English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Incremental Gaussian Processes

Quinonero Candela, J., & Winther, O. (2003). Incremental Gaussian Processes. In S. Becker, S. Thrun, & K. Obermayer (Eds.), Advances in Neural Information Processing Systems 15 (pp. 1001-1008). Cambridge, MA, USA: MIT Press.

Item is

Files

show Files

Locators

show
hide
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Quinonero Candela, J1, Author           
Winther, O, Author
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: In this paper, we consider Tipping‘s relevance vector machine (RVM) and formalize an incremental training
strategy as a variant of the expectation-maximization (EM) algorithm that we call subspace EM. Working with a subset of active basis functions, the sparsity of the RVM solution will ensure that the number of basis functions and thereby the computational complexity is kept low. We also introduce a mean field approach to the intractable classification
model that is expected to give a very good approximation to exact Bayesian inference and contains the Laplace approximation as a special case. We test the algorithms on two large data sets with O(10^3-10^4) examples. The results indicate that Bayesian learning of large data sets, e.g.
the MNIST database is realistic.

Details

show
hide
Language(s):
 Dates: 2003-09
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 2800
 Degree: -

Event

show
hide
Title: Sixteenth Annual Conference on Neural Information Processing Systems (NIPS 2002)
Place of Event: Vancouver, BC, Canada
Start-/End Date: 2002-12-09 - 2002-12-14

Legal Case

show

Project information

show

Source 1

show
hide
Title: Advances in Neural Information Processing Systems 15
Source Genre: Proceedings
 Creator(s):
Becker, S, Editor
Thrun, S, Editor
Obermayer, K, Editor
Affiliations:
-
Publ. Info: Cambridge, MA, USA : MIT Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1001 - 1008 Identifier: ISBN: 0-262-02550-7