ATTENTION:On Tuesday, April 1, 2025, it will not be possible to log in to Indico between 11:00 and 13:00 CEST due to maintenance of the Keycloak service. Note that existing sessions will not be affected if you log in beforehand.
For further information, please have look at the IT-News article

Choose timezone

Your profile timezone:

Use timezone based on: Event/category Custom

Select a custom timezone

Login

Scientific Computing Seminar

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

SR 2

SR 2

Description

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

Meeting ID: 612 4698 7825
password: 019962

- 14:00 → 14:35
  
  Recent Advances in Bayesian Deep Learning 35m
  
  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
- 14:35 → 15:00
  
  Discussion 25m