PhD scholarship in large-scale Bayesian deep learning - DTU Compute

Job description

Do you want to figure out why Bayesian deep learning doesn’t work? And afterwards fix it? At DTU Compute we are working towards building highly scalable Bayesian approximations that actually work for deep learning. The driving approach is to first figure out the root cause of why the usual tricks do not work, and then secondly fix the issues. You will join a highly motivated and collaborative team under the supervision of Søren Hauberg. The research environment favors creative ‘slow thinking’ style research, and we emphasize having fun along the way. Our work is consistently published at the top venues of machine learning research. Responsibilities and qualifications: You should have prior experience with machine learning from both a theoretical and practical perspective. Experience in one of the following topics will be appreciated, but mostly we look for smart people who enjoy learning new things: We tend to work in teams, so a collaborative spirit is required. You must have a two-year master's degree (120 ECTS points) or a similar degree with an academic level equivalent to a two-year master's degree. - Approximate Bayesian inference - Differential geometry - Numerical computati...