Thursday, 22nd of November

11h11 (room R2014, 660 building) (see location)

Adrian Alan Pol


Title: Machine Learning applications to CMS Data Quality Monitoring


The Data Quality Monitoring (DQM) in High Energy Physics is a key task guaranteeing experiment data as usable for physics analysis and consequently ensuring the quality of all physics results published by the collaboration. Currently, in CMS, the monitoring conducted by human experts is extremely expensive in terms of human resources and required expertise. CMS is focusing on the design of machine learning based solutions for automatised DQM, allowing the check of large volumes of data in real-time and improving the ability to detect unexpected failures while reducing the manpower requirements. I will discuss: peculiar challenges posed by the CMS DQM in the context of applying ML algorithms; and examples of perspective, ongoing and successful applications of deep learning to concrete examples of detector monitorables integrated in the production DQM infrastructure of CMS.

Contact: guillaume.charpiat at
All TAU seminars: here

Collaborateur(s) de cette page: guillaume .
Page dernièrement modifiée le Dimanche 18 novembre 2018 20:40:30 CET par guillaume.