Study of exotic hadrons with machine learning

We analyzed the invariant mass spectrum of near-threshold exotic states for one-channel candidates with a deep neural network. It can extract scattering length and effective range, which would shed light on nature given states, from experimental spectrum. As an application, $X(3872)$ $T_{cc}^+$ are studied. The obtained lengths, ranges, most relevant thresholds consistent those fitting to data. advantage network is that it more stable than fitting, especially low-statistic network, provides another way analyze data, also be applied other candidates.