A deep neural network for simultaneous estimation of b quark energy and resolution for the CMS experiment

16:35-16:50, January 28

Talk/ Overview

An algorithm to obtain point and dispersion estimates for the energy of jets arising from bottom quarks produced in proton-proton collisions at an energy of $\sqrt{s}$ = 13 TeV at the CERN LHC is presented. The algorithm, b-jet energy regression, is trained on a large simulated sample of b jets and validated on data recorder by the CMS detector in 2017. A multivariate regression algorithm based on a deep feed-forward neural network employs jet composition and shape information, and the properties of reconstructed secondary vertices associated with the jet. The results of the algorithm are used to improve the experimental sensitivity of analyses that make use of b jets in the final state, such as the observation of Higgs boson decay to a bottom quark-antiquark pair.

Talk/ Speakers

Nadezda Chernyavskaya

Research Scientist & Data Scientist, ETH Zurich and CERN CMS Collaboration

AMLD / Global partners