Gaussian Process Classiication and Svm: Mean Field Results and Leave-one-out Estimator

  title={Gaussian Process Classiication and Svm: Mean Field Results and Leave-one-out Estimator},
  author={Manfred Opper and Ole Winther},
In this chapter, we elaborate on the well-known relationship between Gaussian Processes (GP) and Support Vector Machines (SVM). Secondly, we present approximate solutions for two computational problems arising in GP and SVM. The rst one is the calculation of the posterior mean for GP classiiers using a `naive' mean eld approach. The second one is a leave-one-out estimator for the generalization error of SVM based on a linear response method. Simulation results on a benchmark dataset show… CONTINUE READING
18 Extracted Citations
8 Extracted References
Similar Papers

Citing Papers

Publications influenced by this paper.
Showing 1-10 of 18 extracted citations

Referenced Papers

Publications referenced by this paper.
Showing 1-8 of 8 references

Gaussian Processes for Classi cation

  • M. Opper, O. Winther
  • sub- mitted to Neural Computation
  • 1999
Highly Influential
9 Excerpts

Computing with In nite Networks

  • C.K.I. Williams
  • Neural Infor- mation Processing Systems 9, M. C…
  • 1997
1 Excerpt

Support Vector Machines

  • C. Cortes, V. N. Vapnik
  • Machine Learn- ing 20, 1-25
  • 1995
1 Excerpt

The AdaTron: An Adaptive Perceptron Algorithm

  • J. K. Anlauf, M. Biehl
  • Europhys. Lett. 10, 687
  • 1989
2 Excerpts

Similar Papers

Loading similar papers…