Jet Flavour Classification Using DeepJet

TL;DR

DeepJet is a novel deep learning architecture that significantly improves jet flavour classification and quark-gluon tagging performance in high-energy physics experiments by overcoming previous input size limitations.

Contribution

The paper introduces DeepJet, a new deep learning model that enhances jet flavour classification and extends to quark-gluon tagging, addressing previous input size constraints.

Findings

Improved heavy flavour classification accuracy.

Extended capabilities to quark-gluon tagging.

Overcame input size limitations of prior models.

Abstract

Jet flavour classification is of paramount importance for a broad range of applications in modern-day high-energy-physics experiments, particularly at the LHC. In this paper we propose a novel architecture for this task that exploits modern deep learning techniques. This new model, called DeepJet, overcomes the limitations in input size that affected previous approaches. As a result, the heavy flavour classification performance improves, and the model is extended to also perform quark-gluon tagging.