Speaker
Description
In this work, we implement a neural network model introduced by Y. Fujimoto, K. Fukushima, and K. Murase (Phys. Rev. D 98, 023019 (2018)) to infer the neutron star equation of state (EoS) from mass and radius measurements. The Tolman-Oppenheimer-Volkoff equation allows for the derivation of a mass-radius (MR) relationship from a given EoS by solving a system of ordinary differential equations. The inverse problem—determining the EoS from MR data—is considerably more challenging, particularly when accounting for measurement uncertainties. Machine learning, especially neural networks, has proven to be a powerful tool for tackling this problem without imposing strong prior constraints. Here, we reproduce this neural network model and assess its performance using both hadronic and hybrid equations of state from the CompOSE database.
