Doklady Rossijskoj Akademii Nauk. Mathematika, Informatika, Processy Upravlenia
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


Dokl. RAN. Math. Inf. Proc. Upr.:
Year:
Volume:
Issue:
Page:
Find




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

Doklady Rossijskoj Akademii Nauk. Mathematika, Informatika, Processy Upravlenia, 2020, Volume 490, Pages 74–77
DOI: https://doi.org/10.31857/S2686954320010166 (Mi danma38) 		 
INFORMATICS

Absence of bottlenecks in a neural network determines its generic functional properties

S. V. Kurochkin

National Research University "Higher School of Economics", Moscow, Russian Federation
Full-text PDF (127 kB)
References:
PDF
HTML
DOI: https://doi.org/10.31857/S2686954320010166
Abstract: It is proved that an artificial neural network with smooth activation functions and without bottlenecks is a Morse function for almost all, with respect to the Lebesgue measure, sets of weights.
Keywords: neural network, Morse function.
Funding agency Grant number
NTI
These results were obtained within the framework of a research project implemented at the Center for Big Data Storage and Analysis of Lomonosov Moscow State University.
Presented: K. V. Rudakov
Received: 08.11.2019
Revised: 08.11.2019
Accepted: 08.11.2019
English version:
Doklady Mathematics, 2020, Volume 101, Issue 1, Pages 62–65
DOI: https://doi.org/10.1134/S1064562420010160
Bibliographic databases:
Document Type: Article
UDC: 519.651
Language: Russian
Citation: S. V. Kurochkin, “Absence of bottlenecks in a neural network determines its generic functional properties”, Dokl. RAN. Math. Inf. Proc. Upr., 490 (2020), 74–77; Dokl. Math., 101:1 (2020), 62–65
Citation in format AMSBIB
\Bibitem{Kur20}
\by S.~V.~Kurochkin
\paper Absence of bottlenecks in a neural network determines its generic functional properties
\jour Dokl. RAN. Math. Inf. Proc. Upr.
\yr 2020
\vol 490
\pages 74--77
\mathnet{http://mi.mathnet.ru/danma38}
\crossref{https://doi.org/10.31857/S2686954320010166}
\zmath{https://zbmath.org/?q=an:07424554}
\elib{https://elibrary.ru/item.asp?id=42579066}
\transl
\jour Dokl. Math.
\yr 2020
\vol 101
\issue 1
\pages 62--65
\crossref{https://doi.org/10.1134/S1064562420010160}
Linking options:
  • https://www.mathnet.ru/eng/danma38
  • https://www.mathnet.ru/eng/danma/v490/p74
    • Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    		Doklady Rossijskoj Akademii Nauk. Mathematika, Informatika, Processy Upravlenia Doklady Rossijskoj Akademii Nauk. Mathematika, Informatika, Processy Upravlenia
    Statistics & downloads:
    Abstract page:76
    Full-text PDF :36
    References:14
     
      Contact us:
    		  Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024