Best Neural Network Approximation by using Bernstein Polynomials with GRNN Learning Application
Al-Bahir · 2022
DOI: 10.55810/2313-0083.1003 ↗Kurz gefasst
Fachartikel in der Zeitschrift Al-Bahir, 2022. Verfasst von Hawraa Abbas Almurieb und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 21 Literaturangaben.
Abstract (Originalsprache)
Bernstein polynomials are one of the first and main tools for function approximation. On the other hand, neural networks have many useful applications in approximation and other fields as well. In this paper, we study how we benefit from properties of Bernstein polynomials to define a new version of neural networks, that can be fit approximating functions in terms of modulus of continuity. Numerically, we use neural networks to approximate some types of continuous functions. For that purpose, we use GRNN algorithm to approximate functions uniformly by using Matlab, giving some examples that confirm good rate approximation.
Zitieren
APA
Almurieb, H. A., & Hamody, A. A. (2022). Best Neural Network Approximation by using Bernstein Polynomials with GRNN Learning Application. Al-Bahir. https://doi.org/10.55810/2313-0083.1003
Vancouver
Almurieb HA, Hamody AA. Best Neural Network Approximation by using Bernstein Polynomials with GRNN Learning Application. Al-Bahir. 2022. doi:10.55810/2313-0083.1003
BibTeX
@article{Almurieb2022,
author = {Almurieb, Hawraa Abbas and Hamody, Anwar Anwer},
title = {Best Neural Network Approximation by using Bernstein Polynomials with GRNN Learning Application},
journal = {Al-Bahir},
year = {2022},
doi = {10.55810/2313-0083.1003}
}
EUVIMED