Machine learning for dark matter search experiments
Machine learning (ML) has been widely applied in high energy physics to help the physicists community in particle identification and data
analysis in general. This talk addresses two examples of ML approaches in DEAP-3600 and DarkSide experiments for dark matter direct detection in liquid argon. One application is related to the problem of mitigating background events in the DEAP-3600 experiment
(SNOLAB, Canada) using different estimators (Boosted Decision Trees (BDT), Neural Networks); a second application with Convolutional Neural Networks for position reconstruction in DarkSide experiments will then be discussed. In both cases, the focus will be on the
ML techniques for the data analysis, the training routine, the validation protocol, the integration of ML models into the analysis.
Join Zoom Meeting
https://infn-it.zoom.us/j/83682324121?pwd=ZlhsNzgxbGQwVGhVT2wrUHVwOU1DUT09
Meeting ID: 836 8232 4121
Passcode: 318219
Find your local number: https://infn-it.zoom.us/u/k93Ue9jE
Prof. Umberto D'Alesio - umberto.dalesio@ca.infn.it
Ph.D. Michela Lai - michela.lai@ca.infn.it
Dr Luca Maxia - luca.maxia@ca.infn.it
Dr Mauro Oi - mauro.oi@ca.infn.it