Jet-Images -- Deep Learning Edition

TL;DR

This paper explores the use of deep learning on jet images from particle detectors to improve the identification of highly boosted W bosons, surpassing traditional methods and enhancing physics discovery potential.

Contribution

It demonstrates that deep learning architectures trained on jet images outperform traditional feature-based approaches in jet tagging tasks.

Findings

Deep learning models outperform traditional methods in jet tagging.

Visualization techniques reveal features learned by neural networks.

Enhanced sensitivity for discovering new particles and forces.

Abstract

Building on the notion of a particle physics detector as a camera and the collimated streams of high energy particles, or jets, it measures as an image, we investigate the potential of machine learning techniques based on deep learning architectures to identify highly boosted W bosons. Modern deep learning algorithms trained on jet images can out-perform standard physically-motivated feature driven approaches to jet tagging. We develop techniques for visualizing how these features are learned by the network and what additional information is used to improve performance. This interplay between physically-motivated feature driven tools and supervised learning algorithms is general and can be used to significantly increase the sensitivity to discover new particles and new forces, and gain a deeper understanding of the physics within jets.