Sæmundsson, S;
Terenin, A;
Hofmann, K;
Deisenroth, MP;
(2020)
Variational Integrator Networks for Physically Meaningful Embeddings.
In:
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS) 2020.
AISTATS 2020: Palermo, Italy.
(In press).
Preview |
Text
1910.09349v2.pdf - Accepted Version Download (719kB) | Preview |
Abstract
Learning workable representations of dynamical systems is becoming an increasingly important problem in a number of application areas. By leveraging recent work connecting deep neural networks to systems of differential equations, we propose variational integrator networks, a class of neural network architectures designed to preserve the geometric structure of physical systems. This class of network architectures facilitates accurate long-term prediction, interpretability, and data-efficient learning, while still remaining highly flexible and capable of modeling complex behavior. We demonstrate that they can accurately learn dynamical systems from both noisy observations in phase space and from image pixels within which the unknown dynamics are embedded.
| Type: | Proceedings paper |
|---|---|
| Title: | Variational Integrator Networks for Physically Meaningful Embeddings |
| Event: | 23rd International Conference on Artificial Intelligence and Statistics (AISTATS) |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://www.aistats.org/accepted.html |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10093945 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
