2016/07/31 by Daniel Guest, Julian Collado, Pierre Baldi +5 · 4 citations
Engineering · Physics and Astronomy · #Artificial intelligence #Artificial neural network #Computer science #Curse of dimensionality #Deep learning #Deep neural networks #Dimensionality reduction #Engineering #Graph #High-Energy Particle Collisions Research #Jet (fluid) #Machine learning #Particle Detector Development and Performance #Particle physics #Particle physics theoretical and experimental studies #Pattern recognition (psychology) #Physics #Task (project management) #Theoretical computer science #Tracking (education) #Vertex (graph theory) #hep-ex #physics.data-an
paper · pdf · doi:10.1103/physrevd.94.112002
published as Phys. Rev. D 94, 112002 (2016) · 12 pages, submitted to PRD
openalex created_date 2016/08/23 · arxiv created 2016/09/08 · openalex publication_date 2016/12/02 · arxiv updated 2016/12/07 · openalex updated_date 2026/08/06
Classification of jets as originating from light-flavor or heavy-flavor quarks is an important task for inferring the nature of particles produced in high-energy collisions. The large and variable dimensionality of the data provided by the tracking detectors makes this task difficult. The current state-of-the-art tools require expert data reduction to convert the data into a fixed low-dimensional form that can be effectively managed by shallow classifiers. We study the application of deep networks to this task, attempting classification at several levels of data, starting from a raw list of tracks. We find that the highest-level lowest-dimensionality expert information sacrifices information needed for classification, that the performance of current state-of-the-art taggers can be matched or slightly exceeded by deep-network-based taggers using only track and vertex information, that classification using only lowest-level highest-dimensionality tracking information remains a difficult task for deep networks, and that adding lower-level track and vertex information to the classifiers provides a significant boost in performance compared to the state of the art.