Speaker
Ms
Nkateko Baloyi
(University of the Witwatersrand)
Description
The amount of data produced in the Large Hadron Collider requires modern techniques to improve the processing, classification and regression tasks. In this study, we develop machine learning algorithms that can learn patterns in the data and lead to accurate discrimination of Signal and Background in the search for new bosons decaying into Z + γ final state. The toolkit for multivariate analysis, scikit-learn boosted decision trees and deep neural networks with tensorflow are employed in this study and compared against each other to find the technique that best improves the quality of the signal in the search for new bosons.
Apply to be<br> considered for a student <br> award (Yes / No)?
Yes
Level for award<br> (Hons, MSc, <br> PhD, N/A)?
MSc
Primary author
Ms
Nkateko Baloyi
(University of the Witwatersrand)
Co-authors
Prof.
Bruce Mellado
(University of the Witwatersrand)
Dr
XIFENG RUAN
(WITS)
