Phase 2 of the tracking machine learning challenge has started
The second phase of the TrackML tracking machine learning challenge has just started and you are invited to participate and contribute.
The TrackML challenge is an ongoing effort by machine learning experts and particle physicists from the ATLAS, CMS and LHCb collaborations, including Tobias Golling, Moritz Kiehn, and Sabrina Amrouche from the Département de Physique Nucléaire et Corpusculaire, to investigate new solutions for tracking problem at the next generation of particle detectors. Participants are invited to propose algorithms to reconstruct particle tracks from measurements in a virtual future particle detector. This is one of the crucial steps in analyzing the enormous amount of data from the experiments and one that is becoming ever more challenging.
The first phase of the challenge, the "Accuracy Phase", was running on the Kaggle platform until August 2018. It has successfully finished and the final winners and results are expected to be revealed at the end of September. Here the focus was on developing novel algorithms that can accurately reconstruct the particle tracks, irrespective of the evaluation time. This phase was also an official IEEE WCCI competition (Rio de Janeiro, July 2018). The second “Throughput Phase” is running now and focuses on the throughput (or speed) of the evaluation while still maintaining a good accuracy. This phase is an official NIPS competition (Montreal, December 2018). The Université de Genève is a platinum sponsor for the challenge thanks to contributions from the Faculté des Sciences and the Rectorat.
Sign up for the phase 2 of the TrackML challenge today. The three top scorers will receive cash prizes. Selected winners may be awarded a top-notch NVIDIA v100 GPU, get the chance to visit CERN, or attend the 2018 Conference on Neural Information Processing Systems in Montreal (Canada).
For more information and the conditions for participation, visit the Codalab challenge website and follow the official TrackML Twitter account.