Scientific Computing Seminar

Friday 28 Mar 2025, 14:00 → 15:00 Europe/Berlin

SR 2

https://desy.zoom.us/j/61246987825

Meeting ID: 612 4698 7825
password: 019962

1 Recent Advances in Bayesian Deep Learning

Combining Bayesian principles with the power of deep learning has long been an attractive direction of research, but its real-world impact has fallen short of the promises. Especially in the context of uncertainty estimation, there seem to be simpler methods that perform at least as well. In this talk, I want to argue that uncertainties are not the only reason to use Bayesian deep learning models, but that they also offer improved model selection and incorporation of prior knowledge. I will showcase these benefits supported by the results of two recent papers and situate them in the context of current research trends in Bayesian deep learning.

Speaker: Vincent Fortuin (TU Munich)

advances_in_BDL.pdf

2 Discussion