Neural network approximation over finite dimensional Banach spaces

DOI10.1007/S13398-025-01722-3MaRDI QIDQ6957826zbMATH OpenFDO

Authors George A. Anastassiou

Publication date 16 July 2025

Published in Revista de la Real Academia de Ciencias Exactas, Físicas y Naturales. Serie A: Matemáticas. RACSAM (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S13398-025-01722-3

zbMATH Keywords

accelerated approximationfinite dimensional Banach spacesmodulus of continuityneural network operators approximationperturbation and symmetrization

Mathematics Subject Classification ID

Inequalities in approximation (Bernstein, Jackson, Nikol'ski?-type inequalities) (41A17) Rate of convergence, degree of approximation (41A25) Approximations and expansions (41A99) Classical Banach spaces in the general theory (46B25)

Review text

The paper develops quantitative neural network approximation results for functions defined on finite-dimensional Banach spaces with values in \(\mathbb{R}^N\). The central idea is to exploit the linear homeomorphism between any finite-dimensional Banach space \(E\) and \(\mathbb{R}^N\), thereby reducing the approximation problem to a multivariate setting in Euclidean space.\N\NUsing a perturbed hyperbolic tangent activation function and a symmetrized density construction, the author introduces several multivariate neural network operators: Normalized operators, Quasi-interpolation operators, Kantorovich-type operators and Quadrature-type operators. For each operator, multivariate Jackson-type inequalities are established in terms of the first modulus of continuity. The paper proves both pointwise and uniform convergence and provides explicit quantitative error bounds, including exponentially decaying remainder terms. This work represents a solid and technically rigorous contribution to approximation theory, particularly within the author's established research program on neural network operators.

Cites work

• A logical calculus of the ideas immanent in nervous activity
• Approximation results for neural network operators activated by sigmoidal functions
• scientific article; zbMATH DE number 1179314 (Why is no real title available?)
• scientific article; zbMATH DE number 1555867 (Why is no real title available?)
• Intelligent computations: abstract fractional calculus, inequalities, approximations
• Intelligent systems II. Complete approximation by neural network operators
• Intelligent systems. Approximation by artificial neural networks
• Multivariate neural network operators with sigmoidal activation functions
• Parametrized, Deformed and General Neural Networks
• Rate of convergence of some neural network operators to the unit-univariate case
• The approximation operators with sigmoidal functions
• Trigonometric and hyperbolic generated approximation theory

This page was built for publication: Neural network approximation over finite dimensional Banach spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6957826)