Input-to-State Stable Neural Ordinary Differential Equations with Applications to Transient Modeling of Circuits
This provides incremental improvements for transient modeling in circuit design by ensuring stability and generalization.
The paper tackled the problem of learning stable and accurate behavioral models for electronic circuits by proposing input-to-state stable neural ODEs, achieving accurate reproduction of circuit behavior in commercial simulators even with unseen components.
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.