Title: Application of deep learning to the reconstruction of electron tracks in the CMS experiment
Other Titles: Anwendung von Deep Learning auf die Rekonstruktion von Elektron-Spuren im CMS-Experiment
Language: English
Authors: Loesener, Martin Eduard Michael 
Qualification level: Diploma
Advisor: Frühwirth, Rudolf 
Issue Date: 2019
Number of Pages: 79
Qualification level: Diploma
This work proposes an implementation of a Deep Regression model for the purpose of predicting electron track parameters from collision events at the CMS Experiment at CERN. It is entirely written in Python, one of the most popular programming languages in the field of machine learning, and makes use of PyTorch, a cutting-edge Deep Learning framework, widely known for its dynamic graph structure. Several architectures were used, including the base architecture proposed by Bernkopf (Masters Thesis in preparation) and convolutional neural networks. They were trained and tested using a variety of algorithms and hyper-parameters to assess their performance. A training error reduction of a factor 2 to 3.5 was achieved with respect to the baseline, depending on the parameter. With under 5k network parameters the model offers a light-weight and precise tool to predict electron tracks. With automated predictions of streaming particle track data in mind, a possible bottleneck regarding data imports using different data formats was tested.

Keywords: Electron reconstruction; deep learning
URI: https://resolver.obvsg.at/urn:nbn:at:at-ubtuw:1-124389
Library ID: AC15360965
Organisation: E105 - Institut für Stochastik und Wirtschaftsmathematik 
Publication Type: Thesis
Appears in Collections:Thesis

Files in this item:

Show full item record

Page view(s)

checked on Jun 16, 2021


checked on Jun 16, 2021

Google ScholarTM


Items in reposiTUm are protected by copyright, with all rights reserved, unless otherwise indicated.