Multi-composite general neural network approximation over finite dimensional Banach spaces
Transactions on Computational Modeling and Intelligent Systems · 2026
DOI: 10.65112/tcmis.10051 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions on Computational Modeling and Intelligent Systems, 2026. Verfasst von George A. Anastassiou. Die Arbeit nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
The functions under approximation here have as a domain a finite dimensional Banach space with dimension N∈N and are with values in RN. Exploiting some topological properties of the above we are able to perform multi-composite general Neural Network multivariate approximation to the above functions. The treatment is quantitative. We produce multivariate multi-composite general Jackson type inequalities involving the modulus of continuity of the function under approximation. The established convergences are pointwise and uniform. Our technique is expected to lead to accelerated speeds of convergence.
Zitieren
APA
Anastassiou, G. A. (2026). Multi-composite general neural network approximation over finite dimensional Banach spaces. Transactions on Computational Modeling and Intelligent Systems. https://doi.org/10.65112/tcmis.10051
Vancouver
Anastassiou GA. Multi-composite general neural network approximation over finite dimensional Banach spaces. Transactions on Computational Modeling and Intelligent Systems. 2026. doi:10.65112/tcmis.10051
BibTeX
@article{Anastassiou2026,
author = {Anastassiou, George A.},
title = {Multi-composite general neural network approximation over finite dimensional Banach spaces},
journal = {Transactions on Computational Modeling and Intelligent Systems},
year = {2026},
doi = {10.65112/tcmis.10051}
}
EUVIMED