Speaker
Satsuki Nishimura
Description
Recent studies actively apply machine learning to the exploration of flavor physics. In analyzing the flavor structure of the lepton sector, we apply reinforcement learning to a $U(1)$ flavor model with $L_{e}-L_{mu}-L_{tau}$ charges. By testing multiple architectures to explore charge combinations, we develop a strategy to efficiently achieve high-precision solutions. It turns out that the proposed approach successfully finds parameter sets that reproduce the observed lepton masses and mixing angles.
