Tutorial II

Abstract - Artificial neural networks (ANNs) have long been used as data-driven surrogate models for high-speed devices and circuits, enabling analyses at a fraction of the computational cost of traditional electromagnetic (EM) solvers. Despite their success in applications such as design optimization and uncertainty quantification, conventional ANNs suffer from high training costs, overfitting, limited extrapolation capability, and the inability to enforce the underlying laws of physics. This tutorial introduces the emerging paradigm of physics-informed neural networks (PINNs), which embed governing PDEs and ODEs of target circuits directly into the training process. As a result, PINNs have shifted the state-of-the-art in artificial intelligence from data-based to physics-based techniques. In this tutorial, I will present the mathematical foundations of PINNs and demonstrate how they enable rapid, data-free training while producing physically consistent models. Using examples from signal and power integrity, I will highlight the advantages of PINNs over conventional ANNs, discuss their current limitations, and present recent advances from our Computational Modeling and Simulation laboratory at IIT Roorkee that address these challenges.

Prof. Sourajeet Roy is currently an Associate Professor at IIT Roorkee, where he continues a research and teaching career centered on high-speed electronic systems. He received his Ph.D. (2013) and M.E.Sc. (2009) in Electrical and Computer Engineering from the University of Western Ontario, and a B.Tech (2006) in Electrical and Electronics Engineering from Sikkim Manipal University, giving him a strong foundation across both applied and theoretical aspects of the field. He was an Assistant Professor at Colorado State University from 2013 to 2018, where he built an active research program in signal and power integrity, before joining IIT Roorkee as Associate Professor in 2023 to continue his academic work in India. His research covers numerical modeling and simulation of high-speed devices and circuits, uncertainty quantification, stochastic modeling and reliability analysis, carbon nanotube interconnects, and CAD for signal and power integrity analysis, all of which are directly relevant to his tutorial topic. This breadth of expertise allows him to bridge circuit-level modeling with device-level physical phenomena in practical engineering settings. He is an Associate Editor for IEEE Transactions on Components, Packaging, and Manufacturing Technology, a role in which he helps guide the peer review of leading research in the field.