A STUDY OF NEURAL NETWORK APPLICATIONS TO SIGNAL-PROCESSING

KOLLIAS, S

dc.contributor.author	KOLLIAS, S	en
dc.date.accessioned	2014-03-01T01:07:47Z
dc.date.available	2014-03-01T01:07:47Z
dc.date.issued	1990	en
dc.identifier.issn	0302-9743	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/10167
dc.subject	Associative Memory	en
dc.subject	backpropagation	en
dc.subject	Digital Image	en
dc.subject	Event Detection	en
dc.subject	Learning Algorithm	en
dc.subject	Neural Network Application	en
dc.subject	Optimization Problem	en
dc.subject	Signal and Image Processing	en
dc.subject	Signal Processing	en
dc.subject	Simulated Annealing	en
dc.subject	Neural Network	en
dc.subject.classification	Computer Science, Theory & Methods	en
dc.title	A STUDY OF NEURAL NETWORK APPLICATIONS TO SIGNAL-PROCESSING	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/3-540-52255-7_44	en
heal.identifier.secondary	http://dx.doi.org/10.1007/3-540-52255-7_44	en
heal.language	English	en
heal.publicationDate	1990	en
heal.abstract	This paper examines the use of two characteristic neural network architectures to signal and image processing applications. Digital image halftoning and seismic event detection are treated as optimization problems, to which symmetric Hopfield-type networks with near-neighbor-connections provide efficient solutions. A solution to the halftoning problem, provided by simulated annealing, is also examined and compared to the neural network one. Feedforward	en
heal.publisher	SPRINGER VERLAG	en
heal.journalName	LECTURE NOTES IN COMPUTER SCIENCE	en
dc.identifier.doi	10.1007/3-540-52255-7_44	en
dc.identifier.isi	ISI:A1990CX06600021	en
dc.identifier.volume	412	en
dc.identifier.spage	233	en
dc.identifier.epage	242	en