Vestnik Udmurtskogo Universiteta. Matematika. Mekhanika. Komp'yuternye Nauki
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



Vestn. Udmurtsk. Univ. Mat. Mekh. Komp. Nauki:
Year:
Volume:
Issue:
Page:
Find






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


Vestnik Udmurtskogo Universiteta. Matematika. Mekhanika. Komp'yuternye Nauki, 2018, Volume 28, Issue 2, Pages 260–274
DOI: https://doi.org/10.20537/vm180212
(Mi vuu637)
 

COMPUTER SCIENCE

Neural networks with dynamical coefficients and adjustable connections on the basis of integrated backpropagation

M. N. Nazarov

National Research University of Electronic Technology, pl. Shokina, 1, Zelenograd, Moscow, 124498, Russia
References:
Abstract: We consider artificial neurons which will update their weight coefficients with an internal rule based on backpropagation, rather than using it as an external training procedure. To achieve this we include the backpropagation error estimate as a separate entity in all the neuron models and perform its exchange along the synaptic connections. In addition to this we add some special type of neurons with reference inputs, which will serve as a base source of error estimates for the whole network. Finally, we introduce a training control signal for all the neurons, which can enable the correction of weights and the exchange of error estimates. For recurrent neural networks we also demonstrate how to integrate backpropagation through time into their formalism with the help of some stack memory for reference inputs and external data inputs of neurons. Also, for widely used neural networks, such as long short-term memory, radial basis function networks, multilayer perceptrons and convolutional neural networks, we demonstrate their alternative description within the framework of our new formalism. As a useful consequence, our approach enables us to introduce neural networks with the adjustment of synaptic connections, tied to the integrated backpropagation.
Keywords: artificial neurons, backpropagation, adaptive connection adjustment, recurrent neural networks.
Received: 22.05.2018
Bibliographic databases:
Document Type: Article
UDC: 519.68, 007.5
MSC: 68T05, 62M86
Language: English
Citation: M. N. Nazarov, “Neural networks with dynamical coefficients and adjustable connections on the basis of integrated backpropagation”, Vestn. Udmurtsk. Univ. Mat. Mekh. Komp. Nauki, 28:2 (2018), 260–274
Citation in format AMSBIB
\Bibitem{Naz18}
\by M.~N.~Nazarov
\paper Neural networks with dynamical coefficients and adjustable connections on the basis of integrated backpropagation
\jour Vestn. Udmurtsk. Univ. Mat. Mekh. Komp. Nauki
\yr 2018
\vol 28
\issue 2
\pages 260--274
\mathnet{http://mi.mathnet.ru/vuu637}
\crossref{https://doi.org/10.20537/vm180212}
\isi{https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=Publons&SrcAuth=Publons_CEL&DestLinkType=FullRecord&DestApp=WOS_CPL&KeyUT=000467764800012}
\elib{https://elibrary.ru/item.asp?id=35258693}
Linking options:
  • https://www.mathnet.ru/eng/vuu637
  • https://www.mathnet.ru/eng/vuu/v28/i2/p260
  • Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Вестник Удмуртского университета. Математика. Механика. Компьютерные науки
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024