The universal approximation theorem for complex-valued neural networks

We generalize the classical universal approximation theorem for neural networks to the case of complex-valued neural networks. Precisely, we consider feedforward networks with a complex activation function σ:C→C in which each neuron performs the operation CN→C,z↦σ(b+wTz) with weights w∈CN and a bias...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied and computational harmonic analysis Jg. 64; S. 33 - 61
1. Verfasser: Voigtlaender, Felix
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.05.2023
Schlagworte:
Complex-valued neural networks
Deep neural networks
Holomorphic functions
Polyharmonic functions
Universal approximation theorem
30E10
Deep neural networks
41A30
41A63
31A30
Complex-valued neural networks
Universal approximation theorem
68T07
Holomorphic functions
Polyharmonic functions
ISSN:1063-5203, 1096-603X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We generalize the classical universal approximation theorem for neural networks to the case of complex-valued neural networks. Precisely, we consider feedforward networks with a complex activation function σ:C→C in which each neuron performs the operation CN→C,z↦σ(b+wTz) with weights w∈CN and a bias b∈C. We completely characterize those activation functions σ for which the associated complex networks have the universal approximation property, meaning that they can uniformly approximate any continuous function on any compact subset of Cd arbitrarily well. Unlike the classical case of real networks, the set of “good activation functions”—which give rise to networks with the universal approximation property—differs significantly depending on whether one considers deep networks or shallow networks: For deep networks with at least two hidden layers, the universal approximation property holds as long as σ is neither a polynomial, a holomorphic function, nor an antiholomorphic function. Shallow networks, on the other hand, are universal if and only if the real part or the imaginary part of σ is not a polyharmonic function.
ISSN:1063-5203
1096-603X
DOI:10.1016/j.acha.2022.12.002