Elementary proof of Funahashi's theorem

DOI10.33205/CMA.1466429MaRDI QIDQ6587223zbMATH OpenFDO

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

Publication date 13 August 2024

Published in Constructive Mathematical Analysis (Search for Journal in Brave)

Full work available at URL https://doi.org/10.33205/CMA.1466429

zbMATH Keywords

activation functionFourier analysisFunahashi's theoremneural networkuniform approximation

Mathematics Subject Classification ID

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) Linear composition operators (47B33)

Recommendations

• On a problem of Hornik
• Uniform approximation by a non-convex cone of continuous functions
• Approximation by neural networks with a bounded number of nodes at each level
• scientific article; zbMATH DE number 1989737
• Approximation properties of some two-layer feedforward neural networks

Cites work

• A global universality of two-layer neural networks with ReLU activations
• Enumeration of Seven-Argument Threshold Functions
• scientific article; zbMATH DE number 1022658 (Why is no real title available?)
• scientific article; zbMATH DE number 3314813 (Why is no real title available?)
• Learning representations by back-propagating errors
• The unreasonable effectiveness of deep learning in artificial intelligence

Cited in

(2)

• Compactness of neural networks
• Fractional order Fourier series and chirp approximation

This page was built for publication: Elementary proof of Funahashi's theorem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6587223)