Speaker
Description
Jets are important structures observed in high-energy physics for its wide range of uses, including investigations of electro-weak interactions and Beyond the Standard Model physics, among several other applicabilities. Likewise, in recent years the use of neural networks and other machine learning and artifficial intelligence (AI) methods in high-energy physics has rapidly expanded because of its great versatility. One of the known studies that serves as a intersection between the two subjects is the use of neural networks in jet tagging applications. This study explores a convolutional neural network (CNN) based approach to classify events produced in high-energy collisions by differentiating between events with the presence of heavy quark (charm, bottom), light quark (up, down, strange), and gluon jets, with the main characteristic being that jets are not reconstructed in our approach. The method constructs image-like representations based on the kinematics of charged decay products using detector-level variables, which allow CNNs to identify visual patterns characteristic of each jet type. This approach not only demonstrate strong classification performance, highlighting the versatility of CNN architectures in jet tagging, but also reveals the abillity of AI methods to observe jet structures and differentiate between them even in the absence of jet reconstruction.
| I read the instructions above | Yes |
|---|