Higgs Boson Mass Reconstruction in the tH Multi-lepton Channel using ATLAS data
Cyrus Walther, André Sopczak
TU Dortmund/FEE CTU in Prague, IEAP CTU in Prague
Abstract:
The Higgs boson mass is reconstructed in single top production in association with a Higgs boson, tH, using a regression neural network approach. The reconstruction of the Higgs boson mass is expected to show discrimination to background processes. A focus lies on the lepton association. For the lepton association a classification neural network is used. Hyperparameter optimization as well as feature importance studies are applied in order to increase the neural network performance. For the Higgs boson mass reconstruction a hyperparameter optimization is also performed. The performance of the network is tested on tZ production, as the most significant background process.
Seminar takes place on Tuesday, February 15th 2022 at 2:00 PM
in the IEAP meeting room, Praha 1, Husova 240/5.
| Ing. Bartoloměj Biskup, Ph.D. seminar organizer |
doc. Ing. Ivan Štekl, CSc. director of IEAP |
doc. Dr. André Sopczak IEEE CS - NPSS chair |
NUCLEAR & PLASMA SCIENCES SOCIETY CHAPTER
IEEE Czechoslovakia section
http://www.ieee.cz/en/nps