Multi-output regression using a locally regularised orthogonal least square algorithm
Multi-output regression using a locally regularised orthogonal least square algorithm
The paper proposes a locally regularised orthogonal least squares (LROLS) algorithm for constructing sparse multi-output regression models that generalise well. By associating each regressor in the regression model with an individual regularisation parameter, the ability for the multi-output orthogonal least squares (OLS) model selection to produce a parsimonious model with good generalisation performance is greatly enhanced.
185-195
Chen, S.
9310a111-f79a-48b8-98c7-383ca93cbb80
August 2002
Chen, S.
9310a111-f79a-48b8-98c7-383ca93cbb80
Chen, S.
(2002)
Multi-output regression using a locally regularised orthogonal least square algorithm.
IEE Proceedings - Vision, Image and Signal Processing, 149 (4), .
Abstract
The paper proposes a locally regularised orthogonal least squares (LROLS) algorithm for constructing sparse multi-output regression models that generalise well. By associating each regressor in the regression model with an individual regularisation parameter, the ability for the multi-output orthogonal least squares (OLS) model selection to produce a parsimonious model with good generalisation performance is greatly enhanced.
Text
iee-visp2002-149-4
- Author's Original
Restricted to Repository staff only
Request a copy
More information
Published date: August 2002
Additional Information:
submitted for publication in Oct. 2001, revised in Feb. 2002, accepted in March 2002
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 256833
URI: http://eprints.soton.ac.uk/id/eprint/256833
PURE UUID: 3f58e160-7bb7-4725-91f5-7f7c457c3b17
Catalogue record
Date deposited: 07 Oct 2002
Last modified: 14 Mar 2024 05:47
Export record
Contributors
Author:
S. Chen
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics