Action-based neural networks for effective recognition of images

Alexopoulos, Vassilios; Kollias, Stefanos

dc.contributor.author	Alexopoulos, Vassilios	en
dc.contributor.author	Kollias, Stefanos	en
dc.date.accessioned	2014-03-01T02:41:04Z
dc.date.available	2014-03-01T02:41:04Z
dc.date.issued	1995	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30348
dc.subject	Human Information Processing	en
dc.subject	Human Perception	en
dc.subject	Recurrent Neural Network	en
dc.subject	Neural Network	en
dc.subject	Time Varying	en
dc.subject.other	Artificial intelligence	en
dc.subject.other	Computer architecture	en
dc.subject.other	Image analysis	en
dc.subject.other	Learning systems	en
dc.subject.other	Neural networks	en
dc.subject.other	Object recognition	en
dc.subject.other	Sensory perception	en
dc.subject.other	Spurious signal noise	en
dc.subject.other	Time varying systems	en
dc.subject.other	Recurrent neural networks	en
dc.subject.other	Computer vision	en
dc.title	Action-based neural networks for effective recognition of images	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/NNSP.1995.514915	en
heal.identifier.secondary	http://dx.doi.org/10.1109/NNSP.1995.514915	en
heal.publicationDate	1995	en
heal.abstract	This paper presents a novel approach to the recognition of images or scenes, by associating human perception actions to them and introducing neural network architectures that are able to learn the derived representations. The approach, is related to recent research efforts towards a deeper understanding of human information processing and uses appropriate recurrent neural networks for generating the desired associations in time varying environments. Initial results obtained when applying the proposed approach to the problem of recognition of images of objects, that are deformed and/or corrupted by noise, are very encouraging.	en
heal.publisher	IEEE, Piscataway, NJ, United States	en
heal.journalName	Neural Networks for Signal Processing - Proceedings of the IEEE Workshop	en
dc.identifier.doi	10.1109/NNSP.1995.514915	en
dc.identifier.spage	407	en
dc.identifier.epage	416	en