no code implementations • 24 May 2024 • Peter Lippmann, Gerrit Gerhartz, Roman Remme, Fred A. Hamprecht
In many applications of geometric deep learning, the choice of global coordinate frame is arbitrary, and predictions should be independent of the reference frame.
no code implementations • 8 May 2023 • Roman Remme, Tobias Kaczun, Maximilian Scheurer, Andreas Dreuw, Fred A. Hamprecht
We here set out to learn the kinetic energy functional from ground truth provided by the more expensive Kohn-Sham density functional theory.
no code implementations • ICLR 2020 • Nasim Rahaman, Steffen Wolf, Anirudh Goyal, Roman Remme, Yoshua Bengio
We humans have an innate understanding of the asymmetric progression of time, which we use to efficiently and safely perceive and manipulate our environment.
no code implementations • 2 Jul 2019 • Nasim Rahaman, Steffen Wolf, Anirudh Goyal, Roman Remme, Yoshua Bengio
We humans seem to have an innate understanding of the asymmetric progression of time, which we use to efficiently and safely perceive and manipulate our environment.