Physics-Informed Neural Networks for Device and Circuit Modeling: A Case Study of NeuroSPICE
By: Chien-Ting Tung, Chenming Hu
We present NeuroSPICE, a physics-informed neural network (PINN) framework for device and circuit simulation. Unlike conventional SPICE, which relies on time-discretized numerical solvers, NeuroSPICE leverages PINNs to solve circuit differential-algebraic equations (DAEs) by minimizing the residual of the equations through backpropagation. It models device and circuit waveforms using analytical equations in time domain with exact temporal derivatives. While PINNs do not outperform SPICE in speed or accuracy during training, they offer unique advantages such as surrogate models for design optimization and inverse problems. NeuroSPICE's flexibility enables the simulation of emerging devices, including highly nonlinear systems such as ferroelectric memories.
Similar Papers
Physics-Informed Neural Networks in Power System Dynamics: Improving Simulation Accuracy
Systems and Control
Makes power grid simulations run much faster.
Spectral-Prior Guided Multistage Physics-Informed Neural Networks for Highly Accurate PDE Solutions
Numerical Analysis
Makes computer models of science more accurate.
Applications and Manipulations of Physics-Informed Neural Networks in Solving Differential Equations
Machine Learning (CS)
Solves hard math problems using smart computer brains.