no code implementations • 27 May 2021 • Philipp Joppich, Sebastian Dorn, Oliver De Candido, Wolfgang Utschick, Jakob Knollmüller
This constitutes a statistical inference task in terms of the optimal latent space activations of the underlying uncorrupted datum.
no code implementations • 12 Feb 2020 • Philipp Arras, Philipp Frank, Philipp Haim, Jakob Knollmüller, Reimar Leike, Martin Reinecke, Torsten Enßlin
Observing the dynamics of compact astrophysical objects provides insights into their inner workings, thereby probing physics under extreme conditions.
Instrumentation and Methods for Astrophysics Astrophysics of Galaxies
no code implementations • 29 Jan 2020 • Jakob Knollmüller, Torsten Enßlin
We showed how to use trained neural networks to perform Bayesian reasoning in order to solve tasks outside their initial scope.
2 code implementations • 30 Jan 2019 • Jakob Knollmüller, Torsten A. Enßlin
We propose Metric Gaussian Variational Inference (MGVI) as a method that goes beyond mean-field.
no code implementations • 11 Dec 2018 • Jakob Knollmüller, Torsten A. Enßlin
This transformation is a special form of the reparametrization trick, flattens the hierarchy and leads to a standard Gaussian prior on all resulting parameters.
no code implementations • 26 Dec 2016 • Torsten A. Enßlin, Jakob Knollmüller
The inference of correlated signal fields with unknown correlation structures is of high scientific and technological relevance, but poses significant conceptual and numerical challenges.