Abstract
In this paper, we propose a modified sequential minimal optimization (SMO) algorithm for the minimal enclosing sphere estimation (MESE) problem. Being one of the key issues of the VC dimension estimation, the MESE problem has a formulation similar to that of support vector machines (SVMs) training. This allows adoption of the ideas of Platt’s SMO algorithm. After careful analysis of the MESE problem, key issues are addressed. Experimental results show the feasibility and effectiveness of the proposed algorithm when applied to SVMs model selection.
This work is supported by the National Natural Science Foundation of China (No. 60072029).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Burges, C.J.: A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery 2, 121–267 (1998)
Chung, K.-M., Kao, W.-C., Sun, T., Wang, L.-L., Lin, C.-J.: Radius Margin Bounds for Support Vector Machines with the RBF Kernel. Neural Computation 11, 2643–2681 (2003)
Chang, C.-C., Lin, C.-J.: LIBSVM: A Library for Support Vector Machines (2002), Online at http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.pdf
Platt, J.: Fast Training of Support Vector Machines Using Sequential Minimal Optimization. In: Scholkopf, B., Burges, C., Smola, A. (eds.) Advances in Kernel Methods: Support Vector Learning, pp. 41–65. MIT Press, Cambridge (1998)
Staelin, C.: Parameter Selection for Support Vector Machines (2003), Online at http://www.hpl.hp.com/techreports/2002/HPL-2002-354R1.pdf
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, H., Wang, S., Qi, F. (2004). Minimal Enclosing Sphere Estimation and Its Application to SVMs Model Selection. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks – ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3173. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28647-9_81
Download citation
DOI: https://doi.org/10.1007/978-3-540-28647-9_81
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22841-7
Online ISBN: 978-3-540-28647-9
eBook Packages: Springer Book Archive