Noncompact uniform universal approximation

DOI10.1016/J.NEUNET.2024.106181MaRDI QIDQ6121956zbMATH OpenOpenAlexFDO

Authors Teun D. H. van Nuland

Publication date 27 March 2024

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2308.03812

zbMATH Keywords

deep learningfeedforward ANNfunctional analysisridge functionsuniform convergenceuniversal approximation theorem

Mathematics Subject Classification ID

Approximation by other special function classes (41A30) Multidimensional problems (41A63) Banach algebras of continuous functions, function algebras (46J10) Artificial neural networks and deep learning (68T07)

Recommendations

• Approximation by neural networks with a bounded number of nodes at each level
• scientific article; zbMATH DE number 740111
• The universal approximation theorem for complex-valued neural networks
• Approximation by neural networks with a generalized sigmoidal function
• Uniform approximation by a non-convex cone of continuous functions

Cites work

• Algebraic supersymmetry: a case study
• Approximation by neural networks with a bounded number of nodes at each level
• Approximation by superpositions of a sigmoidal function
• scientific article; zbMATH DE number 48576 (Why is no real title available?)
• scientific article; zbMATH DE number 1405266 (Why is no real title available?)
• Multilayer feedforward networks are universal approximators
• Neural network approximation: three hidden layers are enough
• Quantization and the resolvent algebra
• Ridge functions and applications in neural networks
• Strict deformation quantization of abelian lattice gauge fields
• The quest for a quantum neural network
• The resolvent algebra: A new approach to canonical quantum systems
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(6)

• Universality of neural networks with a sigmoidal activation or discriminatory functions on functional Banach lattices over the real line
• A unified and constructive framework for the universality of neural networks
• Corrigendum to: ``Quantization and the resolvent algebra
• Improved universal approximation with neural networks studied via affine-invariant subspaces of \(L_2 (\mathbb{R}^n)\)
• Global universal approximation of functional input maps on weighted spaces
• Universal approximation results for neural networks with non-polynomial activation function over non-compact domains

This page was built for publication: Noncompact uniform universal approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6121956)