Some density theorems in neural network with variable exponent

DOI10.1007/S00009-025-02935-XMaRDI QIDQ6908722zbMATH OpenFDO

Authors Mitsuo Izuki, Takahiro Noi, Yoshihiro Sawano, Hirokazu Tanaka

Publication date 30 October 2025

Published in Mediterranean Journal of Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S00009-025-02935-X

zbMATH Keywords

Fourier transformdensityvariable exponentsquashing functions

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Function spaces arising in harmonic analysis (42B35) Spaces of measurable functions ((L^p)-spaces, Orlicz spaces, Köthe function spaces, Lorentz spaces, rearrangement invariant spaces, ideal spaces, etc.) (46E30)

Cites work

• scientific article; zbMATH DE number 2057273 (Why is no real title available?)
• scientific article; zbMATH DE number 1557107 (Why is no real title available?)
• scientific article; zbMATH DE number 2105501 (Why is no real title available?)
• A new proof of the boundedness of maximal operators on variable Lebesgue spaces
• Approximate identities and Young type inequalities in Musielak-Orlicz spaces.
• Approximate identities and Young type inequalities in variable Lebesgue-Orlicz spaces \(L^{p(\cdot)}(\log L)^{q(\cdot)}\)
• Approximate identities for the Schwartz space
• Approximation by superpositions of a sigmoidal function
• Approximation properties on Herz spaces
• Heaviside function as an activation function
• Maximal function on generalized Lebesgue spaces L^p(⋅)
• Maximal functions in variable exponent spaces: limiting cases of the exponent
• Multilayer feedforward networks are universal approximators
• Multiresolution approximations and wavelet bases of weighted \(L^p\) spaces
• On modular inequalities in variable \(L^p\) spaces
• On the theory of Besov-Herz spaces and Euler equations
• Real analysis. Theory of measure and integration
• Some modular inequalities in Lebesgue spaces with variable exponent on the complex plane
• Universality of neural networks with a sigmoidal activation or discriminatory functions on functional Banach lattices over the real line
• Variable Lebesgue spaces. Foundations and harmonic analysis
• Wavelet characterization and modular inequalities for weighted Lebesgue spaces with variable exponent
• Weighted Hankel transform and its applications to Fourier transform

This page was built for publication: Some density theorems in neural network with variable exponent

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6908722)