1 code implementation • 13 Mar 2024 • Tim Rensmeyer, Oliver Niggemann
Achieving robust uncertainty quantification for deep neural networks represents an important requirement in many real-world applications of deep learning such as medical imaging where it is necessary to assess the reliability of a neural network's prediction.
no code implementations • 18 Dec 2023 • Willi Grossmann, Sebastian Eilermann, Tim Rensmeyer, Artur Liebert, Michael Hohmann, Christian Wittke, Oliver Niggemann
In this way, the most complex physical relationships can be considered and quickly described.
no code implementations • 5 Apr 2023 • Tim Rensmeyer, Benjamin Craig, Denis Kramer, Oliver Niggemann
Even though Bayesian neural networks offer a promising framework for modeling uncertainty, active learning and incorporating prior physical knowledge, few applications of them can be found in the context of interatomic force modeling.