Zhurnal Vychislitel'noi Matematiki i Matematicheskoi Fiziki
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive
Impact factor

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Zh. Vychisl. Mat. Mat. Fiz.:
Year:
Volume:
Issue:
Page:
Find






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


Zh. Vychisl. Mat. Mat. Fiz., 2018, Volume 58, Number 10, Pages 1728–1740 (Mi zvmmf10798)  

Construction of a correct algorithm and spatial neural network for recognition problems with binary data

M. V. Grishko, A. E. Dyusembaev

Al-Farabi Kazakh National University, Almaty, Kazakhstan

Abstract: Conditions under which it is possible to design a correct algorithm and a six-level spatial neural network reproducing the computations performed by this algorithm for recognition problems with binary data ($\Omega$-regular problems) are found. A distinctive feature of this network is the use of diagonal activation functions in its internal layers, which significantly simplify intermediate computations in the inner and outer loops. Given an $\Omega$-regular problem, the network sequentially computes the rows of the classification matrix for the test sample objects. The computational process (i.e., the inner loop) for each test object consists inside the elementary 3-level network (i.e., $\mu$-block) of a single iteration determined by a single object of the training set. The proposed approach to the neural network construction does not rely on the conventional approach based on the minimization of a functional; rather, it is based on the operator theory developed by Zhuravlev for solving recognition and classification problems.

Key words: correct algorithm, neural network, $\mu$-block, algebra.

DOI: https://doi.org/10.31857/S004446690003591-1

References: PDF file   HTML file

English version:
Computational Mathematics and Mathematical Physics, 2018, 58:10, 1673–1686

Bibliographic databases:

UDC: 519.87
Received: 10.10.2017

Citation: M. V. Grishko, A. E. Dyusembaev, “Construction of a correct algorithm and spatial neural network for recognition problems with binary data”, Zh. Vychisl. Mat. Mat. Fiz., 58:10 (2018), 1728–1740; Comput. Math. Math. Phys., 58:10 (2018), 1673–1686

Citation in format AMSBIB
\Bibitem{GriDus18}
\by M.~V.~Grishko, A.~E.~Dyusembaev
\paper Construction of a correct algorithm and spatial neural network for recognition problems with binary data
\jour Zh. Vychisl. Mat. Mat. Fiz.
\yr 2018
\vol 58
\issue 10
\pages 1728--1740
\mathnet{http://mi.mathnet.ru/zvmmf10798}
\crossref{https://doi.org/10.31857/S004446690003591-1}
\elib{https://elibrary.ru/item.asp?id=36715797}
\transl
\jour Comput. Math. Math. Phys.
\yr 2018
\vol 58
\issue 10
\pages 1673--1686
\crossref{https://doi.org/10.1134/S0965542518100068}
\isi{http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&DestLinkType=FullRecord&DestApp=ALL_WOS&KeyUT=000449497100012}
\scopus{https://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-85056139757}


Linking options:
  • http://mi.mathnet.ru/eng/zvmmf10798
  • http://mi.mathnet.ru/eng/zvmmf/v58/i10/p1728

    SHARE: VKontakte.ru FaceBook Twitter Mail.ru Livejournal Memori.ru


    Citing articles on Google Scholar: Russian citations, English citations
    Related articles on Google Scholar: Russian articles, English articles
  • Журнал вычислительной математики и математической физики Computational Mathematics and Mathematical Physics
    Number of views:
    This page:106
    References:18

     
    Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2021