IN2P3 Machine Learning workshop

Liste des Contributions

6. Introduction

Balázs Kégl (LAL/CNRS), David Rousseau (LAL-Orsay)

29/03/2018 10:30

2. Neural Network Tracking for LHCb Vertex Detector

Da Yu Tou (Centre National de la Recherche Scientifique (FR))

29/03/2018 10:45

The LHCb experiment is scheduled for an upgrade at the end of 2018. In 2021, it has to collect data at collisions rate of 40MHz and an average of 5-6 PVs per event from 1MHz and 1-2 PVs per event today. We present an approach of using deep learning to reconstruct particle tracks in the vertex subdetector of LHCb, the Vertex Locator (VELO).

7. TrackML tracking challenge for LHC tracking

David Rousseau (LAL-Orsay)

29/03/2018 11:10

8. Active learning for "intelligent" simulation

Vladimir Gligorov (LPNHE)

29/03/2018 11:35

9. Generative models for ATLAS calorimetry

Aishik Ghosh (LAL)

29/03/2018 12:00

10. Documentation and tutorials discussion

29/03/2018 12:25

11. CTA Cerenkov telescope reconstruction

Mikaël Jacquemont

29/03/2018 14:00

3. Transient photometric classification: an astronomical data challenge

Emille Ishida (LPC-UBP)

29/03/2018 14:25

Among the many challenges imposed by the next generation of large scale astronomical surveys, the classification of transient sources is arguably one of the biggest obstacles to be overcomed before we can exploit the full potential of these new instruments. Although most of the standard astrophysical transient studies rely on high resolution spectroscopic observations, the new surveys will...

12. NN for image reconstruction for medical application

Francoise Bouvet-Lefebvre (IMNC)

29/03/2018 14:50

4. Gestion des logs au CCIN2P3 et passage à l'échelle : le ML à la rescousse ?

Fabien Wernli (Sysadmin)

29/03/2018 15:15

Près de 100 millions de "logs" et 1 milliard de métriques sont collectées par jour dans les deux datacentres du CCIN2P3. Ils sont traités via une plateforme implémantant le modèle dit "lambda" : les événements traversent deux "pipeline" en parallèle. La première de faible latence permet un traitement synchrone, presque temps-réel. La deuxième permet un traitement "batch" asynchrone sur toute...

5. Automated training of RAMP on CC GPU cluster

Alexandre Boucaud (Paris-Saclay Center for Data Science / LAL)

29/03/2018 15:45

I will present a work undergone in collaboration with Bertrand Rigaud (CCIN2P3) about the creation of a pipeline to allow ML submissions from RAMP challenges to be automatically trained on the CC infrastructure. This will be used in the future to organise IN2P3-backed challenges (LSST, Euclid) and face a short-term high demand in computing power.

13. Experience with GPU platform, CC and elsewhere

29/03/2018 16:05

14. Conclusion

Balázs Kégl (LAL/CNRS), David Rousseau (LAL-Orsay)

29/03/2018 16:15