Comparative analysis of neural networks with complex activation functions
Received: 18 Oct 2026 Revised: 23 Oct 2026 Accepted: 31 Oct 2026
Published: 2026, vol. 30, issue 4, pp. 320–323
Abstract
The report examines a comparative analysis of neural networks with different complex activation functions (CReLU, zReLU, ModReLU, Cardioid, and ModTanh). The analysis results showed that the ModTanh function provides the highest training efficiency.
Keywords: neural networks, activation functions, learning rate, model stability.
BibTeX
@article{IS-Aleksiadis-Ayar2026,
author = {Aleksiadis, Nikos Philippovich and Ayar, Aung Set},
title = {{Comparative analysis of neural networks with complex activation functions}},
journal = {Intelligent Systems. Theory and Applications},
year = {2026},
volume = {30},
number = {4},
pages = {320--323},
}
AMSBIB
\Bibitem{IS-Aleksiadis-Ayar2026}
\by N.\,P.~Aleksiadis, A.\,S.~Ayar
\paper Comparative analysis of neural networks with complex activation functions
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 320--323
\lang In Russian
Published under
Creative Commons Attribution 4.0 International (CC BY 4.0)
RU