The universal approximation theorem for complex-valued neural networks

DOI10.1016/j.acha.2022.12.002WikidataQ123314538 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 functions; holomorphic functions; universal approximation theorem; complex-valued neural networks; deep neural networks

Mathematics Subject Classification ID

68T07: Artificial neural networks and deep learning

30E10: Approximation in the complex plane

41A63: Multidimensional problems

41A30: Approximation by other special function classes

31A30: Biharmonic, polyharmonic functions and equations, Poisson's equation in two dimensions

Uses Software

• ImageNet
• AlexNet