Uncertainty estimation is essential to design robust and reliable systems, but this usually requires more effort to implement and execute compared to maximum-likelihood methods. In this talk, I will summarize some of our recent work that enables fast and scalable estimation of uncertainty using deep models, such as Bayesian neural network. The main feature of our method is that they are extremely easy to implement within existing deep-learning softwares. I will also summarize some of the current challenges faced by the Bayesian deep-learning community and how real-world applications can be useful for our research.
Emtiyaz is a team leader (equivalent to Full Professor) at the RIKEN center for Advanced Intelligence Project (AIP) in Tokyo where he leads the Approximate Bayesian Inference (ABI) Team. From April 2018, Emtiyaz was a visiting professor at the EE department in Tokyo University of Agriculture and Technology (TUAT), and also a part-time lecturer at Waseda University. Emtiyaz is an Action Editor for the Journal of Machine Learning (JMLR). From 2014 to 2016, he was a scientist at EPFL in Matthias Grossglausser’s lab. During his time at EPFL, he taught two large machine learning courses for which he received a teaching award. Emtiyaz first joined EPFL as a post-doc with Matthias Seeger in 2013 and before that he finished his PhD at UBC in 2012 under the supervision of Kevin Murphy.