Jul 6 – 8, 2021
Europe/Zurich timezone

Generative Networks with Uncertainties


Michel Luchmann Tilman Plehn


We show how Bayesian neural networks can be used to estimate uncertainties associated with regression, classification, and now also generative networks. For generative INNs, the combination of the learned density and uncertainty maps also provide insights into how these networks learn. These results show that criticizing the use of neural networks in LHC physics as black boxes is a sociological rather than scientific statement.

Primary authors

Manuel Haußmann (Universität Heidelberg) Marco Bellagente (Universität Heidelberg) Michel Luchmann Tilman Plehn

Presentation materials