Deep-learned Top Tagging with a Lorentz Layer

TL;DR

This paper presents a novel deep neural network-based top quark tagger utilizing Lorentz vectors and Minkowski metric, enhancing identification of boosted top quarks by integrating calorimeter and tracking data.

Contribution

It introduces a new deep learning architecture with a Lorentz layer for top tagging, improving performance over existing methods.

Findings

Significantly better performance for boosted top quark identification.

Effective integration of calorimeter and tracking information.

Outperforms QCD-inspired and image-recognition approaches.

Abstract

We introduce a new and highly efficient tagger for hadronically decaying top quarks, based on a deep neural network working with Lorentz vectors and the Minkowski metric. With its novel machine learning setup and architecture it allows us to identify boosted top quarks not only from calorimeter towers, but also including tracking information. We show how the performance of our tagger compares with QCD-inspired and image-recognition approaches and find that it significantly increases the performance for strongly boosted top quarks.