Journal article icon

Journal article

Variational integrator graph networks for learning energy-conserving dynamical systems

Abstract:

Recent advances show that neural networks embedded with physics-informed priors significantly outperform vanilla neural networks in learning and predicting the long-term dynamics of complex physical systems from noisy data. Despite this success, there has only been a limited study on how to optimally combine physics priors to improve predictive performance. To tackle this problem we unpack and generalize recent innovations into individual inductive bias segments. As such, we are able to syste...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1103/physreve.104.035310

Authors


More by this author
Role:
Author
ORCID:
0000-0001-6450-1128
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
ORCID:
0000-0002-9305-9268
Rhodes Trust More from this funder
Publisher:
American Physical Society Publisher's website
Journal:
Physical Review E Journal website
Volume:
104
Issue:
3
Article number:
035310
Place of publication:
United States
Publication date:
2021-09-30
Acceptance date:
2021-09-15
DOI:
EISSN:
2470-0053
ISSN:
2470-0045
Pmid:
34654151
Language:
English
Keywords:
Pubs id:
1203164
Local pid:
pubs:1203164
Deposit date:
2023-01-20

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP