The Kernel Trick for Distances

Schölkopf, B

Local TagsRelease HistoryDetailsSummary

The Kernel Trick for Distances

Schölkopf, B.(2000). The Kernel Trick for Distances (MSR-TR-2000-51). Redmond, WA, USA: Microsoft Research, Microsoft Corporation.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-E5E6-6 Version Permalink: https://hdl.handle.net/21.11116/0000-0005-B6F9-5

Genre: Report

Files

show Files

hide Files

:

tr-2000-51_1839.pdf (Any fulltext), 443KB

View Save

File Permalink:
https://hdl.handle.net/21.11116/0000-0005-B6FA-4

Name:
tr-2000-51_1839.pdf

Description:
-

OA-Status:

Visibility:
Public

MIME-Type / Checksum:
application/pdf / [MD5]

Technical Metadata:

View

Copyright Date:
-

Copyright Info:
-

License:
-

Locators

show

Creators

show

hide

Creators:
Schölkopf, B¹, Author

Affiliations:
1External Organizations, ou_persistent22

Content

show

hide

Free keywords: -

Abstract: A method is described which, like the kernel trick in support vector machines (SVMs), lets us generalize distance-based algorithms to operate
in feature spaces, usually nonlinearly related to the input space. This is done by identifying a class of kernels which can be represented as normbased distances in Hilbert spaces. It turns out that common kernel algorithms,
such as SVMs and kernel PCA, are actually really distance based
algorithms and can be run with that class of kernels, too.
As well as providing a useful new insight into how these algorithms
work, the present work can form the basis for conceiving new algorithms.

Details

show

hide

Language(s):

Dates: Date issued: 2000-05

Publication Status: Issued

Pages: 9

Publishing info: Redmond, WA, USA : Microsoft Research, Microsoft Corporation

Table of Contents: -

Rev. Type: -

Identifiers: Report Nr.: MSR-TR-2000-51
BibTex Citekey: 1839

Degree: -

Event

show

Legal Case

show

Project information

show

Source

show