Interconnect Device Modeling and Optimization with Physics-Informed Machine Learning.

Jian-Ming Jin is Y. T. Lo Chair Professor in Electrical and Computer Engineering and Director of the Electromagnetics Laboratory and Center for Computational Electromagnetics at the University of Illinois at Urbana-Champaign. He also serves as the Executive Dean of Zhejiang University-University of Illinois at Urbana-Champaign Institute. He has authored The Finite Element Method in Electromagnetics, Electromagnetic Analysis and Design in Magnetic Resonance Imaging, and Theory and Computation of Electromagnetic Fields, and co-authored Computation of Special Functions, Finite Element Analysis of Antennas and Arrays, and Fast and Efficient Algorithms in Computational Electromagnetics. He was elected by ISI among world’s most cited authors in 2002. He is a Fellow of IEEE, OSA, ACES, and Electromagnetics Academy.

Robust optimization of interconnect devices has been challenging because of the complicated electromagnetic behavior of the devices. A wide variety of optimization techniques have been proposed in the past, including search-based and gradient-based methods. All these optimization techniques are based on efficient forward solutions, which is particularly true for the search-based optimization which requires the evaluation of many designs. In the gradient-based optimization, one not only needs to provide forward solutions, but also their gradients with respect to design parameters, which are difficult to obtain. To overcome these challenges, we propose a hybrid algorithm enhanced with a machine learning approach. The hybrid algorithm combines the slow-but-global search-based method with the fast-but-local gradient descent method. To facilitate the proposed optimization scheme and improve its efficiency, we use a neural network-based surrogate model in both search and gradient descent processes. The neural network model can speed up the forward evaluation and provide analytical gradients using standard back-propagation in a very fast and accurate manner. To alleviate the computational burden associated with the time-consuming generation of training data, we further propose the use of a physics-informed machine learning model to improve modeling efficiency and reduce the training data generation cost.