$L^{p}$-convergence of Kantorovich-type Max-Min Neural Network Operators

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Aslan, İsmail, De Marchi, Stefano, Erb, Wolfgang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911943828176896
author Aslan, İsmail
De Marchi, Stefano
Erb, Wolfgang
author_facet Aslan, İsmail
De Marchi, Stefano
Erb, Wolfgang
contents In this work, we study the Kantorovich variant of max-min neural network operators, in which the operator kernel is defined in terms of sigmoidal functions. Our main aim is to demonstrate the $L^{p}$-convergence of these nonlinear operators for $1\leq p<\infty$, which makes it possible to obtain approximation results for functions that are not necessarily continuous. In addition, we will derive quantitative estimates for the rate of approximation in the $L^{p}$-norm. We will provide some explicit examples, studying the approximation of discontinuous functions with the max-min operator, and varying additionally the underlying sigmoidal function of the kernel. Further, we numerically compare the $L^{p}$-approximation error with the respective error of the Kantorovich variants of other popular neural network operators. As a final application, we show that the Kantorovich variant has advantages compared to the sampling variant of the max-min operator and Kantorovich variant of the max-product operator when it comes to approximate noisy functions as for instance biomedical ECG signals.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03329
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle $L^{p}$-convergence of Kantorovich-type Max-Min Neural Network Operators
Aslan, İsmail
De Marchi, Stefano
Erb, Wolfgang
Numerical Analysis
41A30, 41A25
In this work, we study the Kantorovich variant of max-min neural network operators, in which the operator kernel is defined in terms of sigmoidal functions. Our main aim is to demonstrate the $L^{p}$-convergence of these nonlinear operators for $1\leq p<\infty$, which makes it possible to obtain approximation results for functions that are not necessarily continuous. In addition, we will derive quantitative estimates for the rate of approximation in the $L^{p}$-norm. We will provide some explicit examples, studying the approximation of discontinuous functions with the max-min operator, and varying additionally the underlying sigmoidal function of the kernel. Further, we numerically compare the $L^{p}$-approximation error with the respective error of the Kantorovich variants of other popular neural network operators. As a final application, we show that the Kantorovich variant has advantages compared to the sampling variant of the max-min operator and Kantorovich variant of the max-product operator when it comes to approximate noisy functions as for instance biomedical ECG signals.
title $L^{p}$-convergence of Kantorovich-type Max-Min Neural Network Operators
topic Numerical Analysis
41A30, 41A25
url https://arxiv.org/abs/2407.03329