Login

Calorimeter Machine Learning

→ Europe/Zurich
Hide

Summary:

Showed plots of Loss vs. Epoch, Accuracy vs. Epoch, Distributions of the output, and ROC for the Gamma vs. Pi0 classifier with 1 hidden layer (16 units).

Next steps:

1. Move on to study more sophisticated models for  the Gamma Pi0 classifier (like adding more hidden layers or switching to 2d or 3d convolutional neural network). 

2. Start to train the Electron vs. Charged Pion classifier.

3. Matt will add subjettiness to BDT.

There are minutes attached to this event. Show them.
    • 19:00 → 19:20
      Maurizio 20m
      Speaker: Maurizio Pierini (CERN)
    • 19:20 → 19:40
      Ben 20m
      Speaker: Benjamin Henry Hooberman (Univ. Illinois at Urbana-Champaign (US))
    • 19:40 → 20:00
      Amir 20m
      Speaker: Amir Farbin (University of Texas at Arlington (US))
    • 20:00 → 20:20
      Jean-Roch 20m
      Speaker: Dr Jean-Roch Vlimant (California Institute of Technology (US))
    • 20:20 → 20:40
      Ryan 20m
      Speaker: Ryan Reece (University of California,Santa Cruz (US))
    • 20:40 → 21:00
      Matt 20m
      Speaker: Matt Zhang (Univ. Illinois at Urbana-Champaign (US))
    • 21:00 → 21:20
      Taylor 20m
    • 21:20 → 21:40
      Wei Wei 20m
      CaloMeeting-Jul-20-17.pdf
Powered by Indico v3.3.3-pre