Fast Support Vector Machine Classification of Very Large Datasets

@inproceedings{Fehr2007FastSV,
  title={Fast Support Vector Machine Classification of Very Large Datasets},
  author={Janis Fehr and Karina Zapien Arreola and Hans Burkhardt},
  booktitle={GfKl},
  year={2007}
}
In many classification applications, Support Vector Machin es (SVMs) have proven to be high performing and easy to handle classifiers with very go od generalization abilities. However, one drawback of the SVM is its rather high cla ssification complexity which scales linearly with the number of Support Vectors (SV ). This is due to the fact that for the classification of one sample one has to evaluate t he Kernel-Function with all SVs. To speed up classification, several different appro aches… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-9 of 9 references

BREDENSTEINER, Duality and Geometry in SVM Classifiers

  • E.J.K.P. BENNETT
  • Proc. 17th International Conf. on Machine…
  • 2000
Highly Influential
8 Excerpts

BURKHARDT, Fast Support Vector Machine Classification of very large Datasets

  • K. ZAPIEN, H. J. FEHR
  • Technical Report 2/2007,
  • 2007
Highly Influential
9 Excerpts

HULL, A database for handwritten text recognition research

  • J J.
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1994
Highly Influential
3 Excerpts

BURKHARDT, Fast Support Vector Machine Classification using linear SVMs, in Proceedings: ICPR

  • K. ZAPIEN, H. J. FEHR
  • 2006
Highly Influential
3 Excerpts

SMOLA, Learning with Kernels

  • A. B. SCHOELKOPF
  • 2002
2 Excerpts

MANGASARIAN, RSVM: Reduced Support Vector Machines

  • Y LEEO.
  • Proceedings of the first SIAM International…
  • 2001
3 Excerpts

KLEINBERG, Building projectable classifiers of arbitrary complexity

  • K HOE.M.T.
  • Proceedings of the 13th International Conference…
  • 1996

Similar Papers

Loading similar papers…