Neural Processing Letters

, Volume 15, Issue 1, pp 59–67 | Cite as

Conformal Transformation of Kernel Functions: A Data-Dependent Way to Improve Support Vector Machine Classifiers

  • Si Wu
  • Shun-Ichi Amari

Abstract

In this paper we extend the conformal method of modifying a kernel function to improve the performance of Support Vector Machine classifiers [14, 15]. The kernel function is conformally transformed in a data-dependent way by using the information of Support Vectors obtained in primary training. We further investigate the performances of modified Gaussian Radial Basis Function and Polynomial kernels. Simulation results for two artificial data sets show that the method is very effective, especially for correcting bad kernels.

kernel function pattern recognition Riemannian geometry and conformal transformation support vector machine 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Boser, B., Guyon, I. and Vapnik, V.: A training algorithm for optimal margin classifiers. Fifth Annual Workshop on Computational Learning Theory. New York: ACM Press.Google Scholar
  2. 2.
    Cortes, C. and Vapnik, V.: Support Vector Networks, Machine Learning, 20 (1995), 273–297.MATHGoogle Scholar
  3. 3.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer.Google Scholar
  4. 4.
    Aizerman, M. A., Braverman, E. M. and Rozonoer, L. I.: Theoretical foundations of the potential function method in pattern recognition learning. Automation and Remote Control, 25 (1964), 821–837.MathSciNetGoogle Scholar
  5. 5.
    Schölkopf, B., Sung, K., Burges, C. J. C., Girosi, F., Niyogi, P., Poggio, T. and Vapnik, V.: Comparing Support Vector Machines with Gaussian kernels to Radial Basis Function classifiers. IEEE Trans. Signal Processing, 45 (1997), 2758–2765.CrossRefGoogle Scholar
  6. 6.
    Smola, A. J., Schölkopf, B. and Müller, K. R.: The connection between regularization operators and support vector kernels. Neural Network, 11 (1998), 637–649.CrossRefGoogle Scholar
  7. 7.
    Girosi, F.: An equivalence between sparse approximation and support vector machines. Neural Computation, 20 (1998), 1455–1480.CrossRefGoogle Scholar
  8. 8.
    Williams, C. K. I.: Prediction with Gaussian process: From linear regression to linear prediction and beyond. In M. I. Jordan (ed.) Learning in Graphical Models. Kluwer, 1997.Google Scholar
  9. 9.
    Sollich, P.: Probabilistic methods for Support Vector Machines. Advances in Neural Information Systems 12, pp. 349–355, MIT Press, 2000.Google Scholar
  10. 10.
    Seeger, M.: Bayesian model selection for Support Vector machines, Gaussian processes and other kernel classifiers. Advances in Neural Information Systems 12, pp. 603–609, MIT Press, 2000.Google Scholar
  11. 11.
    Opper, M. and Winther, O.: Gaussian process classification and SVM mean field results and Leave-One-Out estimator. In A. J. Smola, P. Bartlett, B. Schölkopf and D. Schuurmans (eds) Advances in Large Margin Classifiers, pp. 43–56. Cambridge, MA, 2000.Google Scholar
  12. 12.
    Schölkopf, B., Simard, P., Smola, A. and Vapnik, V.: Prior knowledge in support vector kernels. Advances in Neural Information Processing Systems 10, MIT Press, 1998.Google Scholar
  13. 13.
    Burges, C. J. C.: Geometry and Invariance in Kernel Based Method. In B. Schölkopf, C. J. C. Burges and A. J. Smola (eds), Advances in Kernel Methods, pp. 89–116, MIT Press, 1999.Google Scholar
  14. 14.
    Amari, S. and Wu, S.: Improving Support Vector machine classifiers by modifying kernel functions. Neural Networks, 12 (1999), 783–789.CrossRefGoogle Scholar
  15. 15.
    Amari, S. and Wu, S.: An information-geometrical method for improving the performance of Support Vector machine classifiers. ICANN99, pp. 85–90, 1999.Google Scholar
  16. 16.
    Burges, C. J. C.: A tutorial on Support Vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2 (1998), 121–167.CrossRefGoogle Scholar
  17. 17.
    Smola, A. J. and Schölkopf, B.: A tutorial on Support Vector regression. Neuro COLT Technical Report TR-1998–030, 1998.Google Scholar
  18. 18.
    Cristanini, N. and Shawe-Tayor, J.: An Introduction to Support Vector Machines and Other Kernel Based Methods. Cambridge Univ. Press, 2000.Google Scholar

Copyright information

© Kluwer Academic Publishers 2002

Authors and Affiliations

  • Si Wu
    • 1
  • Shun-Ichi Amari
    • 1
  1. 1.RIKEN Brain Science Institute, tHirosawa 2-1, Wako-shiSaitamaJapan
  2. 2.Department of Computer ScienceSheffield UniversityUK)

Personalised recommendations