A Hybrid Neural Optimization Scheme Based on Parallel Updates

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	2014-03-01T01:45:29Z
dc.date.available	2014-03-01T01:45:29Z
dc.date.issued	1997	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/24592
dc.subject	boltzmann machine	en
dc.subject	Discrete Optimization	en
dc.subject	Parallel Implementation	en
dc.subject	Input Output	en
dc.subject	Neural Network Model	en
dc.title	A Hybrid Neural Optimization Scheme Based on Parallel Updates	en
heal.type	journalArticle	en
heal.publicationDate	1997	en
heal.abstract	A synchronous Hopfield--type neural network model containing units with analog inputand binary output, which is suitable for parallel implementation, is examined inthe context of solving discrete optimization problems. A hybrid parallel update schemeconcerning the stochastic input-output behaviour of each unit is presented. This parallelupdate scheme maintains the solution quality of the Boltzmann Machine optimizer, whichis inherently sequential. Experimental results on	en