Deep State Space Models for Nonlinear System Identification

Abstract

Deep state space models (SSMs) are an actively researched model class for temporal models developed in the deep learning community which have a close connection to classic SSMs. The use of deep SSMs as a black-box identification model can describe a wide range of dynamics due to the flexibility of deep neural networks. Additionally, the probabilistic nature of the model class allows the uncertainty of the system to be modelled. In this work a deep SSM class and its parameter learning algorithm are explained in an effort to extend the toolbox of nonlinear identification methods with a deep learning based method. Six recent deep SSMs are evaluated in a first unified implementation on nonlinear system identification benchmarks.

Authors: Daniel Gedon, Niklas Wahlström, Thomas B. Schön, Lennart Ljung
Publication: 19th IFAC Symposium on System Identification (SYSID), 2021 (Online)
Links: doi arXiv Code Slides
BibTeX Citation:

@inproceedings{gedon2021deepssm,
  author={Gedon, Daniel and Wahlstr{\"o}m, Niklas and Sch{\"o}n, Thomas B. and Ljung, Lennart},
  title={Deep State Space Models for Nonlinear System Identification},
  booktitle={Proceedings of the 19th IFAC Symposium on System Identification (SYSID)},
  month={July},
  year={2021},
  note={online},
}

Back to page: Publications or Talks.