Towards calibrated and flexible probabilistic deep learning
Thang Bui
Thang Bui is a research scientist at Uber AI and a lecturer in Machine Learning at the University of Sydney. He has a PhD degree in Machine Learning from the Department of Engineering, University of Cambridge and a BEng from the University of Adelaide. He is broadly interested in machine learning and statistics, with a particular focus on neural networks, probabilistic models, approximate Bayesian inference, and sequential decision making under uncertainty.
Deep learning has achieved great successes in many real-world domains, ranging from vision, language to game playing. Yet, it has been shown to possess many limitations, including: (i) it is not robust to out-of-distribution inputs and (ii) it suffers from catastrophic forgetting when faced with streaming data. In this talk, I will show how we have addressed some of these limitations by combining deep learning with probabilistic modelling. This combination provides desirable test-time uncertainty estimates on out-of-distribution data and allows neural networks to be trained in an incremental way. If time permits, I will show general distributed learning, also known as federated learning, can also be handled by the same algorithmic framework.
Related seminars
Tim Baldwin
MBZUAI, The University of Melbourne
Alessio Del Bue
Italian Institute of Technology (IIT)
Dr. Xiaoming Liu
Michigan State University
Dr Lan Du
Monash University