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 37
- Downloads 0
Using Powder Metallurgy Process to Produce Ceramic-Metal Composites
Pressing powders and engineering materials is an innovative method for producing samples with a low cost and multiple industrial applications. In the current article, copper metal was added in different volume ratios to...
Effect of Different Additions of Nano-Zirconia on Some Structural and Mechanical Properties of (Ni-SiC) Composite
Forecasting the Demand for Asphalt Concrete in Karbala Governorate
The challenge of forecasting asphalt concrete demand in the Karbala governorate is the subject of this study. Population and number of vehicles in Karbala are considered among the independent (explanatory) variables tak...
Waste Recycling: Waste to Energy System
Comparison between honey produced by bees, aphids and wasps in Kurdistan Region - Iraq based on biochemical parameters