Deep-learning quasi-particle masses from QCD equation of state

The interactions of quarks and gluons are strong in the non-perturbative regime. equation state (EoS) a strongly-interacting quantum chromodynamics (QCD) medium can only be studied using first-principle lattice QCD calculations. However, complicated EoS reproduced simple statistical formula by treating as free parton gas whose fundamental degrees freedom dressed called quasi-particles, with temperature-dependent masses. We use deep neural networks auto differentiation to solve this variational problem which masses quasi gluons, up/down strange three unknown functions, forms represented network. reproduce at zero net baryon chemical potential these machine learned quasi-particle masses, calculate shear viscosity over entropy density (η/s) function temperature hot matter.