1. DSpace at MEDIU
  2. Harvested articles مقالات مستوردة من مؤسسات وجامعات عالمية
  3. MIT Items
Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/7169
Full metadata record
DC FieldValueLanguage
dc.creatorEvgeniou, Theodoros-
dc.creatorPontil, Massimiliano-
dc.date2004-10-20T20:48:37Z-
dc.date2004-10-20T20:48:37Z-
dc.date2000-05-01-
dc.date.accessioned2013-10-09T02:48:25Z-
dc.date.available2013-10-09T02:48:25Z-
dc.date.issued2013-10-09-
dc.identifierAIM-1681-
dc.identifierCBCL-184-
dc.identifierhttp://hdl.handle.net/1721.1/7169-
dc.identifier.urihttp://koha.mediu.edu.my:8181/xmlui/handle/1721-
dc.descriptionWe present distribution independent bounds on the generalization misclassification performance of a family of kernel classifiers with margin. Support Vector Machine classifiers (SVM) stem out of this class of machines. The bounds are derived through computations of the $V_gamma$ dimension of a family of loss functions where the SVM one belongs to. Bounds that use functions of margin distributions (i.e. functions of the slack variables of SVM) are derived.-
dc.format9 p.-
dc.format1149066 bytes-
dc.format253797 bytes-
dc.formatapplication/postscript-
dc.formatapplication/pdf-
dc.languageen_US-
dc.relationAIM-1681-
dc.relationCBCL-184-
dc.subjectAI-
dc.subjectMIT-
dc.subjectArtificial Intelligence-
dc.subjectmissing data-
dc.subjectmixture models-
dc.subjectstatistical learning-
dc.subjectEM algorithm-
dc.subjectneural networks-
dc.subjectkernel classifiers-
dc.subjectSupport Vector Machine-
dc.subjectregularization networks-
dc.subjectstatistical learning theory-
dc.subjectV-gamma dimension.-
dc.titleA Note on the Generalization Performance of Kernel Classifiers with Margin-
Appears in Collections:MIT Items

Files in This Item:
There are no files associated with this item.
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.