Share Email Print
cover

Proceedings Paper • new

Tracking with deep neural networks
Author(s): Marcin Kucharczyk; Marcin Wolter
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

High Energy Physics experiments require fast and efficient methods to reconstruct the tracks of charged particles. Commonly used algorithms are sequential and the CPU required increases rapidly with a number of tracks. Neural networks can speed up the process due to their capability to model complex non-linear data dependencies and finding all tracks in parallel.

In this paper we describe the application of the Deep Neural Network to the reconstruction of straight tracks in a toy two and three-dimensional models. It is planned to apply this tracking method to the experimental data taken by the MUonE experiment at CERN.

Paper Details

Date Published: 6 November 2019
PDF: 11 pages
Proc. SPIE 11176, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, 111764H (6 November 2019); doi: 10.1117/12.2538197
Show Author Affiliations
Marcin Kucharczyk, Institute of Nuclear Physics (Poland)
Marcin Wolter, Institute of Nuclear Physics (Poland)


Published in SPIE Proceedings Vol. 11176:
Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019
Ryszard S. Romaniuk; Maciej Linczuk, Editor(s)

© SPIE. Terms of Use
Back to Top