Abstract
Majority voting in classifier combination treats all base classifiers equally without considering their performance differences. By analyzing the constraints imposed by the margins of an ensemble classifier, a set of weights can be computed to give better prediction than the majority voting. We propose a regularized classifier combination strategy that maximize the entropy of probability weights assigned to base classifiers subjected to the margin constraints of the ensemble classifier. Furthermore, we show that a sparse solution with a set of support vectors for ensemble classifier can be obtained.
| Original language | English |
|---|---|
| Title of host publication | 2008 International Conference on Wavelet Analysis and Pattern Recognition |
| Publisher | IEEE Canada |
| Pages | 378-383 |
| Number of pages | 6 |
| Volume | 1 |
| ISBN (Print) | 9781424422395 |
| DOIs | |
| Publication status | Published - 31 Aug 2008 |
| Event | International Conference on Wavelet Analysis and Pattern Recognition 2008 - , Hong Kong Duration: 30 Aug 2008 → 31 Aug 2008 https://ieeexplore.ieee.org/xpl/conhome/4629503/proceeding (Conference proceedings) |
Publication series
| Name | International Conference on Wavelet Analysis and Pattern Recognition |
|---|---|
| Publisher | IEEE |
| ISSN (Print) | 2158-5695 |
| ISSN (Electronic) | 2158-5709 |
Conference
| Conference | International Conference on Wavelet Analysis and Pattern Recognition 2008 |
|---|---|
| Country/Territory | Hong Kong |
| Period | 30/08/08 → 31/08/08 |
| Internet address |
|
User-Defined Keywords
- Pattern recognition
- Wavelet analysis
- Conferences