Russian Journal of Nonlinear Dynamics
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



Rus. J. Nonlin. Dyn.:
Year:
Volume:
Issue:
Page:
Find






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


Russian Journal of Nonlinear Dynamics, 2023, Volume 19, Number 2, Pages 281–293
DOI: https://doi.org/10.20537/nd230502
(Mi nd853)
 

This article is cited in 1 scientific paper (total in 1 paper)

Nonlinear engineering and robotics

Noise Impact on a Recurrent Neural Network with a Linear Activation Function

V. M. Moskvitin, N. I. Semenova

Saratov State University, ul. Astrakhanskaya 1, Saratov, 410012 Russia
Full-text PDF (627 kB) Citations (1)
References:
Abstract: In recent years, more and more researchers in the field of artificial neural networks have been interested in creating hardware implementations where neurons and the connection between them are realized physically. Such networks solve the problem of scaling and increase the speed of obtaining and processing information, but they can be affected by internal noise.
In this paper we analyze an echo state neural network (ESN) in the presence of uncorrelated additive and multiplicative white Gaussian noise. Here we consider the case where artificial neurons have a linear activation function with different slope coefficients. We consider the influence of the input signal, memory and connection matrices on the accumulation of noise. We have found that the general view of variance and the signal-to-noise ratio of the ESN output signal is similar to only one neuron. The noise is less accumulated in ESN with a diagonal reservoir connection matrix with a large “blurring” coefficient. This is especially true of uncorrelated multiplicative noise.
Keywords: artificial neural networks, recurrent neural network, echo state network, noise, dispersion, statistic, white gaussian noise.
Funding agency Grant number
Russian Science Foundation 21-72-00002
This work was supported by the Russian Science Foundation (Project no. 21-72-00002).
Received: 28.02.2023
Accepted: 26.04.2023
Document Type: Article
MSC: 60H40, 62M45
Language: english
Citation: V. M. Moskvitin, N. I. Semenova, “Noise Impact on a Recurrent Neural Network with a Linear Activation Function”, Rus. J. Nonlin. Dyn., 19:2 (2023), 281–293
Citation in format AMSBIB
\Bibitem{MosSem23}
\by V. M. Moskvitin, N. I. Semenova
\paper Noise Impact on a Recurrent Neural Network with
a Linear Activation Function
\jour Rus. J. Nonlin. Dyn.
\yr 2023
\vol 19
\issue 2
\pages 281--293
\mathnet{http://mi.mathnet.ru/nd853}
\crossref{https://doi.org/10.20537/nd230502}
Linking options:
  • https://www.mathnet.ru/eng/nd853
  • https://www.mathnet.ru/eng/nd/v19/i2/p281
  • This publication is cited in the following 1 articles:
    Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Russian Journal of Nonlinear Dynamics
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024