Infinitely many concrete multiple-composite quantitative approximations by different Kantorovich - Shilkret neural network operators
Annales Universitatis Scientiarum Budapestinensis de Rolando Eötvös nominatae Sectio computatorica · 2026 · 59 · 47-66
DOI: 10.71352/ac.59.280426 ↗Kurz gefasst
Fachartikel in der Zeitschrift Annales Universitatis Scientiarum Budapestinensis de Rolando Eötvös nominatae Sectio computatorica, 2026. Verfasst von George A. Anastassiou.
Abstract (Originalsprache)
Here we research the multivariate quantitative approximation by infinitely many concrete and different multiple-composite Kantorovich—Shilkret type quasi-interpolation neural network operators with respect to supremum and LP norms. This is achieved with rates via the first multivariate modulus of continuity. We approximate continuous and bounded non-negative functions on Rn, N e N. When they are also uniformly continuous we have pointwise, uniform and L p convergences. Complex approximation is also discussed. Our multiple-composite activation functions are formed by 7 specific known sigmoid functions.
Zitieren
APA
Anastassiou, G. A. (2026). Infinitely many concrete multiple-composite quantitative approximations by different Kantorovich - Shilkret neural network operators. Annales Universitatis Scientiarum Budapestinensis de Rolando Eötvös nominatae Sectio computatorica, 59, 47-66. https://doi.org/10.71352/ac.59.280426
Vancouver
Anastassiou GA. Infinitely many concrete multiple-composite quantitative approximations by different Kantorovich - Shilkret neural network operators. Annales Universitatis Scientiarum Budapestinensis de Rolando Eötvös nominatae Sectio computatorica. 2026;59:47-66. doi:10.71352/ac.59.280426
BibTeX
@article{Anastassiou2026,
author = {Anastassiou, George A.},
title = {Infinitely many concrete multiple-composite quantitative approximations by different Kantorovich - Shilkret neural network operators},
journal = {Annales Universitatis Scientiarum Budapestinensis de Rolando Eötvös nominatae Sectio computatorica},
year = {2026},
volume = {59},
pages = {47--66},
doi = {10.71352/ac.59.280426}
}
EUVIMED