The Path Kernel: A Novel Kernel for Sequential Data

  • Andrea Baisero
  • Florian T. Pokorny
  • Danica Kragic
  • Carl Henrik Ek
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 318)

Abstract

We define a novel kernel function for finite sequences of arbitrary length which we call the path kernel. We evaluate this kernel in a classification scenario using synthetic data sequences and show that our kernel can outperform state of the art sequential similarity measures. Furthermore, we find that, in our experiments, a clustering of data based on the path kernel results in much improved interpretability of such clusters compared to alternative approaches such as dynamic time warping or the global alignment kernel.

Keywords

Kernels Sequences 

References

  1. 1.
    Bahlmann, C., Haasdonk, B., Burkhardt, H.: Online handwriting recognition with support vector machines—a kernel approach. In: 8th International Workshop on  Frontiers in Handwriting Recognition, pp. 49–54 (2002)Google Scholar
  2. 2.
    Berlinet, A., Thomas-Agnan, C.: Reproducing Kernel Hilbert Spaces in Probability and Statistics. Kluwer, Dordrecht (2004)CrossRefMATHGoogle Scholar
  3. 3.
    Buhmann, M.D., Martin, D.: Radial Basis Functions: Theory and Implementations. Cambridge University Press, Cambridge (2003)CrossRefGoogle Scholar
  4. 4.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines (2001)Google Scholar
  5. 5.
    Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines: and Other Kernel-Based Learning Methods. Cambridge University Press, Cambridge (2006)Google Scholar
  6. 6.
    Cuturi, M.: Fast global alignment kernels. In: Proceedings of the International Conference on Machine Learning (2010)Google Scholar
  7. 7.
    Cuturi, M., Vert, J.P., Birkenes, O., Matsui, T.: A kernel for time series based  on global alignments. In: IEEE International Conference on Acoustics, Speech and Signal Processing,  pp. II-413–II-416 (2007)Google Scholar
  8. 8.
    Gudmundsson, S., Runarsson, T.P., Sigurdsson, S.: Support vector machines and dynamic time warping for time series. In: Proceedings of the IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence) (x), pp. 2772–2776 (2008). http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4634188
  9. 9.
    Haasdonk, B.: Feature space interpretation of SVMs with indefinite kernels. IEEE Trans. Pattern Anal. Mach. Intell. 27(4), 482–492 (2005)CrossRefGoogle Scholar
  10. 10.
    Haasdonk, B., Burkhardt, H.: Invariant kernel functions for pattern analysis and machine learning. Mach. Learn. 68(1), 35–61 (2007)CrossRefGoogle Scholar
  11. 11.
    Haussler, D.: Convolution kernels on discrete structures. Tech. Rep. (1999)Google Scholar
  12. 12.
    Leslie, C., Kuang, R.: Fast string kernels using inexact matching for protein sequences. J. Mach. Learn. Res. 5, 1435–1455 (2004)MathSciNetMATHGoogle Scholar
  13. 13.
    Li, M., Zhu, Y.: Image classification via LZ78 based string kernel: a comparative study. Advances in Knowledge Discovery and Data Mining. Springer, Berlin (2006)Google Scholar
  14. 14.
    Lodhi, H., Saunders, C., Shawe-Taylor, J., Cristianini, N., Watkins, C.: Text classification using string kernels. J. Mach. Learn. Res. 2, 419–444 (2002)MATHGoogle Scholar
  15. 15.
    Luo, G., Bergström, N., Ek, C.H., Kragic, D.: Representing actions with  kernels. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2028–2035  (2011)Google Scholar
  16. 16.
    Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoust. Speech Signal Process. 26(1), 43–49 (1978)CrossRefMATHGoogle Scholar
  17. 17.
    Saunders, C., Tschach, H., Shawe-Taylor, J.: Syllables and other string  kernel extensions. In: Proceedings of the Nineteenth International Conference on Machine Learning (ICML’02) (2002)Google Scholar
  18. 18.
    Sivic, J., Zisserman, A.: Efficient visual search of videos cast as text retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 31(4), 591–606 (2009)CrossRefGoogle Scholar
  19. 19.
    Watkins, C.: Dynamic alignment kernels. In: Proceedings of the Advances in Neural Information Processing Systems (1999)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Andrea Baisero
    • 1
  • Florian T. Pokorny
    • 1
  • Danica Kragic
    • 1
  • Carl Henrik Ek
    • 1
  1. 1.Computer Vision and Active Perception Laboratory, Centre for Autonomous SystemsKTH Royal Institute of TechnologyStockholmSweden

Personalised recommendations