Learning the kernel parameters in kernel minimum distance classifier

Choosing appropriate values for kernel parameters is one of the key problems in many kernel-based methods because the values of these parameters have significant impact on the performances of these methods. In this paper, a novel approach is proposed to learn the kernel parameters in kernel minimum distance (KMD) classifier, where the values of the kernel parameters are computed through optimizing an objective function designed for measuring the classification reliability of KMD. Experiments on both artificial and real-world datasets show that the proposed approach works well on learning kernel parameters of KMD.

• Type: Journal
• Year: 2006
• Where: PR
• Authors: Daoqiang Zhang, Songcan Chen, Zhi-Hua Zhou
• Keywords: Appropriate Values, Kernel Minimum Distance, Kernel Parameters, PR 2006