Input-to-State Stable Neural Ordinary Differential Equations with Applications to Transient Modeling of Circuits

Abstract

This paper proposes a class of neural ordinary differential equations parametrized by provably input-to-state stable continuous-time recurrent neural networks. The model dynamics are defined by construction to be input-to-state stable (ISS) with respect to an ISS-Lyapunov function that is learned jointly with the dynamics. We use the proposed method to learn cheap-to-simulate behavioral models for electronic circuits that can accurately reproduce the behavior of various digital and analog circuits when simulated by a commercial circuit simulator, even when interconnected with circuit components not encountered during training. We also demonstrate the feasibility of learning ISS-preserving perturbations to the dynamics for modeling degradation effects due to circuit aging.

Cite

Text

Yang et al. "Input-to-State Stable Neural Ordinary Differential Equations with Applications to Transient Modeling of Circuits." Proceedings of The 4th Annual Learning for Dynamics and Control Conference, 2022.

Markdown

[Yang et al. "Input-to-State Stable Neural Ordinary Differential Equations with Applications to Transient Modeling of Circuits." Proceedings of The 4th Annual Learning for Dynamics and Control Conference, 2022.](https://mlanthology.org/l4dc/2022/yang2022l4dc-inputtostate/)

BibTeX

@inproceedings{yang2022l4dc-inputtostate,
  title     = {{Input-to-State Stable Neural Ordinary Differential Equations with Applications to Transient Modeling of Circuits}},
  author    = {Yang, Alan and Xiong, Jie and Raginsky, Maxim and Rosenbaum, Elyse},
  booktitle = {Proceedings of The 4th Annual Learning for Dynamics and Control Conference},
  year      = {2022},
  pages     = {663-675},
  volume    = {168},
  url       = {https://mlanthology.org/l4dc/2022/yang2022l4dc-inputtostate/}
}