A Bayesian Kernel Logistic Discriminant Model: An Improvement to the Kernel Fisher's Discriminant
Abstract
The Kernel Fisher's Discriminant (KFD) has proven to be competitive to several state-of-the-art classifiers. However, it is assuming equal covariance structure for all transformed classes, which is not true in many applications. In this paper, we propose a novel Bayesian Kernel Logistic Discriminant model (BKLD) which goes one step further by representing each transformed class by its own covariance matrix. This can perform better than the KFD. An extensive comparison of the BKLD to the KFD and to other state-of-the-art non-linear classifiers is performed.
Cite
Text
Ksantini et al. "A Bayesian Kernel Logistic Discriminant Model: An Improvement to the Kernel Fisher's Discriminant." AAAI Conference on Artificial Intelligence, 2008.Markdown
[Ksantini et al. "A Bayesian Kernel Logistic Discriminant Model: An Improvement to the Kernel Fisher's Discriminant." AAAI Conference on Artificial Intelligence, 2008.](https://mlanthology.org/aaai/2008/ksantini2008aaai-bayesian/)BibTeX
@inproceedings{ksantini2008aaai-bayesian,
title = {{A Bayesian Kernel Logistic Discriminant Model: An Improvement to the Kernel Fisher's Discriminant}},
author = {Ksantini, Riadh and Ziou, Djemel and Colin, Bernard and Dubeau, François},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2008},
pages = {1464-1465},
url = {https://mlanthology.org/aaai/2008/ksantini2008aaai-bayesian/}
}