IML Machine Learning Working Group

6/2-024 - BE Auditorium Meyrin (CERN)

6/2-024 - BE Auditorium Meyrin


Show room on map
IML Machine Learning Working Group
Zoom Meeting ID
Simon Akar
Alternative hosts
Riccardo Torre, Fabio Catalano
Useful links
Join via phone
Zoom URL
    • 3:00 PM 3:05 PM
      News 5m
      Speakers: Anja Butter (Centre National de la Recherche Scientifique (FR)), Fabio Catalano (CERN), Julian Garcia Pardinas (CERN), Lorenzo Moneta (CERN), Michael Kagan (SLAC National Accelerator Laboratory (US)), Dr Pietro Vischia (Universidad de Oviedo and Instituto de Ciencias y Tecnologías Espaciales de Asturias (ICTEA)), Stefano Carrazza (CERN)
    • 3:05 PM 3:25 PM
      A Deep Learning Approach to Proton Background Rejection for Positron Analysis with the AMS Electromagnetic Calorimeter 20m

      The Alpha Magnetic Spectrometer (AMS) is a high-precision particle detector onboard the International Space Station containing six different subdetectors. The Transition Radiation Detector and Electromagnetic Calorimeter (ECAL) are used to separate electrons/positrons from the abundant cosmic-ray proton background.

      The positron flux measured in space by AMS falls with a power law which unexpectedly softens above 25 GeV and then hardens above 280 GeV. Several theoretical models try to explain these phenomena, and a purer measurement of positrons at higher energies is needed to help test them. The currently used methods to reject the proton background at high energies involve extrapolating shower features from the ECAL to use as inputs for boosted decision tree and likelihood classifiers.

      We present a new approach for particle identification with the AMS ECAL using deep learning (DL). By taking the energy deposition within all the ECAL cells as an input and treating them as pixels in an image-like format, we train an MLP, a CNN, and multiple ResNets and Convolutional vision Transformers (CvTs) as shower classifiers. Proton rejection performance is evaluated using Monte Carlo (MC) events and AMS data separately. For MC, using events with a reconstructed energy between 0.2 – 2 TeV, at 90% electron accuracy, the proton rejection power of our CvT model is more than 5 times that of both the other DL models and the AMS models. Similarly, for AMS data with a reconstructed energy between 50 – 70 GeV, the proton rejection power of our CvT model is more than 2.5 times that of the AMS models.

      Speaker: Raheem Hashmani (Middle East Technical University (TR))
    • 3:25 PM 3:30 PM
      Questions 5m
    • 3:30 PM 3:50 PM
      Particle-flow End-to-end reconstruction for Highly Granular Calorimeters 20m
      Speakers: Mr Philipp Zehetner (Ludwig Maximilians Universitat (DE)), Shah Rukh Qasim (CERN)
    • 3:50 PM 3:55 PM
      Questions 5m
    • 3:55 PM 4:15 PM
      Jet Diffusion versus JetGPT -- Modern Networks for the LHC 20m

      We introduce two diffusion models and an autoregressive transformer for LHC physics simulations. Bayesian versions allow us to control the networks and capture training uncertainties. After illustrating their different density estimation methods for simple toy models, we discuss their advantages for Z plus jets event generation. While diffusion networks excel through their precision, the transformer scales best with the phase space dimensionality. Given the different training and evaluation speed, we expect LHC physics to benefit from dedicated use cases for normalizing flows, diffusion models, and autoregressive transformers.

      Speaker: Nathan Huetsch (University of Heidelberg)
    • 4:15 PM 4:20 PM
      Questions 5m