English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Asymptotically optimal choice of varepsilon-loss for support vector machines

Smola, A., Murata, N., Schölkopf, B., & Müller, K.-R. (1998). Asymptotically optimal choice of varepsilon-loss for support vector machines. In L. Niklasson, M. Boden, & T. Ziemke (Eds.), ICANN 98: 8th International Conference on Artificial Neural Networks, Skövde, Sweden, 2–4 September 1998 (pp. 105-110). Berlin, Germany: Springer.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Smola, AJ, Author
Murata, N, Author
Schölkopf, B, Author              
Müller, K-R1, Author              
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Under the assumption of asymptotically unbiased estimators we show that there exists a nontrivial choice of the insensitivity parameter in Vapnik’s ε-insensitive loss function which scales linearly with the input noise of the training data. This finding is backed by experimental results.

Details

show
hide
Language(s):
 Dates: 1998-09
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 800
DOI: 10.1007/978-1-4471-1599-1_11
 Degree: -

Event

show
hide
Title: 8th International Conference on Artificial Neural Networks (ICANN 1998)
Place of Event: Skövde, Sweden
Start-/End Date: 1998-09-02 - 1998-09-04

Legal Case

show

Project information

show

Source 1

show
hide
Title: ICANN 98: 8th International Conference on Artificial Neural Networks, Skövde, Sweden, 2–4 September 1998
Source Genre: Proceedings
 Creator(s):
Niklasson, L, Editor
Boden, M, Editor
Ziemke, T, Editor
Affiliations:
-
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 105 - 110 Identifier: -

Source 2

show
hide
Title: Perspectives in Neural Computing
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -