Sebastian Nowozin is currently a Researcher at Microsoft Research Cambridge. His research focuses on probabilistic deep learning, consequences of model misspecification, understanding agent complexity in order to improve learning efficiency, and designing  models for reasoning and planning.

His PhD thesis is titled "Learning with Structured Data: Applications to Computer Vision", which he completed in 2009. We discuss the work in his thesis on structured inputs and  structured outputs, which involves  beautiful ideas from polyhedral combinatorics and optimization. We  talk about his recent work on Bayesian deep learning and the connections it has to ideas that he explored during his PhD.

Episode notes: https://cs.nyu.edu/~welleck/episode4.html

Follow the Thesis Review (@thesisreview) and Sean Welleck (@wellecks) on Twitter, and find out more info about the show at https://cs.nyu.edu/~welleck/podcast.html

[04] Sebastian Nowozin - Learning with Structured Data: Applications to Computer Vision

Each episode of The Thesis Review is a conversation centered around a researcher's PhD thesis, giving insight into their history, revisiting older ideas, and providing a valuable perspective on how their research has evolved (or stayed the same) since.