Approximation results in Orlicz spaces for sequences of Kantorovich max-product neural network operators

Abstract

In this paper we study the theory of the so-called Kantorovich max-product neural network operators in the setting of Orlicz spaces $L^{\phi }$. The results here proved, extend those given by Costarelli and Vinti in Result Math., 2016, to a more general context. The main advantage in studying neural network type operators in Orlicz spaces relies in the possibility to approximate not necessarily continuous functions (data) belonging to different function spaces by a unique general approach. Further, in order to derive quantitative estimates in this context, we introduce a suitable K-functional in $L^{\phi }$ and use it to provide an upper bound for the approximation error of the above operators. Finally, examples of sigmoidal activation functions have been considered and studied in details.

17 pages

Cited by in corpus (6)

• Smooth function approximation by deep neural networks with general activation functions
• A comparison among a fuzzy algorithm for image rescaling with other methods of digital image processing
• Simultaneous approximation by neural network operators with applications to Voronovskaja formulas
• Strong and weak sharp bounds for Neural Network Operators in Sobolev-Orlicz spaces and their quantitative extensions to Orlicz spaces
• Max-product Kantorovich sampling operators: quantitative estimates in functional spaces
• Some applications of modular convergence in vector lattice setting