1 code implementation • CVPR 2023 • Oleksandr Balabanov, Bernhard Mehlig, Hampus Linander
We introduce ensembles of stochastic neural networks to approximate the Bayesian posterior, combining stochastic methods such as dropout with deep ensembles.
1 code implementation • 8 Aug 2018 • Jens Krog, Mohammadreza Alizadehheidari, Erik Werner, Santosh Kumar Bikkarolla, Jonas O. Tegenfeldt, Bernhard Mehlig, Michael A. Lomholt, Fredrik Westerlund, Tobias Ambjornsson
The estimated friction coefficient is in agreement with theoretical estimates for motion of a cylinder in a channel.
Biological Physics Mesoscale and Nanoscale Physics
no code implementations • 9 Jul 1998 • Thomas Dittrich, Gert Koboldt, Bernhard Mehlig, Holger Schanz
Its only free parameter is the characteristic time of exchange between the cells in units of the Heisenberg time.