The Machine Learning Overview of Majorana Demonstrator

Neutrinoless Double Beta Decay (0νββ) is one of the major research interests in neutrino physics. The discovery of 0νββ would answer persistent puzzles in the standard model. In the search for 0νββ, the Majorana Demonstrator experiment retains the best energy resolution and one of the lowest backgrounds in the region of interest. Data is collected from enriched and natural Germanium-76 crystals operating as detector arrays of p-type point-contact and inverted-coaxial point-contact detectors, with a total 64.5 kg-yr final active enriched exposure. We have developed a suite of machine learning tools to collectively analyze the pulse shape parameters used to reject backgrounds. In this talk, we will discuss two machine learning approaches to analyze Majorana data: an interpretable BDT analysis to analyze pulse shape discrimination parameters and a recurrent neural network analysis to analyze the waveform directly. These analyses have the potential to further improve background rejection and reciprocally benefit the traditional analysis.