I started as a Ph.D. student in Nils Thuerey’s group in June 2018 after receiving my M.Sc. degree in Physics at the Technical University of Munich. I am working on differentiable simulations and am actively developing the framework Φ-Flow. My research interests lie in understanding and improving machine learning, especially models that interact with physical systems.
Contact
E-mail: philipp.holl (at) tum.de
Room: 02.13.059
Publications
- Learning to Control PDEs with Differentiable Physics, ICLR 2020.
- Deep-learning-based Pulse Shape Discrimination for Germanium Detectors, EPJC 2019.
- Holography of Wi-fi Radiation, PRL 2017.
Co-authored:
- Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers, NeurIPS 2020.
Teaching
- Summer 2021: Computer Games Laboratory
- Summer 2021: Grundlagen: Algorithmen und Datenstrukturen
- Summer 2020: Computer Games Laboratory
- Summer 2019: Grundlagen Algorithmen und Datenstrukturen
- Summer 2019: Master-Seminar – Deep Learning in Physics
- Winter 2018/19: Master-Seminar – Deep Learning in Computer Graphics