Kurzbeschreibung
GPU Cluster der Forschungsgruppe "Mathematische Datenwissenschaften" der Universität Wien
Ansprechperson
Philipp Grohs
Research Services
HPC - Node für die Forschung im Bereich "mathematical data science".
Vorhandene Ausstattung: 8x NVIDIA A100 GPU node, 128 CPUs, 1TB RAM
Kontakt unter: philipp.grohs@univie.ac.at
Methoden & Expertise zur Forschungsinfrastruktur
High Performance Computing Simulationen unter Zuhilfenahme moderner Methoden aus dem Maschinellen Lernen
Kontakt unter: philipp.grohs@univie.ac.at
Towards a transferable fermionic neural wavefunction for molecules,
Michael Scherbela, Leon Gerard, Philipp Grohs,
Nature Communications volume 15, Article number: 120 (2024)
https://www.nature.com/articles/s41467-023-44216-9
Solving the electronic Schrödinger equation for multiple nuclear geometries with weight-sharing deep neural networks,
Michael Scherbela, Rafael Reisenhofer, Leon Gerard, Philipp Marquetand, Philipp Grohs
Nature Computational Science volume 2, pages 331–341 (2022)
https://www.nature.com/articles/s43588-022-00228-x
Gold-standard solutions to the Schrödinger equation using deep learning: How much physics do we need?
Leon Gerard, Michael Scherbela, Philipp Marquetand, Philipp Grohs
Advances in Neural Information Processing Systems 35 (NeurIPS 2022)
https://proceedings.neurips.cc/paper_files/paper/2022/hash/430894999584d0bd358611e2ecf00b15-Abstract-Conference.html
Michael Scherbela, Leon Gerard, Philipp Grohs,
Nature Communications volume 15, Article number: 120 (2024)
https://www.nature.com/articles/s41467-023-44216-9
Solving the electronic Schrödinger equation for multiple nuclear geometries with weight-sharing deep neural networks,
Michael Scherbela, Rafael Reisenhofer, Leon Gerard, Philipp Marquetand, Philipp Grohs
Nature Computational Science volume 2, pages 331–341 (2022)
https://www.nature.com/articles/s43588-022-00228-x
Gold-standard solutions to the Schrödinger equation using deep learning: How much physics do we need?
Leon Gerard, Michael Scherbela, Philipp Marquetand, Philipp Grohs
Advances in Neural Information Processing Systems 35 (NeurIPS 2022)
https://proceedings.neurips.cc/paper_files/paper/2022/hash/430894999584d0bd358611e2ecf00b15-Abstract-Conference.html