Orthogonal least squares regression with tunable kernels
Orthogonal least squares regression with tunable kernels
A novel technique is proposed to construct sparse regression models based on the orthogonal least squares method with tunable kernels. The proposed technique tunes the centre vector and diagonal covariance matrix of individual regressor by incrementally minimising the training mean square error using a guided random search algorithm, and it offers a state-of-the-art method for constructing very sparse models that generalise well.
484-486
Chen, S.
9310a111-f79a-48b8-98c7-383ca93cbb80
Wang, X.X.
38cba1ba-039f-427c-ac6f-459768df3834
Brown, D.J.
04b8f318-c948-45c0-b542-2d75dcad8200
April 2005
Chen, S.
9310a111-f79a-48b8-98c7-383ca93cbb80
Wang, X.X.
38cba1ba-039f-427c-ac6f-459768df3834
Brown, D.J.
04b8f318-c948-45c0-b542-2d75dcad8200
Chen, S., Wang, X.X. and Brown, D.J.
(2005)
Orthogonal least squares regression with tunable kernels.
Electronics Letters, 41 (8), .
Abstract
A novel technique is proposed to construct sparse regression models based on the orthogonal least squares method with tunable kernels. The proposed technique tunes the centre vector and diagonal covariance matrix of individual regressor by incrementally minimising the training mean square error using a guided random search algorithm, and it offers a state-of-the-art method for constructing very sparse models that generalise well.
Text
EL_OLSTK.pdf
- Other
More information
Published date: April 2005
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 260780
URI: http://eprints.soton.ac.uk/id/eprint/260780
ISSN: 0013-5194
PURE UUID: 4426424b-69ef-473a-b5a0-899d6105ef6c
Catalogue record
Date deposited: 19 Apr 2005
Last modified: 14 Mar 2024 06:43
Export record
Contributors
Author:
S. Chen
Author:
X.X. Wang
Author:
D.J. Brown
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