no code implementations • 1 Jun 2021 • Friedrich Bethke, Richard Pausch, Patrick Stiller, Alexander Debus, Michael Bussmann, Nico Hoffmann
Invertible neural networks are a recent technique in machine learning promising neural network architectures that can be run in forward and reverse mode.
1 code implementation • 8 Sep 2020 • Patrick Stiller, Friedrich Bethke, Maximilian Böhme, Richard Pausch, Sunna Torge, Alexander Debus, Jan Vorberger, Michael Bussmann, Nico Hoffmann
However, recent numerical solvers require manual discretization of the underlying equation as well as sophisticated, tailored code for distributed computing.