Jet Charge and Machine Learning

TL;DR

This paper demonstrates that advanced neural network architectures, including CNNs, RNNs, and recursive networks, significantly improve jet charge classification at the LHC by effectively utilizing jet distance information.

Contribution

It introduces neural network approaches that incorporate jet distance data, outperforming traditional methods in jet charge classification at high-energy colliders.

Findings

Neural networks outperform traditional methods in jet charge extraction.

Distance information within jets enhances classification accuracy.

Both CNNs and RNNs are promising for future collider data analysis.

Abstract

Modern machine learning techniques, such as convolutional, recurrent and recursive neural networks, have shown promise for jet substructure at the Large Hadron Collider. For example, they have demonstrated effectiveness at boosted top or W boson identification or for quark/gluon discrimination. We explore these methods for the purpose of classifying jets according to their electric charge. We find that both neural networks that incorporate distance within the jet as an input and boosted decision trees including radial distance information can provide significant improvement in jet charge extraction over current methods. Specifically, convolutional, recurrent, and recursive networks can provide the largest improvement over traditional methods, in part by effectively utilizing distance within the jet or clustering history. The advantages of using a fixed-size input representation (as with the CNN) or a small input representation (as with the RNN) suggest that both convolutional and recurrent networks will be essential to the future of modern machine learning at colliders.