Standard

Neural networks for classification problem on tabular data. / Nazdryukhin, A. S.; Fedrak, A. M.; Radeev, N. A.

In: Journal of Physics: Conference Series, Vol. 2142, No. 1, 012013, 14.12.2021.

Research output: Contribution to journalConference articlepeer-review

Harvard

Nazdryukhin, AS, Fedrak, AM & Radeev, NA 2021, 'Neural networks for classification problem on tabular data', Journal of Physics: Conference Series, vol. 2142, no. 1, 012013. https://doi.org/10.1088/1742-6596/2142/1/012013

APA

Nazdryukhin, A. S., Fedrak, A. M., & Radeev, N. A. (2021). Neural networks for classification problem on tabular data. Journal of Physics: Conference Series, 2142(1), [012013]. https://doi.org/10.1088/1742-6596/2142/1/012013

Vancouver

Nazdryukhin AS, Fedrak AM, Radeev NA. Neural networks for classification problem on tabular data. Journal of Physics: Conference Series. 2021 Dec 14;2142(1):012013. doi: 10.1088/1742-6596/2142/1/012013

Author

Nazdryukhin, A. S. ; Fedrak, A. M. ; Radeev, N. A. / Neural networks for classification problem on tabular data. In: Journal of Physics: Conference Series. 2021 ; Vol. 2142, No. 1.

BibTeX

@article{2fa1b56edb2f472795726b0c1f6c394d,
title = "Neural networks for classification problem on tabular data",
abstract = "This work presents the results of using self-normalizing neural networks with automatic selection of hyperparameters, TabNet and NODE to solve the problem of tabular data classification. The method of automatic selection of hyperparameters was realised. Testing was carried out with the open source framework OpenML AutoML Benchmark. As part of the work, a comparative analysis was carried out with seven classification methods, experiments were carried out for 39 datasets with 5 methods. NODE shows the best results among the following methods and overperformed standard methods for four datasets.",
author = "Nazdryukhin, {A. S.} and Fedrak, {A. M.} and Radeev, {N. A.}",
note = "Publisher Copyright: {\textcopyright} 2021 Institute of Physics Publishing. All rights reserved.; 11th International Conference on High-Performance Computing Systems and Technologies in Scientific Research, Automation of Control and Production, HPCST 2021 ; Conference date: 21-05-2021 Through 22-05-2021",
year = "2021",
month = dec,
day = "14",
doi = "10.1088/1742-6596/2142/1/012013",
language = "English",
volume = "2142",
journal = "Journal of Physics: Conference Series",
issn = "1742-6588",
publisher = "IOP Publishing Ltd.",
number = "1",

}

RIS

TY - JOUR

T1 - Neural networks for classification problem on tabular data

AU - Nazdryukhin, A. S.

AU - Fedrak, A. M.

AU - Radeev, N. A.

N1 - Publisher Copyright: © 2021 Institute of Physics Publishing. All rights reserved.

PY - 2021/12/14

Y1 - 2021/12/14

N2 - This work presents the results of using self-normalizing neural networks with automatic selection of hyperparameters, TabNet and NODE to solve the problem of tabular data classification. The method of automatic selection of hyperparameters was realised. Testing was carried out with the open source framework OpenML AutoML Benchmark. As part of the work, a comparative analysis was carried out with seven classification methods, experiments were carried out for 39 datasets with 5 methods. NODE shows the best results among the following methods and overperformed standard methods for four datasets.

AB - This work presents the results of using self-normalizing neural networks with automatic selection of hyperparameters, TabNet and NODE to solve the problem of tabular data classification. The method of automatic selection of hyperparameters was realised. Testing was carried out with the open source framework OpenML AutoML Benchmark. As part of the work, a comparative analysis was carried out with seven classification methods, experiments were carried out for 39 datasets with 5 methods. NODE shows the best results among the following methods and overperformed standard methods for four datasets.

UR - http://www.scopus.com/inward/record.url?scp=85123982906&partnerID=8YFLogxK

U2 - 10.1088/1742-6596/2142/1/012013

DO - 10.1088/1742-6596/2142/1/012013

M3 - Conference article

AN - SCOPUS:85123982906

VL - 2142

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

SN - 1742-6588

IS - 1

M1 - 012013

T2 - 11th International Conference on High-Performance Computing Systems and Technologies in Scientific Research, Automation of Control and Production, HPCST 2021

Y2 - 21 May 2021 through 22 May 2021

ER -

ID: 35609172