Universality of neural networks with a sigmoidal activation or discriminatory functions on functional Banach lattices over the real line
DOI10.1007/S10958-022-05889-7OpenAlexW4296008383WikidataQ114225169 ScholiaQ114225169MaRDI QIDQ6147819
Naoya Hatano, Masahiro Ikeda, Yoshihiro Sawano, Isao Ishikawa
Publication date: 1 February 2024
Published in: Journal of Mathematical Sciences (New York) (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s10958-022-05889-7
neural networksigmoidal functionsbounded uniformly continuous functionsdiscriminatory functionsfunctional Banach lattices
Function spaces arising in harmonic analysis (42B35) Fractional derivatives and integrals (26A33) Banach lattices (46B42)
Cites Work
- Theory of Besov spaces
- Approximation by superposition of sigmoidal and radial basis functions
- A global universality of two-layer neural networks with ReLU activations
- A non-dense subspace in \(\mathcal{M}_q^p\) with \(1 < q < p < \infty\)
- On L(p,q) spaces
- Generalized fractional integral operators and fractional maximal operators in the framework of Morrey spaces
- A Thought on Generalized Morrey Spaces
- Approximation by superpositions of a sigmoidal function
This page was built for publication: Universality of neural networks with a sigmoidal activation or discriminatory functions on functional Banach lattices over the real line
