Loading...
Please wait, while we are loading the content...
Similar Documents
Multi-Task Feature and Kernel Selection for SVMs (2004)
| Content Provider | CiteSeerX |
|---|---|
| Author | Jebara, Tony |
| Abstract | We compute a common feature selection or kernel selection configuration for multiple support vector machines (SVMs) trained on different yet inter-related datasets. The method is advantageous when multiple classification tasks and differently labeled datasets exist over a common input space. Different datasets can mutually reinforce a common choice of representation or relevant features for their various classifiers. We derive a multi-task representation learning approach using the maximum entropy discrimination formalism. The resulting convex algorithms maintain the global solution properties of support vector machines. However, in addition to multiple SVM classification/regression parameters they also jointly estimate an optimal subset of features or optimal combination of kernels. Experiments are shown on standardized datasets. 1. |
| File Format | |
| Publisher Date | 2004-01-01 |
| Publisher Institution | Proc. 21st Int’l Conf. Machine Learning |
| Access Restriction | Open |
| Subject Keyword | Global Solution Property Standardized Datasets Multiple Support Vector Machine Common Feature Selection Multiple Classification Task Common Input Space Different Datasets Convex Algorithm Support Vector Machine Optimal Subset Kernel Selection Optimal Combination Maximum Entropy Discrimination Formalism Multi-task Representation Svm Classification Regression Parameter Multi-task Feature Selection Configuration Inter-related Datasets Various Classifier Common Choice Relevant Feature |
| Content Type | Text |
