Extensions of a Theory of Networks for Approximation and Learning: Dimensionality Reduction and Clustering

dc.creator	Poggio, Tomaso
dc.creator	Girosi, Federico
dc.date	2004-10-04T14:35:52Z
dc.date	2004-10-04T14:35:52Z
dc.date	1990-04-01
dc.date.accessioned	2013-10-09T02:42:25Z
dc.date.available	2013-10-09T02:42:25Z
dc.date.issued	2013-10-09
dc.identifier	AIM-1167
dc.identifier	http://hdl.handle.net/1721.1/6014
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	The theory developed in Poggio and Girosi (1989) shows the equivalence between regularization and a class of three-layer networks that we call regularization networks or Hyper Basis Functions. These networks are also closely related to the classical Radial Basis Functions used for interpolation tasks and to several pattern recognition and neural network algorithms. In this note, we extend the theory by defining a general form of these networks with two sets of modifiable parameters in addition to the coefficients $c_\\ alpha$: moving centers and adjustable norm- weight.
dc.format	18 p.
dc.format	2271885 bytes
dc.format	901116 bytes
dc.format	application/postscript
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-1167
dc.subject	learning networks
dc.subject	regularization
dc.title	Extensions of a Theory of Networks for Approximation and Learning: Dimensionality Reduction and Clustering

Files in this item

Files	Size	Format	View
There are no files associated with this item.