The universal approximation theorem for complex-valued neural networks

DOI10.1016/J.ACHA.2022.12.002OpenAlexW4311305958WikidataQ123314538 ScholiaQ123314538MaRDI QIDQ2689134

Felix Voigtlaender

Publication date: 9 March 2023

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2012.03351

zbMATH Keywords

polyharmonic functionsholomorphic functionsuniversal approximation theoremcomplex-valued neural networksdeep neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Approximation in the complex plane (30E10) Multidimensional problems (41A63) Approximation by other special function classes (41A30) Biharmonic, polyharmonic functions and equations, Poisson's equation in two dimensions (31A30)

Related Items (2)

Deep learning methods for partial differential equations and related parameter identification problems ⋮ Computation and learning in high dimensions. Abstracts from the workshop held August 1--7, 2021 (hybrid meeting)

Uses Software

• ImageNet
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Linear functional analysis. An application-oriented introduction. Translated from the 6th German edition by Robert Nürnberg
• Holomorphic functions of several variables. An introduction to the fundamental theory. With the assist. of Gottfried Barthel transl. by Michael Bridgland
• Neural networks in multidimensional domains. Fundamentals and new trends in modelling and control
• Multilayer feedforward networks are universal approximators
• Approximation spaces of deep neural networks
• Universal approximations of invariant maps by neural networks
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Theory of deep convolutional neural networks: downsampling
• Error bounds for approximations with deep ReLU networks
• Universality of deep convolutional neural networks
• Approximation by Fully Complex Multilayer Perceptrons
• Complex-Valued Neural Networks
• Deep Network Approximation for Smooth Functions
• Equivalence of approximation by convolutional neural networks and fully-connected networks
• A Mathematical Motivation for Complex-Valued Convolutional Networks
• On Liouville’s Theorem for Biharmonic Functions
• Weyl's law in the theory of automorphic forms
• Approximation by superpositions of a sigmoidal function

This page was built for publication: The universal approximation theorem for complex-valued neural networks