TabNet for Jet Flavor Tagging: A Machine Learning Approach

Home Page
About
Submit A Journal
Submit A Conference
Submit Paper/Book
- Submit a Preprint
- Submit a Book
Contact

Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi
Cilt: 12 Sayı: 2
TabNet for Jet Flavor Tagging: A Machine Learning Approach

TabNet for Jet Flavor Tagging: A Machine Learning Approach

Pages : 589-599

View : 44 | Download : 117

Publication Date : 2025-11-30

Article Type : Research Paper

Abstract :Jets, collimated particle sprays from high-energy collisions, are abundant at the Large Hadron Collider and critical for studying fundamental interactions. This study addresses the classification of hadronically decaying top quark jets and light quark or gluon jets using TabNet algorithm with leveraging low-level kinematic features of the jet constituents such as energy, transverse momentum, and components. To handle the high dimensionality of the data, Principal Component Analysis is applied for dimensionality reduction, while TabNet’s attention-based mechanism dynamically selects relevant features. The model achieves exceptional performance, with an accuracy of 99.98%, a recall of 99.97%, and an AUC of 1.0, demonstrating an outstanding classification performance.
Keywords : Derin Öğrenme, Tabnet, Üst Kuark Etiketleme

ORIGINAL ARTICLE URL

* There may have been changes in the journal, article,conference, book, preprint etc. informations. Therefore, it would be appropriate to follow the information on the official page of the source. The information here is shared for informational purposes. IAD is not responsible for incorrect or missing information.