Degree of Lp Approximation Using Activated Singular Integrals
Open Access
Abstract
In this article we present the , , approximation properties of activated singular integral operators over the real line. We establish their approximation to the unit operator with rates. The kernels here come from neural network activation functions and we employ the related density functions. The derived inequalities use the high order modulus of smoothness.
Keywords
This publication has 10 references indexed in Scilit:
- Quantitative Uniform Approximation by Activated Singular OperatorsMathematics, 2024
- Parametrized, Deformed and General Neural Networks2023
- Banach Space Valued Neural Network2023
- The Picard and Gauss–Weierstrass Singular Integrals in (p, q)-CalculusBulletin of the Malaysian Mathematical Sciences Society, 2019
- On Generalized Picard Integral Operators2018
- $q$-GENERALIZATIONS OF THE PICARD AND GAUSS-WEIERSTRASS SINGULAR INTEGRALSTaiwanese Journal of Mathematics, 2008
- Convergence of generalized singular integrals to the unit, univariate caseMathematical Inequalities & Applications, 1998
- Remark on the Degree of Approximation of Continuous Functions by Singular IntegralsMathematische Nachrichten, 1993
- Constructive Approximation1993
- On the Rate of Convergence of Singular Integrals for Hölder Continuous FunctionsMathematische Nachrichten, 1990