Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Deep Neural Networks for Particle Identification in Simulated Proton-Proton Collisions at LHC and RHIC
Particle identification is an essential part of experimental high-energy physics, which allows the study of the most fundamental constituents of matter. This thesis explores the use of deep neural networks for identifying particles in simulated proton-proton collisions at the Large Hadron Collider (...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
AUC Knowledge Fountain
2025
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| Summary: | Particle identification is an essential part of experimental high-energy physics, which allows the study of the most fundamental constituents of matter. This thesis explores the use of deep neural networks for identifying particles in simulated proton-proton collisions at the Large Hadron Collider (LHC) and the Relativistic Heavy Ion Collider (RHIC). The deep neural networks were trained on LHC datasets which have various momentum ranges including regions of high transverse momentum above 3 GeV/c. The key findings of thesis include achieving an accuracy of 99.99%, 98.3%, and 90.14% for 3-5 pt, 5-7 pt and above 7 pt regions respectively for the LHC dataset. Another important finding is that the network generalizes perfectly to the RHIC set (lower center of mass energy) and achieves an accuracy of 99.99% for a regular test set. This thesis highlights the huge potential of neural networks in particle identification, even with relatively simple architectures like multilayer perceptron. Further modifications of the network’s structure can yield even higher accuracies, particularly for the critical high momentum regions. |
|---|