Header logo is ei

The connection between regularization operators and support vector kernels.




n this paper a correspondence is derived between regularization operators used in regularization networks and support vector kernels. We prove that the Green‘s Functions associated with regularization operators are suitable support vector kernels with equivalent regularization properties. Moreover, the paper provides an analysis of currently used support vector kernels in the view of regularization theory and corresponding operators associated with the classes of both polynomial kernels and translation invariant kernels. The latter are also analyzed on periodical domains. As a by-product we show that a large number of radial basis functions, namely conditionally positive definite functions, may be used as support vector kernels.

Author(s): Smola, AJ. and Schölkopf, B. and Müller, K-R.
Journal: Neural Networks
Volume: 11
Number (issue): 4
Pages: 637-649
Year: 1998
Month: June
Day: 0

Department(s): Empirical Inference
Bibtex Type: Article (article)

Digital: 0
DOI: 10.1016/S0893-6080(98)00032-X
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF


  title = {The connection between regularization operators and support vector kernels.},
  author = {Smola, AJ. and Sch{\"o}lkopf, B. and M{\"u}ller, K-R.},
  journal = {Neural Networks},
  volume = {11},
  number = {4},
  pages = {637-649},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = jun,
  year = {1998},
  month_numeric = {6}