|
Zhurnal Vychislitel'noi Matematiki i Matematicheskoi Fiziki, 2008, Volume 48, Number 7, Pages 1318–1336
(Mi zvmmf4569)
|
|
|
|
This article is cited in 4 scientific papers (total in 4 papers)
Feature selection algorithm in classification learning using support vector machines
Yu. V. Goncharova, I. B. Muchnikb, L. V. Shvartserc a Dorodnicyn Computing Center, Russian Academy of Sciences,
ul. Vavilova 40, Moscow, 119333, Russia
b Rutgers University, New Brunswick, New Jersey 09903, USA
c Ness Technologies, Atidim, P.O.B. 58152, Tel-Aviv, 61581, Israel
Abstract:
An algorithm for selecting features in the classification learning problem is considered. The algorithm is based on a modification of the standard criterion used in the support vector machine method. The new criterion adds to the standard criterion a penalty function that depends on the selected features. The solution of the problem is reduced to finding the minimax of a convex-concave function. As a result, the initial set of features is decomposed into three classes – unconditionally selected, weighted selected, and eliminated features.
Key words:
feature selection algorithm, classification learning, support vector machine, saddle point searching algorithm.
Received: 15.02.2007 Revised: 25.10.2007
Citation:
Yu. V. Goncharov, I. B. Muchnik, L. V. Shvartser, “Feature selection algorithm in classification learning using support vector machines”, Zh. Vychisl. Mat. Mat. Fiz., 48:7 (2008), 1318–1336; Comput. Math. Math. Phys., 48:7 (2008), 1243–1260
Linking options:
https://www.mathnet.ru/eng/zvmmf4569 https://www.mathnet.ru/eng/zvmmf/v48/i7/p1318
|
|