Extensions of a Theory of Networks for Approximation and Learning: Outliers and Negative Examples

dc.creator	Girosi, Federico
dc.creator	Poggio, Tomaso
dc.creator	Caprile, Bruno
dc.date	2004-10-04T15:14:46Z
dc.date	2004-10-04T15:14:46Z
dc.date	1990-07-01
dc.date.accessioned	2013-10-09T02:45:55Z
dc.date.available	2013-10-09T02:45:55Z
dc.date.issued	2013-10-09
dc.identifier	AIM-1220
dc.identifier	http://hdl.handle.net/1721.1/6530
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	Learning an input-output mapping from a set of examples can be regarded as synthesizing an approximation of a multi-dimensional function. From this point of view, this form of learning is closely related to regularization theory. In this note, we extend the theory by introducing ways of dealing with two aspects of learning: learning in the presence of unreliable examples and learning from positive and negative examples. The first extension corresponds to dealing with outliers among the sparse data. The second one corresponds to exploiting information about points or regions in the range of the function that are forbidden.
dc.format	3388253 bytes
dc.format	1212626 bytes
dc.format	application/postscript
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-1220
dc.title	Extensions of a Theory of Networks for Approximation and Learning: Outliers and Negative Examples

Files in this item

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