Simulation-Augmented Machine Learning: Semiconductor Physics and Defect Discovery (with captions)

Abstract: In semiconductor technology development, it is desirable to pinpoint the source of defect or variation through electrical measurements, which are non-destructive and have much higher throughput than the traditional failure analysis. This can be achieved through machine learning which is a powerful tool for correlating the electrical characteristics to the nature of the defect/variation. However, a good machine is only possible with enough well-controlled training data, which is difficult to obtain experimentally. Technology Computer-Aided-Design (TCAD) and SPICE simulations which are well-calibrated to experimental data are proposed to generate the training data. In this talk, we will first demonstrate the use of TCAD to generate data to train machines to deduce the epitaxial layer thickness of Si p-i-n diodes and the work function and operating temperature variation of Ga2O3 Schottky Barrier Diodes, based solely on the measured electrical characteristics. We will emphasize the use of minimal domain expertise to obviate the difficulties in feature extraction. We will also demonstrate the techniques that are important to make the TCAD-trained machine applicable to predicting experimental data. SPICE-augmented ML will be demonstrated for detecting contact resistance degradation in inverters. Finally, we will discuss the use of TCAD-augmented machines to help reverse engineering, inverse design, and understand novel devices from hand-drawn images. Bio Hiu Yung Wong is an Associate Professor and Silicon Valley AMDT Endowed Chair in Electrical Engineering, at San Jose State University. He received his Ph.D. degree in Electrical Engineering and Computer Science from the University of California, Berkeley in 2006. From 2006 to 2009, he worked as a Technology Integration Engineer at Spansion. From 2009 to 2018, he was a TCAD Senior Staff Application Engineer at Synopsys.He received the Curtis W. McGraw Research Award from ASEE Engineering Research Council in 2022, the NSF CAREER award and the Newnan Brothers Award for Faculty Excellence in 2021, and Synopsys Excellence Award in 2010. He is the author of the book, "Introduction to Quantum Computing: From a Layperson to a Programmer in 30 Steps". He is one of the founding faculties of the Master of Science in Quantum Technology at San Jose State University.His research interests include the application of machine learning in simulation and manufacturing, cryogenic electronics, quantum computing, and wide bandgap device simulations. His works have produced 1 book, 1 book chapter, more than 100 papers, and 10 patents. Moderator: Il Young Chung, co-organizer of Quantum Computing and Data Science