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/1721.1/7180
Full metadata record
DC FieldValueLanguage
dc.creatorSchoelkopf, B.-
dc.creatorSung, K.-
dc.creatorBurges, C.-
dc.creatorGirosi, F.-
dc.creatorNiyogi, P.-
dc.creatorPoggio, T.-
dc.creatorVapnik, V.-
dc.date2004-10-20T20:48:54Z-
dc.date2004-10-20T20:48:54Z-
dc.date1996-12-01-
dc.date.accessioned2013-10-09T02:48:28Z-
dc.date.available2013-10-09T02:48:28Z-
dc.date.issued2013-10-09-
dc.identifierAIM-1599-
dc.identifierCBCL-142-
dc.identifierhttp://hdl.handle.net/1721.1/7180-
dc.identifier.urihttp://koha.mediu.edu.my:8181/xmlui/handle/1721-
dc.descriptionThe Support Vector (SV) machine is a novel type of learning machine, based on statistical learning theory, which contains polynomial classifiers, neural networks, and radial basis function (RBF) networks as special cases. In the RBF case, the SV algorithm automatically determines centers, weights and threshold such as to minimize an upper bound on the expected test error. The present study is devoted to an experimental comparison of these machines with a classical approach, where the centers are determined by $k$--means clustering and the weights are found using error backpropagation. We consider three machines, namely a classical RBF machine, an SV machine with Gaussian kernel, and a hybrid system with the centers determined by the SV method and the weights trained by error backpropagation. Our results show that on the US postal service database of handwritten digits, the SV machine achieves the highest test accuracy, followed by the hybrid approach. The SV approach is thus not only theoretically well--founded, but also superior in a practical application.-
dc.format6 p.-
dc.format2032389 bytes-
dc.format277809 bytes-
dc.formatapplication/postscript-
dc.formatapplication/pdf-
dc.languageen_US-
dc.relationAIM-1599-
dc.relationCBCL-142-
dc.subjectAI-
dc.subjectMIT-
dc.subjectArtificial Intelligence-
dc.subjectradial basis function networks-
dc.subjectsupport vector machines-
dc.subjectpattern recognition-
dc.subjectmachine learning-
dc.subjectVC-dimension-
dc.subjectperformance comparison-
dc.subjectmodel selection-
dc.titleComparing Support Vector Machines with Gaussian Kernels to Radial Basis Function Classifiers-
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.