Open main menu
Research portal |
About the portal
Publications
Projects
Talks
Awards
Doctorates
Habilitations
Persons
Organisations
DE
|
EN
Existence, uniqueness, and convergence rates for gradient flows in the training of artificial neural networks with ReLU activation
Eberle, Simon; Jentzen, Arnulf; Riekert, Adrian; Weiss, Georg S.
Research article (journal)
| Peer reviewed
Details about the publication
Journal:
Electronic Research Archive (Electron. Res. Arch.)
Volume:
31
Issue:
5
Page range:
2519-2554
Status:
Published
Release year:
2023 (06/03/2023)
Language in which the publication is written:
English
DOI:
10.3934/era.2023128
Link to the full text:
http://www.aimspress.com/article/doi/10.3934/era.2023128
Keywords:
Deep learning; Artificial intelligence; Optimization; Gradient flow; Kurdyka-Łojasiewicz inequalities
Authors from the University of Münster
Jentzen
,
Arnulf
Institute for Analysis and Numerics
Professorship for applied mathematics (Prof. Jentzen)
Riekert
,
Adrian
Mathematical Institute