1-2 July 2019
CERN
Europe/Zurich timezone

The HL-LHC will see ATLAS and CMS see proton bunch collisions reaching track multiplicity up to 10.000 charged tracks per event. Algorithms need to be developed to harness the increased combinatorial complexity. To engage the Computer Science community to contribute new ideas, we have organized a Tracking Machine Learning challenge (TrackML). Participants were provided events with 100k 3D points, and are asked to group the points into tracks; they are also given a 100GB training dataset including the ground truth.

The TrackML challenge has run in two phases.

  • The first "Accuracy" phase has run on Kaggle platform from May to August 2018; algorithms were judged judged only on a score related to the fraction of correctly assigned hits. The first phase has seen 653 participants, with top performers with innovative approaches, exposed at NeurIPS 2018 Competition workshop and documented in 1904.06778 
  • The second "Throughput" phase ran Sep 2018 to March 2019 on Codalab, required code submission; algorithms were then ranked by combining accuracy and speed. It has seen astonishingly fast submissions.

This workshop will gather at CERN organizers, top competitors and anyone with interest with fast tracking.

Registration is free.

Non CERN user are welcome (they need to tick the appropriate box in the registration form).

The workshop takes place from Monday 1PM to Tuesday 5:30PM. Tuesday morning is reserved for visit of CERN highlights for non HEP participants.In particular, visits of ATLAS or CMS experiments which will be exceptionally open are foreseen.

Contact : trackml-contact@googlegroups.com

 

The agenda is being built, the following speakers and/or topics are confirmed:

 

Introductions:

  • Introduction

  • TrackML CERN Open Dataset release talk (15+5)

  • CTD/WIT workshop Valencia highlights (15+5)

Challenge:

  • Overview and  solutions not covered by speakers

  • Sergey Gorbunov  accuracy #3 throughput #1 

  • Dmitry Emelianov accuracy #4 throughput #2 

  • MarcelKunze throughput #3 

  • Yuval Reina/TrianXylouris (accuracy HEP ML prize V100) 

  • Nicole and Liam Finnie (acurracy HEPML NeurIPSinvite) 

 

Sponsors:

  • Peter Messmer : Nvidia 

  • Walter Reade (remote presentation) : Kaggle

  • UniGe  TBA

TrackML spin-off talks: 

  • Tobias Isenberg/Xiyao Wang: TrackML Hololens visualisation 

  • Hep.QPR/QMLQCF tracking with quantum with TrackML dataset TBC (15+5)

  • Hep.TrkX TBC  (15+5)

  • Spotify/Annoy library TBC (15+5)

  • Future usage of TrackML dataset (ACTS integration, OpenData detector) TBC

Discussion and Conclusions

 

 

 

 

Starts
Ends
Europe/Zurich
CERN
Registration
Registration for this event is currently open.
Your browser is out of date!

If you are using Internet Explorer, please use Firefox, Chrome or Edge instead.

Otherwise, please update your browser to the latest version to use Indico without problems.

×