Sistemy i Sredstva Informatiki [Systems and Means of Informatics]
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



Sistemy i Sredstva Inform.:
Year:
Volume:
Issue:
Page:
Find






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


Sistemy i Sredstva Informatiki [Systems and Means of Informatics], 2020, Volume 30, Issue 4, Pages 159–167
DOI: https://doi.org/10.14357/08696527200415
(Mi ssi744)
 

Parabolic integrodifferential splines as activation functions to increase the efficiency of information processing by neural networks

T. K. Biryukova

Institute of Informatics Problems, Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119133, Russian Federation
References:
Abstract: The paper considers the method to increase the efficiency of information processing by neural networks by using the parabolic integrodifferential splines (ID-splines) developed by the author as an activation function (AF) for neurons. If the coefficients of parabolic ID-splines along with the weights of the neurons are the trainable parameters of the neural network, then the AF in the form of a parabolic ID spline changes in the learning process to minimize the error function. This increases the accuracy of the results of the neural network calculations and accelerates its training and operation. The prospects for modifying neural networks with known architectures (such as ResNet) by introducing ID-spline as AF are analyzed. Apparently, such an approach can improve the quality of functioning of some popular neural networks. It is concluded that parabolic ID splines as AF can increase the efficiency of artificial intelligence technologies in such tasks as decision making, computer games development, approximating and predicting data (in the financial and social spheres, in science, etc.), classification of information, processing of images and videos, application of computer vision, processing of texts, speech, and music, etc.
Keywords: arrtificial intelligence, deep learning, neural network, activation function, spline interpolation, integrodifferential spline, parabolic spline.
Received: 02.11.2020
Document Type: Article
Language: Russian
Citation: T. K. Biryukova, “Parabolic integrodifferential splines as activation functions to increase the efficiency of information processing by neural networks”, Sistemy i Sredstva Inform., 30:4 (2020), 159–167
Citation in format AMSBIB
\Bibitem{Bir20}
\by T.~K.~Biryukova
\paper Parabolic integrodifferential splines as activation functions to increase the efficiency of information processing by neural networks
\jour Sistemy i Sredstva Inform.
\yr 2020
\vol 30
\issue 4
\pages 159--167
\mathnet{http://mi.mathnet.ru/ssi744}
\crossref{https://doi.org/10.14357/08696527200415}
Linking options:
  • https://www.mathnet.ru/eng/ssi744
  • https://www.mathnet.ru/eng/ssi/v30/i4/p159
  • Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Системы и средства информатики
    Statistics & downloads:
    Abstract page:105
    Full-text PDF :59
    References:15
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024