HEP.TrackX Weekly

Monday 6 Feb 2017, 13:30 → 14:30 US/Pacific

vidyo

Paolo Calafiura, Steven Farrell

Please join the meeting by clicking this link:
https://vidyoportal.cern.ch/flex.html?roomdirect.html&key=UoHjbOgfcsrBsDfBwOlOsCObR3E 

If you want to join by phone, please use one of the phone numbers listed in the link below: http://information-technology.web.cern.ch/services/fe/howto/users-join-vidyo-meeting-phone and enter the meeting extension 103958871 in order to join.

Present: Lindsey, Josh, Jean-Roch, Steve, Jim, Aris, Stephan, Paolo

 

Hot items:

• Conference contributions:

  • Steve will present @ Connecting the Dots/Intelligent Detector - LAL Mar 6-9 https://ctdwit2017.lal.in2p3.fr/

    • Abstract: submitted

    • We will try to participate to trackML RAMP. Lots of details @ https://indico.cern.ch/event/607400/   (access code 31415)

    • David R is putting together a starter kit (track generator, fitter)

    • There is also a call for help in these areas

      • Different starter kits

      • Scoring function (big thing)

      • Estimation of required training/testing statistics

      • Bits and pieces

  • ICLR Feb 17 arkiv 2-3 pages. Mayur working on it,

  • Confirmed talk @ IML workshop @ CERN Mar 20-22. Must nominate speaker https://indico.cern.ch/event/595059/overview

  • ACAT Seattle Aug 21: https://indico.cern.ch/event/567550/

    • Submission deadline?

• Maria: potential collaboration with google-cloud

Outstanding Action Items:

• Paolo → discuss Ramp participation with David R.

  • Done: other folks working on starting kit, we should participate to the Ramp

• Computing platform:

  • CalTech GPU servers. Jean-Roch contact person if you need access. Contact JR on skype

New Action Items:

• Add Aris to NERSC repository

• Mayur → share his ICLR abstract with group.

Round the Table for Status Reports:

Caltech

• No news

FNAL

• Aris started working on dropout layer to measure uncertainty as suggested by Dustin/Stephan. Still trying to get it work.

  • Josh: also possible to use likelihood based loss-function where you add central-value and residual. Cfd Josh talk . Will present next week.

LBL

• Mayur needs a reference solution to compare to his LSTM “filter”. Attempts to use pyKalman, using EM to learn the dynamics of the tracks have been frustrating. Paolo trying to write out Acts::KF prediction alongside simulated hits.

• Steve trying to find best way to show hits predictions alongside data in 3D rather than on projections.