Quantum convolutional neural networks for high energy physics
Date
2022-09-05
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Benemérita Universidad Autónoma de Puebla
Abstract
"Artificial Intelligence is a tool that is increasingly becoming an integral element of scientific research. High Energy Physics, whose experiments produce some of the largest amounts of data in science, is no exception. For this reason, the objective of this thesis is to develop a pipeline for classifying backgrounds and signals particle jets using Machine Learning (ML) techniques, specifically convolutional neural networks (CNN). Particle jets have proven to be a very powerful tool for studying particle collisions at accelerators such as CMS and ATLAS, at the LHC, where the constituents of these events hadronize or decay so quickly that they are very difficult to detect. Jets are objects that seek to retrieve information about these particles by encapsulating the energy depositions that were indeed sensed by the detector. So having an algorithm that can reliably tell us which particle generated a given jet is not a straightforward assignment, even more so taking into account that many approaches can be taken to this problem depending on the way in which we believe it is most convenient to arrange our data".
Description
Keywords
Citation
Collections
Document Viewer
Select a file to preview:
Can't see the file? Try reloading