Rectified Gaussian Distributions and the Formation of Local Filters From Video Data

Título

dc.contributor.author	Corchado Rodríguez, Emilio Santiago
dc.contributor.author	Charles, Darryl
dc.contributor.author	Fyfe, Colin
dc.date.accessioned	2017-09-06T09:16:41Z
dc.date.available	2017-09-06T09:16:41Z
dc.date.issued	2001-04
dc.identifier.citation	ESANN'2001 proceedings - European Symposium on Artificial Neural Networks. pp. 397-402.
dc.identifier.isbn	2-930307-01-3
dc.identifier.uri	https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2001-33.pdf
dc.identifier.uri	http://hdl.handle.net/10366/135115
dc.description.abstract	We investigate the use of an unsupervised artificial neural network to form a sparse representation of the underlying causes in a data set. By using fixed lateral connections that are derived from the Rectified Generalised Gaussian distribution, we form a network that is capable of identifying multiple cause structure in visual data and grouping similar causes together on the output response of the network. We show that the network may be used to form local spatiotemporal filters in response to real images contained in video data.
dc.format.mimetype	application/pdf
dc.language.iso	en
dc.publisher	D-Facto public.
dc.rights	Attribution-NonCommercial-NoDerivs 3.0 Unported
dc.rights.uri	https://creativecommons.org/licenses/by-nc-nd/3.0/
dc.subject	Computer Science
dc.title	Rectified Gaussian Distributions and the Formation of Local Filters From Video Data
dc.type	info:eu-repo/semantics/conferenceObject
dc.rights.accessRights	info:eu-repo/semantics/openAccess