Parsimonious Kernel Fisher Discrimination

269

Views

0

Downloads

Pasupa, Kitsuchart, Harrison, Robert F. and Willett, Peter (2007) Parsimonious Kernel Fisher Discrimination In: Pattern Recognition and Image Analysis, Lecture Notes in Computer Science Springer Berlin Heidelberg, 531-538.

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.

Item Type:

Book Section

Identification Number (DOI):

Deposited by:

ระบบ อัตโนมัติ

Date Deposited:

2021-09-06 03:38:22

Last Modified:

2021-09-06 03:38:22

Impact and Interest:

Statistics