Filtered gaussian processes for learning with large data-sets

Authors:
Jian Qing Shi;Roderick Murray-Smith;D. Mike Titterington;Barak A. Pearlmutter
Affiliations:
School of Mathematics and Statistics, University of Newcastle, UK;Department of Computing Science, University of Glasgow, Scotland;Department of Statistics, University of Glasgow, Scotland;Hamilton Institute, NUI Maynooth, Co. Kildare, Ireland
Venue:
Switching and Learning in Feedback Systems
Year:
2003

Citing 3
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
Evaluation of gaussian processes and other methods for non-linear regression

Evaluation of gaussian processes and other methods for non-linear regression
A Bayesian Committee Machine

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Kernel-based non-parametric models have been applied widely over recent years. However, the associated computational complexity imposes limitations on the applicability of those methods to problems with large data-sets. In this paper we develop a filtering approach based on a Gaussian process regression model. The idea is to generate a small-dimensional set of filtered data that keeps a high proportion of the information contained in the original large data-set. Model learning and prediction are based on the filtered data, thereby decreasing the computational burden dramatically.