Multivariate Generalized Logistic Neural Networks on Infinite Domain as Positive Linear Operators and a Taste of Measure Theory
Approximation Theory and Special Functions · 08.04.2026 · 2 (1) · 28-54
DOI: 10.65135/atsf.2026.7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Approximation Theory and Special Functions, online erschienen am 08.04.2026. Verfasst von George Anastassiou. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
We study a family of multivariate neural network operators on the infinite domain, constructed via a symmetrized generalized logistic activation function. These operators are treated as positive linear mappings acting on bounded and continuous functions. We establish quantitative approximation results in terms of moduli of continuity and Frechet derivatives. The operators are also examined within a probabilistic framework, highlighting their connections to measure theory.
Zitieren
APA
Anastassiou, G. (2026). Multivariate Generalized Logistic Neural Networks on Infinite Domain as Positive Linear Operators and a Taste of Measure Theory. Approximation Theory and Special Functions, 2(1), 28-54. https://doi.org/10.65135/atsf.2026.7
Vancouver
Anastassiou G. Multivariate Generalized Logistic Neural Networks on Infinite Domain as Positive Linear Operators and a Taste of Measure Theory. Approximation Theory and Special Functions. 2026;2(1):28-54. doi:10.65135/atsf.2026.7
BibTeX
@article{Anastassiou2026,
author = {Anastassiou, George},
title = {Multivariate Generalized Logistic Neural Networks on Infinite Domain as Positive Linear Operators and a Taste of Measure Theory},
journal = {Approximation Theory and Special Functions},
year = {2026},
volume = {2},
number = {1},
pages = {28--54},
doi = {10.65135/atsf.2026.7}
}
EUVIMED