mlsanityData to 7 Oct 2026

Deep State Space Models for Nonlinear System Identification

arXiv 2003.14162 ↗First posted 31 Mar 2020eess.SY cs.LG cs.SYcited by 30

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 5; 2023: 7; 2024: 5; 2025: 3; 2026: 4.

30 papers.

Sort:

By area:

  1. 2023Deep networks for system identification: a Surveycited by 35
  2. 2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 29
  3. 2022Deep Subspace Encoders for Nonlinear System Identificationcited by 12
  4. 2021Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertaintycited by 11
  5. 2021Sparse Bayesian Deep Learning for Dynamic System Identificationcited by 8
  6. 2022Neural Extended Kalman Filters for Learning and Predicting Dynamics of Structural Systemscited by 8
  7. 2024OPa-Ma: Text Guided Mamba for 360-degree Image Out-paintingcited by 7
  8. 2023Sequential Estimation of Gaussian Process-based Deep State-Space Modelscited by 5
  9. 2024A probabilistic framework for learning non-intrusive corrections to long-time climate simulations from short-time training datacited by 5
  10. 2023Towards Flexibility and Interpretability of Gaussian Process State-Space Modelcited by 4
  11. 2023Stable Linear Subspace Identification: A Machine Learning Approachcited by 4
  12. 2024Regularization-Based Efficient Continual Learning in Deep State-Space Modelscited by 4
18 more
  1. 2023Physics-informed Machine Learning for Calibrating Macroscopic Traffic Flow Modelscited by 3
  2. 2024AI-Aided Kalman Filterscited by 3
  3. 2022Learning Deep Input-Output Stable Dynamicscited by 2
  4. 2025End-to-End Learning Framework for Solving Non-Markovian Optimal Controlcited by 2
  5. 2026SOLIS: Physics-Informed Learning of Interpretable Neural Surrogates for Nonlinear Systemscited by 2
  6. 2021Non-Autoregressive vs Autoregressive Neural Networks for System Identificationcited by 1
  7. 2021Deep Probabilistic Time Series Forecasting using Augmented Recurrent Input for Dynamic Systemscited by 1
  8. 2022DeepBayes -- an estimator for parameter estimation in stochastic nonlinear dynamical modelscited by 1
  9. 2023A Variational Autoencoder Framework for Robust, Physics-Informed Cyberattack Recognition in Industrial Cyber-Physical Systemscited by 1
  10. 2025Data-driven identification of nonlinear dynamical systems with LSTM autoencoders and Normalizing Flowscited by 1
  11. 2021Switching Recurrent Kalman Networkscited by 0
  12. 2022Interpretable Latent Variables in Deep State Space Modelscited by 0
  13. 2023Exploiting the capacity of deep networks only at training stage for nonlinear black-box system identificationcited by 0
  14. 2024Recursive Gaussian Process State Space Modelcited by 0
  15. 2025Coordinate ascent neural Kalman-MLE for state estimationcited by 0
  16. 2026Time-Varying Deep State Space Models for Sequences with Switching Dynamicscited by 0
  17. 2026Physics-Guided Recurrent State-Space Neural Networks for Multi-Step Predictioncited by 0
  18. 2026Online Learning via Learned Latent Bayesian Trackingcited by 0