Machine-enhanced CP-asymmetries in the Higgs sector

Improving the sensitivity to CP-violation in Higgs sector is one of pillars precision programme at Large Hadron Collider. We present a simple method that allows CP-sensitive observables be directly constructed from output neural networks. show these have improved CP-violating effects production and decay boson, when compared use traditional angular alone. The kinematic correlations identified by networks can used design new analyses based on observables, with similar improvement sensitivity.