Show simple item record

Multi-Class Learning: Simplex Coding And Relaxation Error

dc.date.accessioned2011-09-27T20:30:07Z
dc.date.accessioned2018-11-26T22:26:43Z
dc.date.available2011-09-27T20:30:07Z
dc.date.available2018-11-26T22:26:43Z
dc.date.issued2011-09-27
dc.identifier.urihttp://hdl.handle.net/1721.1/66085
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/66085
dc.description.abstractWe study multi-category classification in the framework of computational learning theory. We show how a relaxation approach, which is commonly used in binary classification, can be generalized to the multi-class setting. We propose a vector coding, namely the simplex coding, that allows to introduce a new notion of multi-class margin and cast multi-category classification into a vector valued regression problem. The analysis of the relaxation error be quantified and the binary case is recovered as a special case of our theory. From a computational point of view we can show that using the simplex coding we can design regularized learning algorithms for multi-category classification that can be trained at a complexity which is independent to the number of classes.en_US
dc.format.extent3 p.en_US
dc.subjectcomputational learningen_US
dc.subjectmachine learningen_US
dc.subjectconvex relaxationen_US
dc.titleMulti-Class Learning: Simplex Coding And Relaxation Erroren_US


Files in this item

FilesSizeFormatView
MIT-CSAIL-TR-2011-043.pdf214.8Kbapplication/pdfView/Open

This item appears in the following Collection(s)

Show simple item record