Statistical Mechanics of Support Vector Networks

@inproceedings{Dietrich1999StatisticalMO,
  title={Statistical Mechanics of Support Vector Networks},
  author={Rainer Dietrich and Manfred Opper and Haim Sompolinsky},
  year={1999}
}
Using methods of statistical physics, we investigate the generalization performance of support vector machines (SVMs), which have been recently introduced as a general alternative to neural networks. For nonlinear classification rules, the generalization error saturates on a plateau when the number o examples is too small to properly estimate the coefficients of the nonlinear part. When trained on simple rules, we find that SVMs overfit only weakly. The performance of SVMs is strongly enhanced… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-10 of 28 extracted citations

References

Publications referenced by this paper.
Showing 1-7 of 7 references

A 31

  • H. Yoon, J. H. Oh, J. Phys
  • 7771
  • 1998
1 Excerpt

Phys

  • M. Opper, D. Haussler
  • Rev. Lett. 75, 3772 (1995); Europhys. Lett. 37…
  • 1997

inPhysics of Neural Networks I,edited

  • R. Kühn, J. L. van Hemmen
  • 1996
1 Excerpt

inPhysics of Neural Networks III

  • M. Opper, W. Kinzel
  • edited by J. L. van Hemmen, E. Domany, and K…
  • 1996
1 Excerpt

Mach

  • C. Cortes, V. Vapnik
  • Learn. 20, 273–297
  • 1995
1 Excerpt

Rev

  • T.L.H. Watkin, A. Rau, M. Biehl
  • Mod. Phys. 65, 499
  • 1993

Electron

  • T. Cover, IEEE Trans
  • Comput. 14, 326
  • 1965

Similar Papers

Loading similar papers…