Artificial Intelligence

Bayesian Inference with Deep Generative Algorithms

Friday, May 08, 2020, 2:00pm - 3:00pm PDTiCal
This event is open to the public.
AI Seminar
Professor Assad Oberai, USC

If you are not the speaker, please make sure to turn off audio and video when entering a room. 

If you would like to raise a question for the Q&A time, please click Chat function in the meeting controls. This will open the chat option on the right. You can type a message into the chat box and wait for the Speaker to respond before the end of the session.

Key Words: Bayesian Inference, Deep Generative Algorithms, Inverse Problems, Computer Vision

Abstract: Generative adversarial networks (GANs) have demonstrated a remarkable ability to learn the underlying distribution of a complex field from a collection of its samples. In doing so, these networks also reduce the dimension of the field by generating samples from a vector space of smaller dimension. In this talk I will explore the use of GANs as priors in a Bayesian inference problem. When viewed from this perspective, they provide the ability to efficiently generate sample-based priors and to quantify uncertainty in an inference problem. We will discuss the utility of this approach and provide examples that are motivated physics-based inference problems, problems in computer vision that include de-noising, in-painting and anomaly detection (the so-called out-of-distribution detection problem).

Biosketch:  Assad Oberai is the vice Dean for Research and a Professor of Aerospace and Mechanical Engineering in the Viterbi school of engineering. He earned a Bachelor of Engineering degree from Osmania University (India) in 1992, an MS from the University of Colorado in 1994, and a PhD from Stanford University in 1998, all in Mechanical Engineering.  He was an Assistant Professor at Boston University (2001-2005), and Rensselaer Polytechnic Institute (RPI) in 2006. At RPI, he was the Associate Dean for Research and Graduate Studies in the School of Engineering, and the Associate Director of the Scientific Computation Research Center. He joined USC in January 2018. 
Assad leads the Computation and Data Driven Discovery (CD3) group which designs, implements and applies data- and physics-based models and algorithms to solve problems in engineering and science. Problems such as better detection, diagnosis and care of diseases like cancer, understanding the role of mechanics and physics in medicine and biology, modeling the evolution of multi-physics and multiscale systems, and reduced-order models for aerospace and mechanical systems. He has authored more than 100 articles in archival journals on these topics. He is on the board of academic editors for three journals.

Assad is a Fellow of the American Society of Mechanical Engineers (ASME, 2020), the American Institute of Medical and Biological Engineering (AIMBE, 2016), and the United States Association of Computational Mechanics (USACM, 2015).  In 2015 he was awarded the Research Excellence Award by the School of Engineering at Rensselaer. He received the Humboldt Foundation Award for experienced researchers in 2009, and the Erasmus Mundus Master Course Lectureship at Universidad Politécnica de Cataluña, Barcelona in 2010. He was awarded the Thomas J.R. Hughes Young Investigator Award for his contributions to Applied Mechanics by the ASME in 2007. He is a recipient of the National Science Foundation Career award in 2005 and the Department of Energy Early Career award in 2004.

« Return to Events