Linear classifiers and selection of informative features
Yu. I. ZhuravlevDorodnicyn Computing Centre of the Russian Academy of Sciences, Moscow, 119333, RussiaYu. P. LaptinGlushkov Institute of Cybernetics of the Ukrainian National Academy of Sciences, Kiev, 03680, UkraineА. П. ВиноградовDorodnicyn Computing Centre of the Russian Academy of Sciences, Moscow, 119333, RussiaN. G. ZhurbenkoGlushkov Institute of Cybernetics of the Ukrainian National Academy of Sciences, Kiev, 03680, UkraineOleksii LykhovydGlushkov Institute of Cybernetics of the Ukrainian National Academy of Sciences, Kiev, 03680, UkraineO. A. BerezovskyiGlushkov Institute of Cybernetics of the Ukrainian National Academy of Sciences, Kiev, 03680, Ukraine
2017en
ABI
Аннотация
In this work, to construct classifiers for two linearly inseparable sets, the problem of minimizing the margin of incorrect classification is formulated, approaches to achieving approximate solution, and calculation estimates of the optimal value for this problem, are considered. Results of computational experiments that compare proposed approaches with SVM are presented. The problem of identifying informative features for large-dimensional diagnostic applications is analyzed and algorithms for its solution are developed.
Перевод пока недоступен
Идентификаторы
Цитирования и источники
Цитирований: 2Использованных источников: 0