While deep learning has been revolutionary for machine learning, most modern deep learning models cannot represent their uncertainty nor take advantage of the well studied tools of probability theory. The field of Bayesian deep learning aims to change this by developing deep learning models that take advantage of Bayesian techniques and Bayesian models that incorporate deep learning elements. In Bayesian Deep Learning we develop principled tools grounded in probability theory which are also practical for real-world applications. Applications making use of Bayesian deep learning include: automatic medical diagnosis, autonomous cars, adversarial machine learning, astrophysics, and many more.

For more information, visit the Oxford Applied and Theoretical Machine Learning Group website.