Teaching
University of Minnesota Twin Cities
- IE 3522Quality Engineering and Six Sigma
- IE 8534Physics-Informed Machine Learning: Methodology and Applications
Lecture slides · PDF · 128 slidesPhysics-Informed Machine Learning: Methodology and PracticePDEs and forward/inverse problems, physics-informed neural networks, operator learning (graph kernel networks, Fourier neural operators, DeepONet), PDE identification, neural ODEs and the adjoint method, and differentiable physics.
- IE 3521Statistics, Quality, and Reliability
Georgia Institute of Technology
- ISYE 3133Engineering Optimization
- ISYE 7204Informatics of Production and Service SystemsDeveloped and delivered five guest lectures on physics-informed machine learning, which received excellent feedback from the students.
Tutorials and Guest Lectures
- 2026Physics-Informed Machine Learning: Methodology and Applications in Quality Science & EngineeringAdapted from the IE 8534 course material.
PDF · 67 slidesTutorial slidesPINNs, operator learning (FNO, DeepONet), derivative-informed training of neural operators, and physics-informed machine learning for inverse problems viewed as PDE-constrained optimization.
- 2026Decomposition-Based Anomaly Detection: RPCA, Robust GAN Inversion, and BeyondAt the invitation of Dr. Yuhao Zhong.
PDF · 38 slidesLecture slidesRPCA and decomposition-based anomaly detection, additive tensor decomposition and compressed smooth sparse decomposition, robust GAN inversion (RGI, R-RGI), Uni-3DAD for 3D point clouds, and the VISION workshop and datasets.