Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/3493
Full metadata record
DC FieldValueLanguage
dc.contributor.authorREIMANN, Peter-
dc.contributor.authorVAN DEN BROECK, Christian-
dc.contributor.authorBEX, Geert Jan-
dc.date.accessioned2007-11-28T15:36:01Z-
dc.date.available2007-11-28T15:36:01Z-
dc.date.issued1996-
dc.identifier.citationJOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 29(13). p. 3521-3535-
dc.identifier.issn0305-4470-
dc.identifier.urihttp://hdl.handle.net/1942/3493-
dc.description.abstractWe consider random patterns on the N-sphere which are uniformly distributed with the exception of a single symmetry-breaking orientation, along which they are Gaussian distributed. The unsupervised recognition of this orientation by different learning rules is studied in the large-N limit using the replica method. The model is simple enough to be analytically tractable and rich enough to exhibit most of the phenomena observed with other pattern distributions. A learning algorithm based on the minimization of a cost function is identified which reaches the upper theoretical limit imposed by the optimal (Bayes-) learning scenario. An implementation of this algorithm is proposed and tested numerically.-
dc.language.isoen-
dc.publisherIOP PUBLISHING LTD-
dc.titleA Gaussian scenario for unsupervised learning-
dc.typeJournal Contribution-
dc.identifier.epage3535-
dc.identifier.issue13-
dc.identifier.spage3521-
dc.identifier.volume29-
local.format.pages15-
dc.description.notesLIMBURGS UNIV CENTRUM,B-3590 DIEPENBEEK,BELGIUM.Reimann, P, LORAND EOTVOS UNIV,PUSKIN U 5-7,H-1088 BUDAPEST,HUNGARY.-
local.type.refereedRefereed-
local.type.specifiedArticle-
dc.bibliographicCitation.oldjcatA1-
dc.identifier.doi10.1088/0305-4470/29/13/021-
dc.identifier.isiA1996UX09000021-
item.fulltextNo Fulltext-
item.accessRightsClosed Access-
item.fullcitationREIMANN, Peter; VAN DEN BROECK, Christian & BEX, Geert Jan (1996) A Gaussian scenario for unsupervised learning. In: JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 29(13). p. 3521-3535.-
item.contributorREIMANN, Peter-
item.contributorBEX, Geert Jan-
item.contributorVAN DEN BROECK, Christian-
Appears in Collections:Research publications
Show simple item record

SCOPUSTM   
Citations

26
checked on Sep 2, 2020

WEB OF SCIENCETM
Citations

22
checked on Jun 29, 2022

Page view(s)

52
checked on Jul 2, 2022

Google ScholarTM

Check

Altmetric


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