Neural network reconstruction of the dense matter equation of state from neutron star observables

The Equation of State (EoS) strongly interacting cold and hot ultra-dense QCD matter remains a major challenge in the field nuclear astrophysics. With advancements measurements neutron star masses, radii, tidal deformabilities, from electromagnetic gravitational wave observations, stars play an important role constraining EoS. In this work, we present novel method that exploits deep learning techniques to reconstruct EoS mass-radius (M-R) observations. We employ neural networks (NNs) represent model-independent way, within range $\sim$1-7 times saturation density. unsupervised Automatic Differentiation (AD) framework is implemented optimize EoS, so as yield through TOV equations, M-R curve best fits demonstrate works by rebuilding on mock data, i.e., pairs derived randomly generated polytropic reconstructed data with reasonable accuracy, using just 11 close current number actual