Jul 6 – 8, 2021
Europe/Zurich timezone

Shared Data and Algorithms for Deep Learning in Fundamental Physics

Jul 7, 2021, 8:20 PM


William Korcari (Hamburg University (DE))


We introduce a collection of datasets from fundamental physics research including particle physics, astroparticle physics, hadron, and nuclear physics for supervised machine learning studies. These datasets, containing hadronic top quarks, cosmic air showers, phase transitions in the hadronic matter, and generator-level histories, are combined and made public to simplify future work on cross-disciplinary machine learning and transfer learning in fundamental physics. Based on these samples, we present two simple and yet flexible models: a fully connected neural network and a graph-based neural network architecture that can easily be applied to a wide range of supervised learning tasks in these domains. Furthermore, we show that our approaches reach performance close to state-of-the-art dedicated methods on all datasets.

Affiliation Hamburg University
Academic Rank PhD student

Primary authors

William Korcari (Hamburg University (DE)) Lisa Benato (Hamburg University (DE)) Erik Buhmann (Hamburg University (DE)) Martin Erdmann (Rheinisch Westfaelische Tech. Hoch. (DE)) Peter Fackelday Jonas Glombitza (RWTH AACHEN UNIVERSITY) Nikolai Hartmann (Ludwig Maximilians Universitat (DE)) Gregor Kasieczka (Hamburg University (DE)) Thomas Kuhr (Ludwig Maximilians Universitat (DE)) Tilman Plehn (Heidelberg University) Jan Steinheimer Horst Stoecker (GSi) Kai Zhou (FIAS, Goethe-University Frankfurt am Main)

Presentation materials