Vestnik Yuzhno-Ural'skogo Gosudarstvennogo Universiteta. Seriya "Matematika. Mekhanika. Fizika"
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



Vestn. Yuzhno-Ural. Gos. Un-ta. Ser. Matem. Mekh. Fiz.:
Year:
Volume:
Issue:
Page:
Find






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


Vestnik Yuzhno-Ural'skogo Gosudarstvennogo Universiteta. Seriya "Matematika. Mekhanika. Fizika", 2015, Volume 7, Issue 3, Pages 5–9 (Mi vyurm259)  

Mathematics

Stability of multilayer recursive neural networks

S. A. Ivanov, I. I. Blees

South Ural State University
References:
Abstract: Numerical stability criteria are described for multilayer discrete-time neural networks. Stability domains in the space of parameters are built. The problem reduces to the stability problem for difference matrix equations of a higher order with delay. Stability cones are major tolls for problem solution.
Keywords: neural networks; difference matrix equations; stability of difference equations; multilayer network.
Received: 26.03.2015
Bibliographic databases:
Document Type: Article
UDC: 517.96
Language: Russian
Citation: S. A. Ivanov, I. I. Blees, “Stability of multilayer recursive neural networks”, Vestn. Yuzhno-Ural. Gos. Un-ta. Ser. Matem. Mekh. Fiz., 7:3 (2015), 5–9
Citation in format AMSBIB
\Bibitem{IvaBle15}
\by S.~A.~Ivanov, I.~I.~Blees
\paper Stability of multilayer recursive neural networks
\jour Vestn. Yuzhno-Ural. Gos. Un-ta. Ser. Matem. Mekh. Fiz.
\yr 2015
\vol 7
\issue 3
\pages 5--9
\mathnet{http://mi.mathnet.ru/vyurm259}
\elib{https://elibrary.ru/item.asp?id=23730234}
Linking options:
  • https://www.mathnet.ru/eng/vyurm259
  • https://www.mathnet.ru/eng/vyurm/v7/i3/p5
  • Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Statistics & downloads:
    Abstract page:146
    Full-text PDF :70
    References:34
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024