| Time: | October 11, 2024, 9:00 a.m. – 9:45 a.m. |
|---|---|
| Lecturer: | Prof. Dr. Tristan Bereau, Universität Heidelberg |
| Venue: | ICP Seminarraum 1.079 Allmandring 3 70569 Vaihingen |
| Download as iCal: |
|
Generative machine learning in multiscale molecular simulations
Generative machine learning is offering new possibilities in various scientific fields. I will describe recent efforts in the context of multiscale molecular simulations: the basin structure of a complex free-energy landscape for dimensionality reduction; a backmapping strategy that learns the atomistic distribution of atoms conditional on the coarse-grained degrees of freedom; and finally a diffusion model to efficiently compute free energies.