English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Healing the Relevance Vector Machine through Augmentation

Rasmussen, C., & Candela, J. (2005). Healing the Relevance Vector Machine through Augmentation. In S. Dzeroski, L. de Raedt, & S. Wrobel (Eds.), ICML '05: 22nd international conference on Machine learning (pp. 689-696). New York, NY, USA: ACM Press.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-D6D9-C Version Permalink: http://hdl.handle.net/21.11116/0000-0005-0E0C-0
Genre: Conference Paper

Files

show Files
hide Files
:
pdf3460.pdf (Any fulltext), 380KB
Name:
pdf3460.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Rasmussen, CE1, 2, Author              
Candela, JQ3, 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              
3Friedrich Miescher Laboratory, Max Planck Society, Max-Planck-Ring 9, 72076 Tübingen, DE, ou_2575692              

Content

show
hide
Free keywords: -
 Abstract: The Relevance Vector Machine (RVM) is a sparse approximate Bayesian kernel method. It provides full predictive distributions for test cases. However, the predictive uncertainties have the unintuitive property, that emphthey get smaller the further you move away from the training cases. We give a thorough analysis. Inspired by the analogy to non-degenerate Gaussian Processes, we suggest augmentation to solve the problem. The purpose of the resulting model, RVM*, is primarily to corroborate the theoretical and experimental analysis. Although RVM* could be used in practical applications, it is no longer a truly sparse model. Experiments show that sparsity comes at the expense of worse predictive distributions.

Details

show
hide
Language(s):
 Dates: 2005-08
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 3460
DOI: 10.1145/1102351.1102438
 Degree: -

Event

show
hide
Title: 22nd International Conference on Machine Learning (ICML 2005)
Place of Event: Bonn, Germany
Start-/End Date: 2005-08-07 - 2005-08-11

Legal Case

show

Project information

show

Source 1

show
hide
Title: ICML '05: 22nd international conference on Machine learning
Source Genre: Proceedings
 Creator(s):
Dzeroski, S, Editor
de Raedt, L, Editor
Wrobel, S, Editor
Affiliations:
-
Publ. Info: New York, NY, USA : ACM Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 689 - 696 Identifier: ISBN: 1-59593-180-5