Approach the Gell-Mann-Okubo Formula with Machine Learning

Abstract

Machine learning is a novel and powerful technology and has been widely used in various science topics. We demonstrate a machine-learning-based approach built by a set of general metrics and rules inspired by physics. Taking advantages of physical constraints, such as dimension identity, symmetry and generalization, we succeed to approach the Gell-Mann–Okubo formula using a technique of symbolic regression. This approach can effectively find explicit solutions among user-defined observables, and can be extensively applied to studying exotic hadron spectrum.