A Global Universality of Two-Layer Neural Networks with ReLU Activations

A Global Universality of Two-Layer Neural Networks with ReLU Activations

In the present study, we investigate a universality of neural networks, which concerns a density of the set of two-layer neural networks in function spaces. There are many works that handle the convergence over compact sets. In the present paper, we consider a global convergence by introducing a nor...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of function spaces 2021, Vol.2021, p.1-3, Article 6637220
Hauptverfasser: Hatano, Naoya, Ikeda, Masahiro, Ishikawa, Isao, Sawano, Yoshihiro
Format: Artikel
Sprache:eng
Schlagworte:
Approximation
Convergence
Function space
Machine learning
Mathematics
Mathematics, Applied
Neural networks
Physical Sciences
Science & Technology
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In the present study, we investigate a universality of neural networks, which concerns a density of the set of two-layer neural networks in function spaces. There are many works that handle the convergence over compact sets. In the present paper, we consider a global convergence by introducing a norm suitably, so that our results will be uniform over any compact set.
ISSN:2314-8896
2314-8888
DOI:10.1155/2021/6637220