Asymmetric kernel method and its application to Fisher's discriminant

Authors:
Naoya Koide;Yukihiko Yamashita
Affiliations:
Tokyo Institute of Technology, Graduate School of Science and Engineering, Japan;Tokyo Institute of Technology, Graduate School of Science and Engineering, Japan
Venue:
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
Year:
2006

Citing 0
Cited 1

Learning a Robust Relevance Model for Search Using Kernel Methods

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose the asymmetric kernel method. Furthermore, we apply it to Fisher's discriminant and provide an kernel Fisher's discriminant with variable kernel parameters. We also provide the experimental result of the existing and the new kernel Fisher's discriminants by using several standard datasets and show the advantage of our method.