Parsimonious Kernel Fisher Discrimination
Parsimonious Kernel Fisher Discrimination
By applying recent results in optimization transfer, a new algorithm for kernel Fisher Discriminant Analysis is provided that makes use of a non-smooth penalty on the coefficients to provide a parsimonious solution. The algorithm is simple, easily programmed and is shown to perform as well as or better than a number of leading machine learning algorithms on a substantial benchmark. It is then applied to a set of extreme small-sample-size problems in virtual screening where it is found to be less accurate than a currently leading approach but is still comparable in a number of cases.
978-3-540-72846-7
531-538
Pasupa, Kitsuchart
952ededb-8c97-41b7-a65b-6aba31de2669
Harrison, Robert F.
c3ce2e0f-5408-4db9-90bd-a3149a932a72
Willett, Peter
1e5de175-dff4-4449-8e65-98263351544b
6 June 2007
Pasupa, Kitsuchart
952ededb-8c97-41b7-a65b-6aba31de2669
Harrison, Robert F.
c3ce2e0f-5408-4db9-90bd-a3149a932a72
Willett, Peter
1e5de175-dff4-4449-8e65-98263351544b
Pasupa, Kitsuchart, Harrison, Robert F. and Willett, Peter
(2007)
Parsimonious Kernel Fisher Discrimination.
Proceeding of 3rd Iberian Conference on Pattern Recognition and Image Analysis (IbPria'2007), Girona, Spain.
06 - 08 Jun 2007.
.
(doi:10.1007/978-3-540-72847-4_68).
Record type:
Conference or Workshop Item
(Other)
Abstract
By applying recent results in optimization transfer, a new algorithm for kernel Fisher Discriminant Analysis is provided that makes use of a non-smooth penalty on the coefficients to provide a parsimonious solution. The algorithm is simple, easily programmed and is shown to perform as well as or better than a number of leading machine learning algorithms on a substantial benchmark. It is then applied to a set of extreme small-sample-size problems in virtual screening where it is found to be less accurate than a currently leading approach but is still comparable in a number of cases.
Text
Parsimonious_Kernel_Fisher_Discrimination.pdf
- Accepted Manuscript
More information
Published date: 6 June 2007
Additional Information:
Event Dates: 6-8 June 2007
Venue - Dates:
Proceeding of 3rd Iberian Conference on Pattern Recognition and Image Analysis (IbPria'2007), Girona, Spain, 2007-06-06 - 2007-06-08
Organisations:
Electronics & Computer Science
Identifiers
Local EPrints ID: 266582
URI: http://eprints.soton.ac.uk/id/eprint/266582
ISBN: 978-3-540-72846-7
PURE UUID: 4f3ad853-fec9-45e6-9637-97ff2f12f53d
Catalogue record
Date deposited: 19 Aug 2008 22:27
Last modified: 14 Mar 2024 08:30
Export record
Altmetrics
Contributors
Author:
Kitsuchart Pasupa
Author:
Robert F. Harrison
Author:
Peter Willett
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