Electrical & Computer Engineering Colloquium
July 25, 2019 2:00 P.M.
Refreshments will be served
Physics Guided Deep Learning for Large-Scale Spatiotemporal Analysis
Qi (Rose) Yu
Khoury College of Computer Sciences
Abstract: Applications such as climate science, intelligent transportation, and aerospace control apply machine learning for large-scale spatiotemporal data. Existing deep learning models take a purely data-driven approach that fails to exploit the underlying physics principles and structures. This makes them unsuitable to domains with limited data, complex dependencies or requires stability guarantees, that are common in the spatiotemporal analysis. We show how to design physics guided deep learning models that can deal with long-term dependencies, non-linear dynamics, and multi-resolution structure. We will showcase the application of these models to problems such as long-term forecasting, long-range sequence imputation, and combating ground effect in quadcopter landing.
Bio: Dr. Yu is an Assistant Professor in the Khoury College of Computer Sciences at Northeastern University. Previously, she was a postdoctoral researcher in Caltech Computing and Mathematical Sciences. She earned her PhD in Computer Sciences at the University of Southern California and was a visiting researcher at Stanford University. Her research focuses on developing machine learning techniques for large-scale time series and spatiotemporal data. She is generally interested in the theory and applications of deep learning, tensor optimization and spatiotemporal modeling. Her work has been successfully applied to intelligent transportation, climate informatics, and aerospace control. Among her awards, she has won the best dissertation award in USC computer science, best paper award at NIPS time series workshop, and was nominated as one of the “MIT Rising Stars in EECS”.