High capacity associative memory based on the random neural network model

Likas, A; Stafylopatis, A

dc.contributor.author	Likas, A	en
dc.contributor.author	Stafylopatis, A	en
dc.date.accessioned	2014-03-01T01:11:59Z
dc.date.available	2014-03-01T01:11:59Z
dc.date.issued	1996	en
dc.identifier.issn	0218-0014	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/11904
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-0342832251&partnerID=40&md5=e5312b31a738638578016808e70e7742	en
dc.relation.uri	http://www.informatik.uni-trier.de/~ley/db/journals/ijprai/ijprai10.html#LikasS96	en
dc.subject	Associative memory	en
dc.subject	Hebbian learning	en
dc.subject	Neural computation	en
dc.subject	Random neural network	en
dc.subject	Spectral learning	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.other	THRESHOLD FUNCTIONS	en
dc.subject.other	QUEUING-NETWORKS	en
dc.subject.other	CUSTOMERS	en
dc.title	High capacity associative memory based on the random neural network model	en
heal.type	journalArticle	en
heal.language	English	en
heal.publicationDate	1996	en
heal.abstract	In this paper the Bipolar Random Network is described, which constitutes an extension of the Random Neural Network model and exhibits autoassociative memory capabilities. This model is characterized by the existence of positive and negative nodes and symmetrical behavior of positive and negative signals circulating in the network. The network's ability of acting as autoassociative memory is examined and several techniques are developed concerning storage and reconstruction of patterns. These approaches are either based on properties of the network or constitute adaptations of existing neural network techniques. The performance of the network under the proposed schemes has been investigated through experiments showing very good storage and reconstruction capabilities. Moreover, the scheme exhibiting the best behavior seems to outperform other well-known associative neural network models, achieving capacities that exceed 0.5n where n is the size of the network.	en
heal.publisher	WORLD SCIENTIFIC PUBL CO PTE LTD	en
heal.journalName	International Journal of Pattern Recognition and Artificial Intelligence	en
dc.identifier.isi	ISI:A1996WW14300003	en
dc.identifier.volume	10	en
dc.identifier.issue	8	en
dc.identifier.spage	919	en
dc.identifier.epage	937	en