Bulletin of Irkutsk State University. Series Mathematics
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Bulletin of Irkutsk State University. Series Mathematics:
Year:
Volume:
Issue:
Page:
Find






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


Bulletin of Irkutsk State University. Series Mathematics, 2022, Volume 39, Pages 111–126
DOI: https://doi.org/10.26516/1997-7670.2022.39.111
(Mi iigum481)
 

This article is cited in 4 scientific papers (total in 4 papers)

Algebraic and logical methods in computer science and artificial intelligence

On endomorphisms of the additive monoid of subnets of a two-layer neural network

Andrey V. Litavrin

Siberian Federal University, Krasnoyarsk, Russian Federation
Full-text PDF (717 kB) Citations (4)
References:
Abstract: Previously, for each multilayer neural network of direct signal propagation (hereinafter, simply a neural network), finite commutative groupoids were introduced, which were called additive subnet groupoids. These groupoids are closely related to the subnets of the neural network over which they are built. A grupoid is a monoid if and only if it is built over a two-layer neural network. Earlier, endomorphisms and their properties were studied for these groupoids. Some endomorphisms were constructed, but an exhaustive element-by-element description was not received. It was shown that every finite monoid is isomorphic to some submonoid of the monoid of all endomorphisms of a suitable additive subnet groupoid for some suitable neural network.
In this paper, we study endomorphisms of additive groupoids of subnets of two-layer neural networks. The main result of the work is an element-wise description of the monoid of all endomorphisms of additive monoids of subnets built over a two-layer neural network. The item-by-item description is obtained by constructing a general form of endomorphism. The general view of an endomorphism is parameterized by the endomorphisms of suitable booleans with respect to the union operation. Therefore, endomorphisms of these Booleans were studied in this work. In particular, the semirings of endomorphisms of these Booleans with respect to the union were studied. In addition, to describe the general form of the endomorphism of the additive monoid of subnets, homomorphisms of one Boalean into another (with respect to union) were used.
Keywords: groupoid endomorphism, feedforward multilayer neural network, multilayer neural network subnet.
Funding agency Grant number
Ministry of Science and Higher Education of the Russian Federation 075-02-2022-876
This work is supported by the Krasnoyarsk Mathematical Center and financed by the Ministry of Science and Higher Education of the Russian Federation (Agreement No. 075-02-2022-876).
Received: 13.12.2021
Revised: 19.01.2022
Accepted: 27.01.2022
Bibliographic databases:
Document Type: Article
UDC: 512.577+519.68:007.5
Language: English
Citation: Andrey V. Litavrin, “On endomorphisms of the additive monoid of subnets of a two-layer neural network”, Bulletin of Irkutsk State University. Series Mathematics, 39 (2022), 111–126
Citation in format AMSBIB
\Bibitem{Lit22}
\by Andrey~V.~Litavrin
\paper On endomorphisms of the additive monoid of subnets of a two-layer neural network
\jour Bulletin of Irkutsk State University. Series Mathematics
\yr 2022
\vol 39
\pages 111--126
\mathnet{http://mi.mathnet.ru/iigum481}
\crossref{https://doi.org/10.26516/1997-7670.2022.39.111}
\mathscinet{http://mathscinet.ams.org/mathscinet-getitem?mr=4403436}
\isi{https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=Publons&SrcAuth=Publons_CEL&DestLinkType=FullRecord&DestApp=WOS_CPL&KeyUT=000773248700008}
Linking options:
  • https://www.mathnet.ru/eng/iigum481
  • https://www.mathnet.ru/eng/iigum/v39/p111
  • This publication is cited in the following 4 articles:
    Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Statistics & downloads:
    Abstract page:148
    Full-text PDF :125
    References:28
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024