Speaker
Nalamotse Joshua Choma
(Wits University)
Description
Deep neural networks have the ability to learn from highly complex data and discover non-linear feature combinations. This makes them a suitable tool to explore the high volumes of data in HEP. This study explores the ability of semi-supervised learning in conjunction with deep neural networks to extract signal from the background in the $Z\gamma$ final state using the Monte Carlo simulated signal samples for 139 fb$^{-1}$ of integrated luminosity for Run 2, collected at the LHC. The approach is adopted with the sole intention of calculating the limit on the production of Higgs-like to $Z\gamma$ where the significance of the signal is maximum.
Level for award;(Hons, MSc, PhD, N/A)?
PhD
| Apply to be considered for a student ; award (Yes / No)? | Yes |
|---|
Primary author
Nalamotse Joshua Choma
(Wits University)
Co-authors
Salah-eddine Dahbi
(University of Wits)
Gaogalalwe Mokgatitswane
(University of the Witwatersrand (ZA))
Xifeng Ruan
(University of the Witwatersrand)
Bruce Mellado
(University of the Witwatersrand)
