Some properties of the classification algorithms using ensemble kernels

Some properties of the classification algorithms using ensemble kernels Full article

Conference

International Conference «Marchuk Scientific Readings 2020», dedicated to the 95th anniversary of the birthday of RAS Academician Guri. I. Marchuk
19-23 Oct 2020 , Новосибирск

Journal

Journal of Physics: Conference Series
ISSN: 1742-6588 , E-ISSN: 1742-6596

Output data

Year: 2021, Volume: 1715, Number: 1, Article number : 012011, Pages count : DOI: 10.1088/1742-6596/1715/1/012011

Authors

Odinokikh N. ¹ , Berikov V. ^1,2

Affiliations

1	Novosibirsk State University, Novosibirsk, Russian Federation
2	Sobolev Institute of Mathematics SB RAS, Novosibirsk, Russian Federation

Funding (3)

1	Russian Foundation for Basic Research	19-29-01175
2	Russian Foundation for Basic Research	18-07-00600
3	Sobolev Institute of Mathematics	0314-2019-0015

In this paper, we study the properties of the KCCE algorithm (Kernel-based Classification with Cluster Ensemble) proposed in our previous publication. Different strategies for choosing the ensemble weights are investigated from the point of view of their influence on the quality and speed of the algorithm. We perform numerical experiments with the algorithm on real datasets from the UCI repository under conditions of artificially added noise at different levels. © 2021 Institute of Physics Publishing. All rights reserved.

Odinokikh N. , Berikov V.
Some properties of the classification algorithms using ensemble kernels
Journal of Physics: Conference Series. 2021. V.1715. N1. 012011 . DOI: 10.1088/1742-6596/1715/1/012011 Scopus OpenAlex

Scopus:	2-s2.0-85100711322
OpenAlex:	W3120518310

Пока нет цитирований