Multiple Kernel Feature Fusion Using Kernel Fisher Method

Abstract:

Different from the existing multiple kernel methods which mainly work in implicit kernel space, we propose a novel multiple kernel method in empirical kernel mapping space. In empirical kernel mapping space, the combination of kernels can be treated as the weighted fusion of empirical kernel mapping samples. Based this fact, we developed a multiple kernel Fisher method to realize multiple kernel classification in empirical kernel mapping space. The experiments here illustrate that the proposed multiple kernel fisher method is feasible and effective.

• Periodical: Applied Mechanics and Materials (Volumes 333-335)
• Pages: 1406-1409
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.333-335.1406
• Online since: July 2013
• Authors: Bo Yang
• Keywords: Empirical Kernel Mapping, Kernel Feature Fusion, Kernel Fisher Analysis, Multiple Kernel Learning

References

[1] O. Chapelle, V. Vapnik, Choosing multiple parameters for support vector machines, Machine Learning. 46 (2002) 131-159.

[2] M. Momma, A pattern search method for model selection of support vector regression, In Proceedings of the Second SIAM International Conference on Data Mining. (2002) 261-274.

DOI: 10.1137/1.9781611972726.16

[3] K.P. Bennett, MARK: A boosting algorithm for heterogeneous kernel models, In SIGKDD. (2002) 24-31.

[4] F. Bach: Multiple kernel learning, conic duality, and the SMO algorithm, In Proceedings of the 21st International Conference on Machine Learning. (2004).

DOI: 10.1145/1015330.1015424

[5] S. Sonnenburg, A general and efficient multiple kernel learning algorithm, In Neural Information Processing Systems. (2005).

[6] G. Rätsch, Large scale multiple kernel learning, Journal of Machine Learning Research. (2006).

[7] S.J. Kim, A. Magnani, S. Boyd, Optimal Kernel Selection in Kernel Fisher Discriminant, Proceedings of the 23rd International Conference on Machine Learning. (2006) 465-472.

DOI: 10.1145/1143844.1143903

[8] B. Scholkopf, Input space versus feature space in kernel based methods, IEEE Trans On Neural Networks. 10 (1999) 1000-1017.

DOI: 10.1109/72.788641

[9] D.J. Newman, UCI from http: /www. ics. uci. edu/~mlearn/MLRepository. html.

[10] I. Tsang, A. Kocsor, J. Kwok, Efficient Kernel Feature Extraction for Massive Data Sets, In International Conference on Knowledge Discovery and Data Mining. (2006).

DOI: 10.1145/1150402.1150494