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

Papageorgiou, G; Likas, A; Stafylopatis, A

dc.contributor.author	Papageorgiou, G	en
dc.contributor.author	Likas, A	en
dc.contributor.author	Stafylopatis, A	en
dc.date.accessioned	2014-03-01T01:13:50Z
dc.date.available	2014-03-01T01:13:50Z
dc.date.issued	1998	en
dc.identifier.issn	0377-2217	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/12735
dc.subject	Boltzmann machine	en
dc.subject	Discrete optimization	en
dc.subject	Hopfield network	en
dc.subject	Neural networks	en
dc.subject	Simulated annealing	en
dc.subject.classification	Management	en
dc.subject.classification	Operations Research & Management Science	en
dc.subject.other	OPTIMIZATION	en
dc.subject.other	COMPUTATION	en
dc.title	Improved exploration in Hopfield network state-space through parameter perturbation driven by simulated annealing	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/S0377-2217(97)00375-5	en
heal.identifier.secondary	http://dx.doi.org/10.1016/S0377-2217(97)00375-5	en
heal.language	English	en
heal.publicationDate	1998	en
heal.abstract	An 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.publisher	ELSEVIER SCIENCE BV	en
heal.journalName	European Journal of Operational Research	en
dc.identifier.doi	10.1016/S0377-2217(97)00375-5	en
dc.identifier.isi	ISI:000074232900004	en
dc.identifier.volume	108	en
dc.identifier.issue	2	en
dc.identifier.spage	283	en
dc.identifier.epage	292	en