Identifying Hadronic Molecular States with a Neural Network

Abstract

Neural networks are trained to judge whether or not an exotic state is a hadronic molecule of a given channel according its line-shapes. This method performs well in both trainings and validation tests. As applications, it is applied to study $X(3872)$, $X(4260)$ and $Z_c(3900)$. The results show that $Z_c(3900)$ should be regarded as a ${\bar{D}}^{\ast }D$ molecular state but $X(3872)$ not. As for $X(4260)$, it can not be a molecular state of $\ddot{I}{‡}_{c0}\ddot{I}‰$. Some discussions on $X_1(2900)$ are also provided.

Revised version published in EPJC, one author is added