Neural Processing Letters

, Volume 19, Issue 1, pp 63–72

Minimizing the Cross Validation Error to Mix Kernel Matrices of Heterogeneous Biological Data

  • Koji Tsuda
  • Shinsuke Uda
  • Taishin Kin
  • Kiyoshi Asai
Article

DOI: 10.1023/B:NEPL.0000016845.36307.d7

Cite this article as:
Tsuda, K., Uda, S., Kin, T. et al. Neural Processing Letters (2004) 19: 63. doi:10.1023/B:NEPL.0000016845.36307.d7

Abstract

In biological data, it is often the case that objects are described in two or more representations. In order to perform classification based on such data, we have to combine them in a certain way. In the context of kernel machines, this task amounts to mix several kernel matrices into one. In this paper, we present two ways to mix kernel matrices, where the mixing weights are optimized to minimize the cross validation error. In bacteria classification and gene function prediction experiments, our methods significantly outperformed single kernel classifiers in most cases.

bacteria classification bioinformatics kernel machines mixing kernel matrices 

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Koji Tsuda
    • 1
    • 2
  • Shinsuke Uda
    • 1
    • 3
  • Taishin Kin
    • 1
  • Kiyoshi Asai
    • 1
    • 4
  1. 1.AISTComputational Biology Research CenterTokyoJapan. e-mail
  2. 2.Max Planck Institute for Biological CyberneticsTubingenGermany
  3. 3.Department of Computational Intelligence and Systems ScienceTokyo Institute of TechnologyYokohamaJapan
  4. 4.Department of Computational Biology, Graduate School of Frontier ScienceUniversity of TokyoKashiwaJapan

Personalised recommendations