End-to-end particle and event identification at the Large Hadron Collider with CMS Open Data(15'+5')

Jul 23, 2019, 5:40 PM
32-123 (MIT)





Emanuele Usai (Brown University (US))


We present an innovative end-to-end deep learning approach for jet identification at the LHC. The method combines deep neural networks with low-level detector information, such as calorimeter energy deposits and tracking information, to build a discriminator to identify different particles. Using two physics examples as references: electron and photon discrimination and quark and gluon discrimination, we demonstrate the performance of the end-to-end approach using simulated events with full detector geometry available as CMS Open Data. We also offer insights into the importance of the information extracted from various sub-detectors and describe how end-to-end techniques can be extended to event-level classification using information from the whole detector.

Primary authors

Prof. Barnabas Poczos (Carnegie Mellon University) Bjorn Burkle (Brown University (US)) Emanuele Usai (Brown University (US)) John Alison (Carnegie-Mellon University (US)) Manfred Paulini (Carnegie-Mellon University (US)) Meenakshi Narain (Brown University (US)) Michael Andrews (Carnegie-Mellon University (US)) Dr Patrick Bryant (Carnegie-Mellon University (US)) Sergei Gleyzer (University of Florida (US)) Sitong An (CERN, Carnegie Mellon University (US)) Ulrich Heintz (Brown University (US))

Presentation materials