Improved exploration in Hopfield network state-space through parameter perturbation driven by simulated annealing

dc.contributor.authorPapageorgiou, G.en
dc.contributor.authorLikas, A.en
dc.contributor.authorStafylopatis, A.en
dc.date.accessioned2015-11-24T17:03:02Z
dc.date.available2015-11-24T17:03:02Z
dc.identifier.issn0377-2217-
dc.identifier.urihttps://olympias.lib.uoi.gr/jspui/handle/123456789/11125
dc.rightsDefault Licence-
dc.subjectdiscrete optimizationen
dc.subjectneural networksen
dc.subjectsimulated annealingen
dc.subjecthopfield networken
dc.subjectboltzmann machineen
dc.subjectoptimizationen
dc.subjectcomputationen
dc.titleImproved exploration in Hopfield network state-space through parameter perturbation driven by simulated annealingen
heal.abstractAn approach is presented for treating discrete optimization problems mapped on the architecture of the Hopfield neural network. The method constitutes a modification to the local minima escape (LME) algorithm which has been recently proposed as a method that uses perturbations in the network's parameter space in order to escape from local minimum states of the Hopfield network. Our approach (LMESA) adopts this perturbation mechanism but, in addition, introduces randomness in the selection of the next local minimum state to be visited in a manner analogous with the case of Simulated Annealing (SA). Experimental results using instances of the Weighted Maximum Independent Set (MIS) problem indicate that the proposed method leads to significant improvement over the conventional LME approach in terms of quality of the obtained solutions, while requirin\cr &g a comparable amount of computational effort. (C) 1998 Elsevier Science B.V.en
heal.accesscampus-
heal.fullTextAvailabilityTRUE-
heal.journalNameEuropean Journal of Operational Researchen
heal.journalTypepeer reviewed-
heal.languageen-
heal.publicationDate1998-
heal.recordProviderΠανεπιστήμιο Ιωαννίνων. Σχολή Θετικών Επιστημών. Τμήμα Μηχανικών Ηλεκτρονικών Υπολογιστών και Πληροφορικήςel
heal.typejournalArticle-
heal.type.elΆρθρο Περιοδικούel
heal.type.enJournal articleen

Αρχεία

Φάκελος/Πακέτο αδειών

Προβολή: 1 - 1 of 1
Φόρτωση...
Μικρογραφία εικόνας
Ονομα:
license.txt
Μέγεθος:
1.74 KB
Μορφότυπο:
Item-specific license agreed upon to submission
Περιγραφή: