Vestnik KRAUNC. Fiziko-Matematicheskie Nauki
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive
Guidelines for authors
Submit a manuscript

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Vestnik KRAUNC. Fiz.-Mat. Nauki:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Vestnik KRAUNC. Fiziko-Matematicheskie Nauki, 2023, Volume 43, Number 2, Pages 69–86
DOI: https://doi.org/10.26117/2079-6641-2023-43-2-69-86
(Mi vkam602)
 

INFORMATION AND COMPUTATION TECHNOLOGIES

Applicability of genetic algorithms for determining the weighting coefficients of an artificial neural network with one hidden layer

A. D. Smorodinovab, T. V. Gavrilenkoba, V. A. Galkinab

a Surgut Branch of SRISA
b Surgut State University
References:
Abstract: In the training of an artificial neural network, one of the central problems is the initial initialization and adjustment of weighting coefficients associated with pseudo-random initialization of weighting coefficients. The article describes a basic genetic algorithm, as well as a method for determining weight coefficients using this algorithm. A combined method for determining weighting coefficients is also presented, which provides for initial initialization using a genetic algorithm at the first stage and the use of stochastic gradient descent at the second stage of training, the proposed methods are tested on a number of artificial neural networks of direct propagation for various tasks of binary classification of real and synthetic data, as well as for unambiguous multiclass classification of handwritten digits on images from the database MNIST data. Artificial neural networks are constructed on the basis of the Kolmogorov-Arnold theorem. This article presents a comparative analysis of two methods for determining weight coefficients – using a genetic algorithm and gradient descent. Based on the results of the comparative analysis, it is concluded that a genetic algorithm can be used to determine the weighting coefficients both as an algorithm for the initial initialization of an artificial neural network and as an algorithm for adjusting the weighting coefficients.
Keywords: artificial neural networks, genetic algorithm, Kolmogorov-Arnold theorem, neural network training.
Funding agency Grant number
Russian Academy of Sciences - Federal Agency for Scientific Organizations 0580-2021-0007
The name of the funding programme: The publication was made within the framework of the state task of the Federal State Institution FNTs NIISI RAS (Performance of fundamental scientific research GP 47) on topic No. 0580-2021-0007 «Development of methods for mathematical modeling of distributed systems and corresponding calculation methods» here. Organization that has provided funding: Ministry of Science and Higher Education of the Russian Federation.
Document Type: Article
UDC: 004.85
MSC: 68T99
Language: Russian
Citation: A. D. Smorodinov, T. V. Gavrilenko, V. A. Galkin, “Applicability of genetic algorithms for determining the weighting coefficients of an artificial neural network with one hidden layer”, Vestnik KRAUNC. Fiz.-Mat. Nauki, 43:2 (2023), 69–86
Citation in format AMSBIB
\Bibitem{SmoGavGal23}
\by A.~D.~Smorodinov, T.~V.~Gavrilenko, V.~A.~Galkin
\paper Applicability of genetic algorithms for determining the weighting coefficients of an artificial neural network with one hidden layer
\jour Vestnik KRAUNC. Fiz.-Mat. Nauki
\yr 2023
\vol 43
\issue 2
\pages 69--86
\mathnet{http://mi.mathnet.ru/vkam602}
\crossref{https://doi.org/10.26117/2079-6641-2023-43-2-69-86}
Linking options:
  • https://www.mathnet.ru/eng/vkam602
  • https://www.mathnet.ru/eng/vkam/v43/i2/p69
  • Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Vestnik KRAUNC. Fiziko-Matematicheskie Nauki Vestnik KRAUNC. Fiziko-Matematicheskie Nauki
    Statistics & downloads:
    Abstract page:48
    Full-text PDF :17
    References:17
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024