Fractional Convergence of Symmetrized Neural Network Operators: A Generalized Voronovskaya-Damasclin Approach
Journal of Superintelligence and Computing · 04.03.2026
DOI: 10.66967/jsc.2026.v2i103 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Superintelligence and Computing, online erschienen am 04.03.2026. Die Arbeit nennt 8 Literaturangaben.
Abstract (Originalsprache)
This paper explores the asymptotic behavior of univariate neural network operators, with an emphasis on both classical and fractional differentiation over infinite domains. The analysis leverages symmetrized and perturbed hyperbolic tangent activation functions to investigate basic, Kantorovich, and quadrature-type operators. Voronovskaya-type expansions, along with the novel Voronovskaya-Damasclin theorem, are derived to obtain precise error estimates and establish convergence rates, thereby extending classical results to fractional calculus via Caputo derivatives. The study delves into the intricate interplay between operator parameters and approximation accuracy, providing a comprehensive framework for future research in multidimensional and stochastic settings. This work lays the groundwork for a deeper understanding of neural network operators in complex mathematical.
Zitieren
APA
(2026). Fractional Convergence of Symmetrized Neural Network Operators: A Generalized Voronovskaya-Damasclin Approach. Journal of Superintelligence and Computing. https://doi.org/10.66967/jsc.2026.v2i103
Vancouver
Fractional Convergence of Symmetrized Neural Network Operators: A Generalized Voronovskaya-Damasclin Approach. Journal of Superintelligence and Computing. 2026. doi:10.66967/jsc.2026.v2i103
BibTeX
@article{euvimed2026,
title = {Fractional Convergence of Symmetrized Neural Network Operators: A Generalized Voronovskaya-Damasclin Approach},
journal = {Journal of Superintelligence and Computing},
year = {2026},
doi = {10.66967/jsc.2026.v2i103}
}
EUVIMED