Inferring the dynamics of oscillatory systems using recurrent neural networks
- We investigate the predictive power of recurrent neural networks for oscillatory systems not only on the attractor but in its vicinity as well. For this, we consider systems perturbed by an external force. This allows us to not merely predict the time evolution of the system but also study its dynamical properties, such as bifurcations, dynamical response curves, characteristic exponents, etc. It is shown that they can be effectively estimated even in some regions of the state space where no input data were given. We consider several different oscillatory examples, including self-sustained, excitatory, time-delay, and chaotic systems. Furthermore, with a statistical analysis, we assess the amount of training data required for effective inference for two common recurrent neural network cells, the long short-term memory and the gated recurrent unit. Published under license by AIP Publishing.
Author details: | Rok CestnikORCiDGND, Markus AbelORCiDGND |
---|---|
DOI: | https://doi.org/10.1063/1.5096918 |
ISSN: | 1054-1500 |
ISSN: | 1089-7682 |
Pubmed ID: | https://pubmed.ncbi.nlm.nih.gov/31266337 |
Title of parent work (English): | Chaos : an interdisciplinary journal of nonlinear science |
Publisher: | American Institute of Physics |
Place of publishing: | Melville |
Publication type: | Article |
Language: | English |
Date of first publication: | 2019/06/26 |
Publication year: | 2019 |
Release date: | 2021/01/27 |
Volume: | 29 |
Issue: | 6 |
Number of pages: | 9 |
Funding institution: | Marie Sklodowska-Curie GrantEuropean Union (EU) [642563] |
Organizational units: | Mathematisch-Naturwissenschaftliche Fakultät / Institut für Physik und Astronomie |
DDC classification: | 5 Naturwissenschaften und Mathematik / 53 Physik / 530 Physik |
Peer review: | Referiert |
Publishing method: | Open Access / Green Open-Access |