Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Switching Dynamical Systems with Deep Neural Networks

: Ojeda, César; Georgiev, Bogdan; Cvejoski, Kostadin; Schücker, Jannis; Bauckhage, Christian; Sánchez, Ramsés J.


Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
ICPR 2020, 25th International Conference on Pattern Recognition. Proceedings : 10-15 January 2021, Milan, Italy, Virtual
Piscataway, NJ: IEEE, 2021
ISBN: 978-1-7281-8809-6
ISBN: 978-1-7281-8808-9
International Conference on Pattern Recognition (ICPR) <25, 2021, Online>
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
01/S18038A; ML2R
Fraunhofer IAIS ()
time series analysis; neural networks; switches; Predictive models; data models; pattern recognition; dynamical system; Neural Nets; nonlinear dynamical systems; recurrent neural networks; time series

The problem of uncovering different dynamical regimes is of pivotal importance in time series analysis. Switching dynamical systems provide a solution for modeling physical phenomena whose time series data exhibit different dynamical modes. In this work we propose a novel variational RNN model for switching dynamics allowing for both non-Markovian and nonlinear dynamical behavior between and within dynamic modes. Attention mechanisms are provided to inform the switching distribution. We evaluate our model on synthetic and empirical datasets of diverse nature and successfully uncover different dynamical regimes and predict the switching dynamics.