Best Neural Network Approximation by using Bernstein Polynomials with GRNN Learning Application
Journal Title: Al-Bahir Journal for Engineering and Pure Sciences - Year 2022, Vol 1, Issue 1
Abstract
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.
Authors and Affiliations
Hawraa Abbas Almurieb, Anwar Anwer Hamody
Keywords
Related Articles
- EP ID EP744518
- DOI -
- Views 29
- Downloads 0
Some concepts related to supra soft v- open
Concentration of Spraying Solution Effect on the Structural, Morphological and Optical Properties of NiO Thin Films
In the present study nickel oxide NiO thin films of thickness ranging about 250e350 nm which were prepared on glass substrates by using chemical spray pyrolysis as a simple and low cost method. The impact of thickness a...
Cancellation and Weak Cancellation S-Acts
The purpose of this work is to introduce and study a generalization of the cancellation (weak cancellation) of modules to acts. Then some notions related of modules was extend to arbitrary acts. Several statements that a...
RETRACTED: Fabrication and Characterization of Wood Fiber Reinforced Polymer Composites
RETRACTED: Fabrication and Characterization of Wood Fiber Reinforced Polymer Composites
A New Generalized Gamma-Weibull Distribution and its Applications