Machine learning interprétable pour l'analyse de données à CLAS12
Noëlie Cherrier · theses.fr (ABES) · 2021
Artificial intelligence is used massively in numerous applications, especially since the rise of deep learning techniques. However, some of these applications require a careful study and validation of the inducted model functioning. Considering experimental physics, the performances of the models on real data must be known and controlled, and their functioning explained to enable a validation via peer review. In the particular case of the CLAS12 experiment at Jefferson Laboratory, an electron beam is sent onto a proton target to probe its inner structure. To access certain structure functions of the proton, a subset of the collected data must be selected corresponding to an exclusive interaction: deeply virtual Compton scattering. This thesis focuses on this event selection. To improve the classical physics analysis, an approach exploiting intrinsically interpretable machine learning models, also called transparent models, is proposed. In this way, the functioning of the model is understood more easily and the selection errors are minimized and controlled.