Deep learning as optimal control problems
View/ Open
Volume
54
Pagination
620 - 623
Publisher
DOI
10.1016/j.ifacol.2021.06.124
Journal
IFAC-PapersOnLine
Issue
ISSN
2405-8963
Metadata
Show full item recordAbstract
We briefly review recent work where deep learning neural networks have been interpreted as discretisations of an optimal control problem subject to an ordinary differential equation constraint. We report here new preliminary experiments with implicit symplectic Runge-Kutta methods. In this paper, we discuss ongoing and future research in this area.
Authors
Benning, M; Celledoni, E; Ehrhardt, MJ; Owren, B; Schönlieb, C-BCollections
- Mathematics [1478]