Neural ordinary differential equation and holographic quantum chromodynamics

Abstract The neural ordinary differential equation (neural ODE) is a novel machine learning architecture whose weights are smooth functions of the continuous depth. We apply ODE to holographic QCD by regarding weight as bulk metric, and train with lattice data chiral condensate at finite temperature. finds consistent geometry various values temperature discovers emergent black hole horizon in automatically. Wilson loops calculated machine-learned spacetime have dependence confinement Debye-screening behavior. In models physically interpretable weights, frees us from discretization artifact leading difficult ingenuity hyperparameters, improves numerical accuracy make model more trustworthy.