dc.contributor.author | Benning, M | |
dc.contributor.author | Celledoni, E | |
dc.contributor.author | Ehrhardt, MJ | |
dc.contributor.author | Owren, B | |
dc.contributor.author | Schönlieb, C-B | |
dc.date.accessioned | 2021-08-06T12:45:58Z | |
dc.date.available | 2021-08-06T12:45:58Z | |
dc.date.issued | 2021-07-01 | |
dc.identifier.issn | 2405-8963 | |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/73500 | |
dc.description.abstract | 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. | en_US |
dc.format.extent | 620 - 623 | |
dc.publisher | Elsevier | en_US |
dc.relation.ispartof | IFAC-PapersOnLine | |
dc.rights | https://doi.org/10.1016/j.ifacol.2021.06.124 | |
dc.title | Deep learning as optimal control problems | en_US |
dc.type | Article | en_US |
dc.rights.holder | © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. | |
dc.identifier.doi | 10.1016/j.ifacol.2021.06.124 | |
pubs.issue | 9 | en_US |
pubs.notes | Not known | en_US |
pubs.volume | 54 | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |