Universal approximation with complex-valued deep narrow neural networks

DOI10.1007/S00365-025-09713-8MaRDI QIDQ6918069zbMATH OpenFDO

Authors Paul Geuchen, Thomas Jahn, Hannes Matt

Publication date 10 October 2025

Published in Constructive Approximation (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/S00365-025-09713-8

zbMATH Keywords

complex-valued neural networksholomorphic functionpolyharmonic functionuniform approximationuniversality

Mathematics Subject Classification ID

Approximation in the complex plane (30E10) Approximation by other special function classes (41A30) Multidimensional problems (41A63) Artificial neural networks and deep learning (68T07)

Cites work

• Approximation by superpositions of a sigmoidal function
• Approximation spaces of deep neural networks
• Entanglement detection with complex-valued neural networks
• Equivalence of approximation by convolutional neural networks and fully-connected networks
• Holomorphic functions of several variables. An introduction to the fundamental theory. With the assist. of Gottfried Barthel transl. by Michael Bridgland
• scientific article; zbMATH DE number 3539473 (Why is no real title available?)
• scientific article; zbMATH DE number 1324223 (Why is no real title available?)
• scientific article; zbMATH DE number 1022658 (Why is no real title available?)
• scientific article; zbMATH DE number 3232606 (Why is no real title available?)
• scientific article; zbMATH DE number 5350457 (Why is no real title available?)
• Measure Theoretic Results for Approximation by Neural Networks with Limited Weights
• Neural network with unbounded activation functions is universal approximator
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Quantitative Approximation Results for Complex-Valued Neural Networks
• Radii of regular polytopes
• Stochastic Feedforward Neural Networks: Universal Approximation
• The universal approximation theorem for complex-valued neural networks
• Universal approximation bounds for superpositions of a sigmoidal function
• Universal approximation of polygonal fuzzy neural networks in sense of K-integral norms
• Universal approximations of invariant maps by neural networks
• Universality of deep convolutional neural networks

This page was built for publication: Universal approximation with complex-valued deep narrow neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6918069)