Deep State Space Models for Nonlinear System Identification
This work extends the toolbox of nonlinear identification methods with a deep learning-based approach, which is incremental as it builds on existing deep SSM research.
The authors tackled the problem of nonlinear system identification by evaluating six deep state space models on benchmarks, finding that these models can describe a wide range of dynamics and model uncertainty due to their probabilistic nature.
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.