc.language.isoen-
dc.publisherIOP PUBLISHING LTD-
dc.titleBayes-optimal performance in a discrete space-
dc.typeJournal Contribution-
dc.identifier.epageL560-
dc.identifier.issue50-
dc.identifier.spageL555-
dc.identifier.volume32-
local.format.pages6-
dc.description.notesLimburgs Univ Ctr, B-3590 Diepenbeek, Belgium. Aston Univ, Neural Comp Res Grp, Birmingham B4 7ET, W Midlands, England.Copelli, M, Limburgs Univ Ctr, Univ Campus, B-3590 Diepenbeek, Belgium.-
local.type.refereedRefereed-
local.type.specifiedLetter-
dc.bibliographicCitation.oldjcatA1-
dc.identifier.isi000084444100004-
item.fullcitationVAN DEN BROECK, Christian; Copelli, M & Opper, M (1999) Bayes-optimal performance in a discrete space. In: JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 32(50). p. L555-L560.-
item.validationecoom 2001-
item.fulltextNo Fulltext-
item.accessRightsClosed Access-
item.contributorVAN DEN BROECK, Christian-
item.contributorCopelli, M-
item.contributorOpper, M-
Appears in Collections:Research publications
Show simple item record

WEB OF SCIENCETM
Citations

3
checked on May 18, 2024

Page view(s)

76
checked on Nov 7, 2023

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.