Optimal Unsupervised Learning in Feedforward Neural Networks

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6976

Full metadata record

DC Field	Value	Language
dc.creator	Sanger, Terence D.	-
dc.date	2004-10-20T20:11:57Z	-
dc.date	2004-10-20T20:11:57Z	-
dc.date	1989-01-01	-
dc.date.accessioned	2013-10-09T02:48:00Z	-
dc.date.available	2013-10-09T02:48:00Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AITR-1086	-
dc.identifier	http://hdl.handle.net/1721.1/6976	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	We investigate the properties of feedforward neural networks trained with Hebbian learning algorithms. A new unsupervised algorithm is proposed which produces statistically uncorrelated outputs. The algorithm causes the weights of the network to converge to the eigenvectors of the input correlation with largest eigenvalues. The algorithm is closely related to the technique of Self-supervised Backpropagation, as well as other algorithms for unsupervised learning. Applications of the algorithm to texture processing, image coding, and stereo depth edge detection are given. We show that the algorithm can lead to the development of filters qualitatively similar to those found in primate visual cortex.	-
dc.format	8663770 bytes	-
dc.format	6747778 bytes	-
dc.format	application/postscript	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AITR-1086	-
dc.title	Optimal Unsupervised Learning in Feedforward Neural Networks	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI