A kernel approach for learning from almost orthogonal patterns

Schölkopf, B; Weston, J; Eskin , E; Leslie, C; Noble, WS

doi:10.1007/3-540-36755-1_44

Local TagsRelease HistoryDetailsSummary

A kernel approach for learning from almost orthogonal patterns

Schölkopf, B., Weston, J., Eskin, E., Leslie, C., & Noble, W. (2002). A kernel approach for learning from almost orthogonal patterns. In T. Elomaa, H. Mannila, & H. Toivonen (Eds.), Machine Learning: ECML 2002: 13th European Conference on Machine Learning Helsinki, Finland, August 19–23, 2002 (pp. 511-528). Berlin, Germany: Springer.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-E0E3-9 Version Permalink: https://hdl.handle.net/21.11116/0000-0005-8D4E-6

Genre: Conference Paper

Files

show Files

Locators

show

hide

Locator:
https://link.springer.com/content/pdf/10.1007%2F3-540-36755-1_44.pdf (Publisher version) Open Access status unknown

Description:
-

OA-Status:

Creators

show

hide

Creators:
Schölkopf, B^{1, 2}, Author
Weston, J^{1, 2}, Author
Eskin , E, Author
Leslie, C, Author
Noble, WS, Author

Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794

Content

show

hide

Free keywords: -

Abstract: In kernel methods, all the information about the training data is contained in the Gram matrix. If this matrix has large diagonal values, which arises for many types of kernels, then kernel methods do not perform well. We propose and test several methods for dealing with this problem by reducing the dynamic range of the matrix while preserving the positive definiteness of the Hessian of the quadratic programming problem that one has to solve when training a Support Vector Machine.

Details

show

hide

Language(s):

Dates: Date issued: 2002-08

Publication Status: Issued

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: BibTex Citekey: 1770
DOI: 10.1007/3-540-36755-1_44

Degree: -

Event

show

hide

Title: 13th European Conference on Machine Learning (ECML 2002)

Place of Event: Helsinki, Finland

Start-/End Date: 2002-08-19 - 2002-08-23

Legal Case

show

Project information

show

Source 1

show

hide

Title: Machine Learning: ECML 2002: 13th European Conference on Machine Learning Helsinki, Finland, August 19–23, 2002

Source Genre: Proceedings

Creator(s):
Elomaa, T, Editor
Mannila, H, Editor
Toivonen, H, Editor

Affiliations:
-

Publ. Info: Berlin, Germany : Springer

Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 511 - 528 Identifier: ISBN: 978-3-540-44036-9

Source 2

show

hide

Title: Lecture Notes in Computer Science

Source Genre: Series

Creator(s):

Affiliations:

Publ. Info: -

Pages: - Volume / Issue: 2430 Sequence Number: - Start / End Page: - Identifier: -