A Note on the Generalization Performance of Kernel Classifiers with Margin
| dc.date.accessioned | 2004-10-20T20:48:37Z | |
| dc.date.accessioned | 2018-11-24T10:23:10Z | |
| dc.date.available | 2004-10-20T20:48:37Z | |
| dc.date.available | 2018-11-24T10:23:10Z | |
| dc.date.issued | 2000-05-01 | en_US |
| dc.identifier.uri | http://hdl.handle.net/1721.1/7169 | |
| dc.identifier.uri | http://repository.aust.edu.ng/xmlui/handle/1721.1/7169 | |
| dc.description.abstract | We 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. | en_US |
| dc.format.extent | 9 p. | en_US |
| dc.format.extent | 1149066 bytes | |
| dc.format.extent | 253797 bytes | |
| dc.language.iso | en_US | |
| dc.subject | AI | en_US |
| dc.subject | MIT | en_US |
| dc.subject | Artificial Intelligence | en_US |
| dc.subject | missing data | en_US |
| dc.subject | mixture models | en_US |
| dc.subject | statistical learning | en_US |
| dc.subject | EM algorithm | en_US |
| dc.subject | neural networks | en_US |
| dc.subject | kernel classifiers | en_US |
| dc.subject | Support Vector Machine | en_US |
| dc.subject | regularization networks | en_US |
| dc.subject | statistical learning theory | en_US |
| dc.subject | V-gamma dimension. | en_US |
| dc.title | A Note on the Generalization Performance of Kernel Classifiers with Margin | en_US |
Files in this item
| Files | Size | Format | View |
|---|---|---|---|
| AIM-1681.pdf | 253.7Kb | application/pdf | View/ |
| AIM-1681.ps | 1.149Mb | application/postscript | View/ |