Loading...
Please wait, while we are loading the content...
Similar Documents
Scale-sensitive Ψ-dimensions: the Capacity Measures for Classifiers Taking Values in R Q
| Content Provider | CiteSeerX |
|---|---|
| Author | Guermeur, Yann |
| Abstract | Abstract. Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such “VC dimensions ” exist for models taking values in {0, 1}, {1,..., Q} and R. We introduce the generalizations appropriate for the missing case, the one of models with values in R Q. This provides us with a new guaranteed risk for M-SVMs which appears superior to the existing one. Keywords: Large margin classifiers, Generalized VC dimensions, M-SVMs. hal-00156914, version 1- 25 Jun 2007 |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Capacity Measure Statistical Learning Theory Generalized Vc Dimension Crucial Role New Guaranteed Risk Classifier Taking Value Large Margin Classifier Vc Dimension Missing Case Scale-sensitive Dimension |
| Content Type | Text |
| Resource Type | Article |
