Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/3482
Full metadata record
DC FieldValueLanguage
dc.contributor.authorReimers, L-
dc.contributor.authorBOUTEN, Marcus-
dc.contributor.authorVAN ROMPAEY, Bart-
dc.date.accessioned2007-11-28T15:09:47Z-
dc.date.available2007-11-28T15:09:47Z-
dc.date.issued1996-
dc.identifier.citationJOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 29(19). p. 6247-6252-
dc.identifier.issn0305-4470-
dc.identifier.urihttp://hdl.handle.net/1942/3482-
dc.description.abstractPursuing the work of Penney and Sherrington, we determine the optimal continuous-weight perceptron which, on clipping, correctly predicts the largest number of weights for the binary perceptron with maximum stability. We calculate the fraction of correctly predicted binary weights when only the continuous weights stronger than a certain threshold are clipped. We finally carry out simulations for a perceptron with 50 weights to test the practicability of different learning strategies.-
dc.language.isoen-
dc.publisherIOP PUBLISHING LTD-
dc.titleLearning strategy for the binary perceptron-
dc.typeJournal Contribution-
dc.identifier.epage6252-
dc.identifier.issue19-
dc.identifier.spage6247-
dc.identifier.volume29-
local.format.pages6-
dc.description.notesReimers, L, LIMBURGS UNIV CTR,UNIV CAMPUS,B-3590 DIEPENBEEK,BELGIUM.-
local.type.refereedRefereed-
local.type.specifiedArticle-
dc.bibliographicCitation.oldjcatA1-
dc.identifier.doi10.1088/0305-4470/29/19/010-
dc.identifier.isiA1996VL96000010-
item.accessRightsClosed Access-
item.contributorReimers, L-
item.contributorBOUTEN, Marcus-
item.contributorVAN ROMPAEY, Bart-
item.fulltextNo Fulltext-
item.fullcitationReimers, L; BOUTEN, Marcus & VAN ROMPAEY, Bart (1996) Learning strategy for the binary perceptron. In: JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 29(19). p. 6247-6252.-
Appears in Collections:Research publications
Show simple item record

SCOPUSTM   
Citations

5
checked on Sep 2, 2020

WEB OF SCIENCETM
Citations

5
checked on Jul 18, 2024

Page view(s)

90
checked on Nov 7, 2023

Google ScholarTM

Check

Altmetric


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