PICTORIAL INFORMATION-RETRIEVAL USING THE RANDOM NEURAL NETWORK

STAFYLOPATIS, A; LIKAS, A

dc.contributor.author	STAFYLOPATIS, A	en
dc.contributor.author	LIKAS, A	en
dc.date.accessioned	2014-03-01T01:09:00Z
dc.date.available	2014-03-01T01:09:00Z
dc.date.issued	1992	en
dc.identifier.issn	0098-5589	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/10786
dc.subject	ASSOCIATIVE MEMORY	en
dc.subject	HEBBIAN LEARNING	en
dc.subject	INFORMATION RETRIEVAL	en
dc.subject	NEURAL COMPUTATION	en
dc.subject	PICTORIAL INFORMATION SYSTEMS	en
dc.subject	RANDOM NEURAL NETWORK	en
dc.subject.classification	Computer Science, Software Engineering	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.other	VISUAL LANGUAGE COMPILER	en
dc.subject.other	THRESHOLD FUNCTIONS	en
dc.subject.other	CAPACITY	en
dc.subject.other	SYSTEM	en
dc.title	PICTORIAL INFORMATION-RETRIEVAL USING THE RANDOM NEURAL NETWORK	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/32.148477	en
heal.identifier.secondary	http://dx.doi.org/10.1109/32.148477	en
heal.language	English	en
heal.publicationDate	1992	en
heal.abstract	A technique is developed based on the use of a neural network model for performing information retrieval in a pictorial information system. The neural network provides autoassociative memory operation and allows the retrieval of stored symbolic images using erroneous or incomplete information as input. The network used is based on an adaptation of the random neural network model featuring positive and negative nodes and symmetrical behavior of positive and negative signals. The network architecture considered here has hierarchical structure and allows two level operation during learning and recall. An experimental software prototype, including an efficient graphical interface, has been implemented and tested. The performance of the system has been investigated through experiments under several schemes concerning storage and reconstruction of patterns. These schemes are either based on properties of the random network or constitute adaptations of known neural network techniques.	en
heal.publisher	IEEE COMPUTER SOC	en
heal.journalName	IEEE TRANSACTIONS ON SOFTWARE ENGINEERING	en
dc.identifier.doi	10.1109/32.148477	en
dc.identifier.isi	ISI:A1992JE24400005	en
dc.identifier.volume	18	en
dc.identifier.issue	7	en
dc.identifier.spage	590	en
dc.identifier.epage	600	en