Open Access System for Information Sharing

Login Library

 

Article
Cited 4 time in webofscience Cited 3 time in scopus
Metadata Downloads
Full metadata record
Files in This Item:
There are no files associated with this item.
DC FieldValueLanguage
dc.contributor.authorXiong, YS-
dc.contributor.authorKwon, C-
dc.contributor.authorOh, JH-
dc.date.accessioned2016-03-31T13:49:42Z-
dc.date.available2016-03-31T13:49:42Z-
dc.date.created2009-02-28-
dc.date.issued1998-08-28-
dc.identifier.issn0305-4470-
dc.identifier.other1998-OAK-0000000387-
dc.identifier.urihttps://oasis.postech.ac.kr/handle/2014.oak/20661-
dc.description.abstractWe study a fully-connected parity machine with K hidden units for continuous weights. The geometrical structure of the weight space of this model is analysed in terms of the volumes associated with the internal representations of the training set. By examining the asymptotic behaviour of order parameters in the large K limit, we find the maximum number ru,, the storage capacity, of patterns per input unit to be K In K/ln2 up to leading order, which saturates the mathematical bound given by Mitchison and Durbin. Unlike the committee machine, the storage capacity per weight remains unchanged compared with the corresponding tree-like architecture.-
dc.description.statementofresponsibilityX-
dc.languageEnglish-
dc.publisherIOP PUBLISHING LTD-
dc.relation.isPartOfJOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL-
dc.subjectMULTILAYER NEURAL NETWORKS-
dc.subjectINTERNAL REPRESENTATIONS-
dc.subjectSTATISTICAL-MECHANICS-
dc.subjectCOMMITTEE-MACHINES-
dc.subjectSPACE STRUCTURE-
dc.titleStorage capacity of a fully-connected parity machine with continuous weights-
dc.typeArticle-
dc.contributor.college기술경영 대학원 과정-
dc.identifier.doi10.1088/0305-4470/31/34/007-
dc.author.googleXIONG, YS-
dc.author.googleKWON, C-
dc.author.googleOH, JH-
dc.relation.volume31-
dc.relation.issue34-
dc.relation.startpage7043-
dc.relation.lastpage7049-
dc.contributor.id10110134-
dc.relation.journalJOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL-
dc.relation.indexSCI급, SCOPUS 등재논문-
dc.relation.sciSCI-
dc.collections.nameJournal Papers-
dc.type.rimsART-
dc.identifier.bibliographicCitationJOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, v.31, no.34, pp.7043 - 7049-
dc.identifier.wosid000075770300007-
dc.date.tcdate2019-01-01-
dc.citation.endPage7049-
dc.citation.number34-
dc.citation.startPage7043-
dc.citation.titleJOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL-
dc.citation.volume31-
dc.contributor.affiliatedAuthorOh, JH-
dc.identifier.scopusid2-s2.0-0038931151-
dc.description.journalClass1-
dc.description.journalClass1-
dc.description.wostc4-
dc.type.docTypeArticle-
dc.subject.keywordPlusMULTILAYER NEURAL NETWORKS-
dc.subject.keywordPlusINTERNAL REPRESENTATIONS-
dc.subject.keywordPlusSTATISTICAL-MECHANICS-
dc.subject.keywordPlusCOMMITTEE-MACHINES-
dc.subject.keywordPlusSPACE STRUCTURE-
dc.relation.journalWebOfScienceCategoryPhysics, Multidisciplinary-
dc.relation.journalWebOfScienceCategoryPhysics, Mathematical-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.relation.journalResearchAreaPhysics-

qr_code

  • mendeley

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

Related Researcher

Researcher

오종훈OH, JONG HOON
Grad Program for Tech Innovation & Mgmt
Read more

Views & Downloads

Browse