Bayesian models are rooted in Bayesian statistics and easily benefit from the vast literature in the field. In contrast, deep learning lacks a solid mathematical grounding. Instead, empirical developments in deep learning are often justified by metaphors, evading the unexplained principles at play. These two fields are perceived as fairly antipodal to each other in their respective communities. It is perhaps astonishing then that most modern deep learning models can be cast as performing approximate inference in a Bayesian setting. The implications of this are profound: we can use the rich Bayesian statistics literature with deep learning models, explain away many of the curiosities with this technique, combine results from deep learning into Bayesian modeling, and much more.
Yarin Gal shares a new theory linking Bayesian modeling and deep learning and demonstrates the practical impact of the framework with a range of real-world applications. Yarin also explores open problems for future research—problems that stand at the forefront of this new and exciting field.
Yarin Gal is a research fellow in computer science at St Catharine’s College at the University of Cambridge and a part-time fellow at the Alan Turing Institute, the UK’s national institute for data science. Yarin is working toward a PhD within the Cambridge Machine Learning group under Zoubin Ghahramani, funded by the Google Europe doctoral fellowship. Previously, he was a software engineer at IDesia Biometrics, where he developed code and UI for mobile platforms. Yarin holds an undergraduate degree in mathematics and computer science from the Open University in Israel and a master’s degree in computer science from Oxford under Phil Blunsom.
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org