Multivariate and Abstract Neural Networks as Positive Linear Operators

View at publisher Summarise with VIRAT
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Basic multivariate-abstract neural network operators are interpreted as positive linear operators and the related general theory applies to them. These operators are induced by a symmetrized density function deriving from the parametrized and deformed hyperbolic tangent activation function. We are acting on the space of continuous functions on a box in ℝ N , N ∈ ℕ, with values to a general Banach space. We study quantitatively the rate of convergence of these neural network operators to the unit operator. Our inequalities involve the modulus of continuity of the function under approximation or its Fréchet derivative. Convexity of functions is also taken into consideration. It follows [155].

Fields of Study & Subjects

Approximation Theory and Sequence Spaces Neural Networks and Applications Mathematical Inequalities and Applications

Publication details

Journal / source
Series on concrete and applicable mathematics
Pages
115–139
Publication date
25 March 2026
Language
EN
Document type
Book chapter