Papers
Topics
Authors
Recent
2000 character limit reached

Kernel Modelling of Fading Memory Systems (2403.11945v2)

Published 18 Mar 2024 in eess.SY, cs.SY, and math.OC

Abstract: The paper is a follow-up of the recently introduced kernel-based framework to identify nonlinear input-output systems regularized by desirable input-output incremental properties. Assuming that the system has fading memory, we propose to learn the functional that maps the past input to the present output rather than the operator mapping input trajectories to output trajectories. While retaining the benefits of the previously proposed framework, this modification simplifies the selection of the kernel, enforces causality, and enables temporal simulation.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. “Fading memory and the problem of approximating nonlinear operators with Volterra series” In IEEE Transactions on Circuits and Systems 32.11, 1985, pp. 1150–1161 DOI: 10.1109/TCS.1985.1085649
  2. “Echo state networks are universal” In Neural Networks 108, 2018, pp. 495–508 DOI: 10.1016/j.neunet.2018.08.025
  3. “Neural Systems as Nonlinear Filters” In Neural Computation 12, 2000 DOI: 10.1162/089976600300015123
  4. Thiago B. Burghi, Maarten Schoukens and Rodolphe Sepulchre “System identification of biophysical neuronal models” arXiv, 2020 DOI: 10.48550/arXiv.2012.07691
  5. Nicholas M. Boffi, Stephen Tu and Jean-Jacques Slotine “Nonparametric Adaptive Control and Prediction: Theory and Randomized Algorithms” In 2021 60th IEEE Conference on Decision and Control (CDC) Austin, TX, USA: IEEE, 2021, pp. 2935–2942 DOI: 10.1109/CDC45484.2021.9682907
  6. Gianluigi Pillonetto and Giuseppe De Nicolao “A New Kernel-Based Approach for Linear System Identification” In Automatica 46.1, 2010, pp. 81–93 DOI: 10.1016/j.automatica.2009.10.031
  7. Gianluigi Pillonetto, Minh Ha Quang and Alessandro Chiuso “A New Kernel-Based Approach for NonlinearSystem Identification” In IEEE Transactions on Automatic Control 56.12, 2011, pp. 2825–2840 DOI: 10.1109/TAC.2011.2131830
  8. “Kernel Methods in System Identification, Machine Learning and Function Estimation: A Survey” In Automatica 50.3, 2014, pp. 657–682 DOI: 10.1016/j.automatica.2014.01.001
  9. Francesco Dinuzzo “Kernels for Linear Time Invariant System Identification” In SIAM Journal on Control and Optimization 53.5 Society for Industrial and Applied Mathematics, 2015, pp. 3299–3317 DOI: 10.1137/130920319
  10. “Kernel Methods for the Approximation of Nonlinear Systems” In SIAM Journal on Control and Optimization 55.4, 2017, pp. 2460–2492 DOI: 10.1137/14096815X
  11. Mohammad Khosravi and Roy S. Smith “On Robustness of Kernel-Based Regularized System Identification” In IFAC-PapersOnLine 54.7, 19th IFAC Symposium on System Identification SYSID 2021, 2021, pp. 749–754 DOI: 10.1016/j.ifacol.2021.08.451
  12. Mohammad Khosravi and Roy S. Smith “Kernel-Based Identification with Frequency Domain Side-Information” In Automatica 150, 2023, pp. 110813 DOI: 10.1016/j.automatica.2022.110813
  13. Lennart Ljung, Tianshi Chen and Biqiang Mu “A Shift in Paradigm for System Identification” In International Journal of Control 93.2 Taylor & Francis, 2020, pp. 173–180 DOI: 10.1080/00207179.2019.1578407
  14. “Robust EM Kernel-Based Methods for Linear System Identification” In Automatica 67, 2016, pp. 114–126 DOI: 10.1016/j.automatica.2016.01.036
  15. M. Gevers “Identification for Control” In Annual Reviews in Control 20, 1996, pp. 95–106 DOI: 10.1016/S1367-5788(97)00008-4
  16. Max Revay, Ruigang Wang and Ian R. Manchester “Recurrent Equilibrium Networks: Unconstrained Learning of Stable and Robust Dynamical Models” In 2021 60th IEEE Conference on Decision and Control (CDC), 2021, pp. 2282–2287 DOI: 10.1109/CDC45484.2021.9683054
  17. Max Revay, Ruigang Wang and Ian R. Manchester “A Convex Parameterization of Robust Recurrent Neural Networks” In IEEE Control Systems Letters 5.4, 2021, pp. 1363–1368 DOI: 10.1109/LCSYS.2020.3038221
  18. “Lipschitz Recurrent Neural Networks”, 2023 URL: https://openreview.net/forum?id=-N7PBXqOUJZ
  19. “Monotone Operator Equilibrium Networks” In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS’20 Red Hook, NY, USA: Curran Associates Inc., 2020, pp. 10718–10728
  20. “Contracting Implicit Recurrent Neural Networks: Stable Models with Improved Trainability” In Proceedings of the 2nd Conference on Learning for Dynamics and Control PMLR, 2020, pp. 393–403 URL: https://proceedings.mlr.press/v120/revay20a.html
  21. “Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks” In Proceedings of the 33rd International Conference on Neural Information Processing Systems Red Hook, NY, USA: Curran Associates Inc., 2019, pp. 11427–11438
  22. Henk J. Waarde and Rodolphe Sepulchre “Kernel-based models for system analysis” arXiv, 2021 arXiv: http://arxiv.org/abs/2110.11735
  23. Rodolphe Sepulchre, Thomas Chaffey and Fulvio Forni “On the incremental form of dissipativity” In IFAC-PapersOnLine 55.30, 25th International Symposium on Mathematical Theory of Networks and Systems MTNS 2022, 2022, pp. 290–294 DOI: 10.1016/j.ifacol.2022.11.067
  24. “A quantitative description of membrane current and its application to conduction and excitation in nerve” In The Journal of Physiology 117.4, 1952, pp. 500–544 URL: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1392413/
  25. Jeff S. Shamma and Rongze Zhao “Fading-memory feedback systems and robust stability” In Automatica 29.1, 1993, pp. 191–200 DOI: 10.1016/0005-1098(93)90182-S
  26. I.W. Sandberg “Approximately Finite Memory and the Circle Criterion” In IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications 41.7, 1994, pp. 473–476 DOI: 10.1109/81.298359
  27. Lukas Gonon, Lyudmila Grigoryeva and Juan-Pablo Ortega “Reservoir Kernels and Volterra Series”, 2022 arXiv: http://arxiv.org/abs/2212.14641
  28. “The identification of nonlinear discrete-time fading-memory systems using neural network models” Conference Name: IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing In IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing 41.11, 1994, pp. 740–751 DOI: 10.1109/82.331544
  29. Vern I. Paulsen and Mrinal Raghupathi “An Introduction to the Theory of Reproducing Kernel Hilbert Spaces”, Cambridge Studies in Advanced Mathematics Cambridge: Cambridge University Press, 2016 DOI: 10.1017/CBO9781316219232
  30. “Universal Kernels on Non-Standard Input Spaces” In Advances in Neural Information Processing Systems 23 Curran Associates, Inc., 2010 URL: https://papers.nips.cc/paper/2010/hash/4e0cb6fb5fb446d1c92ede2ed8780188-Abstract.html
  31. Charles A. Micchelli and Massimiliano Pontil “On Learning Vector-Valued Functions” In Neural Computation 17.1, 2005, pp. 177–204 DOI: 10.1162/0899766052530802
  32. “Universal Multi-Task Kernels” In Journal of Machine Learning Research 9.52, 2008, pp. 1615–1646 URL: http://jmlr.org/papers/v9/caponnetto08a.html
  33. “On the computational power of circuits of spiking neurons” In Journal of Computer and System Sciences 69.4, 2004, pp. 593–616 DOI: 10.1016/j.jcss.2004.04.001
  34. Paulo Lopes Santos and T-P Azevedo Perdicoúlis “A Non-Parametric LPV Approach to the Indentification of Linear Periodic Systems” In IFAC-PapersOnLine 54.8, 4th IFAC Workshop on Linear Parameter Varying Systems LPVS 2021, 2021, pp. 13–19 DOI: 10.1016/j.ifacol.2021.08.574
  35. Ehsan Sobhani Tehrani and Robert E. Kearney “A Non-Parametric Linear Parameter Varying Approach for Identification of Linear Time-Varying Systems.” In IFAC-PapersOnLine 48.28, 17th IFAC Symposium on System Identification SYSID 2015, 2015, pp. 733–738 DOI: 10.1016/j.ifacol.2015.12.217
  36. Ehsan Sobhani Tehrani and Robert E. Kearney “A Non-Parametric Approach for Identification of Parameter Varying Hammerstein Systems” In IEEE Access 10, 2022, pp. 6348–6362 DOI: 10.1109/ACCESS.2022.3141704

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Slide Deck Streamline Icon: https://streamlinehq.com

Whiteboard

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up