Login

Calorimeter Machine Learning

→ Europe/Zurich
42/R-024 (CERN)

42/R-024

CERN

6
Show room on map
Hide

Cut at (HCAL_E+ECAL_E)/truth_E > 0.66, H/E < 0.4 (loose filters for regression, stronger H/E cut for classification)
Make TriForce do filtering on the fly
Look at lower dropout rate
Switch to early stopping instead of fixed batches
For 1D plots, train multiple times per point and get errors
Look at SeLU instead of ReLU (also batch norm?)
Accuracy vs. energy plots for both small energy range and full energy range

There are minutes attached to this event. Show them.
    • 15:00 → 15:20
      Maurizio 20m
      Speaker: Maurizio Pierini (CERN)
    • 15:20 → 15:40
      Ben 20m
      Speaker: Benjamin Henry Hooberman (Univ. Illinois at Urbana-Champaign (US))
    • 15:40 → 16:00
      Amir 20m
      Speaker: Amir Farbin (University of Texas at Arlington (US))
    • 16:00 → 16:20
      Jean-Roch 20m
      Speaker: Dr Jean-Roch Vlimant (California Institute of Technology (US))
    • 16:20 → 16:40
      Ryan 20m
      Speaker: Ryan Reece (University of California,Santa Cruz (US))
    • 16:40 → 17:00
      Matt 20m
      Speaker: Matt Zhang (Univ. Illinois at Urbana-Champaign (US))
      (2018-06-08) Classification Baseline.pdf
    • 17:00 → 17:20
      Taylor 20m
    • 17:20 → 17:40
      Junze 20m
    • 17:40 → 18:00
      Dominick - Regression 20m
      Speaker: Dominick Olivito (Univ. of California San Diego (US))
      lcdml_reg_olivito_080618.pdf
Powered by Indico v3.3.2-pre