Details

Autor(en) / Beteiligte

• Louppe, Gilles
• Cho, Kyunghyun
• Becot, Cyril
• Cranmer, Kyle

Titel

QCD-aware recursive neural networks for jet physics

Ist Teil von

• The journal of high energy physics, 2019-01, Vol.2019 (1), p.1-23, Article 57

Ort / Verlag

Berlin/Heidelberg: Springer Berlin Heidelberg

Erscheinungsjahr

2019

Link zum Volltext

Quelle

EZB Free E-Journals

Beschreibungen/Notizen

• A bstract Recent progress in applying machine learning for jet physics has been built upon an analogy between calorimeters and images. In this work, we present a novel class of recursive neural networks built instead upon an analogy between QCD and natural languages. In the analogy, four-momenta are like words and the clustering history of sequential recombination jet algorithms is like the parsing of a sentence. Our approach works directly with the four-momenta of a variable-length set of particles, and the jet-based tree structure varies on an event-by-event basis. Our experiments highlight the flexibility of our method for building task-specific jet embeddings and show that recursive architectures are significantly more accurate and data efficient than previous image-based networks. We extend the analogy from individual jets (sentences) to full events (paragraphs), and show for the first time an event-level classifier operating on all the stable particles produced in an LHC event.