Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 3: Machine-learning methods and computing in astroparticle physics

AKPIK 3.6: Vortrag

Mittwoch, 27. März 2019, 16:50–17:00, H06

Cascade Reconstruction in IceCube using Generative Neural Networks — •Mirco Huennefeld, Tobias Hoinka, Jan Soedingrekso, Sebastian Bange, and Alexander Harnisch for the IceCube collaboration — TU Dortmund, Dortmund, Deutschland

Reliable and accurate reconstruction methods are vital to the success of high-energy physics experiments such as IceCube. Machine learning based techniques, in particular deep neural networks, can provide a viable alternative to maximum-likelihood methods. Most common neural network architectures originate from non-physical domains such as image recognition. While these methods can enhance the reconstruction performance in IceCube, there is much potential for tailored techniques. In the typical physics use-case, many symmetries, invariances and prior knowledge exist in the data, which are yet to be exploited by current network architectures. Novel and specialized deep learning-based reconstruction techniques are desired which can leverage the physics potential of experiments like IceCube. A new approach using generative neural networks for the reconstruction of cascade-like events in IceCube is presented.