USING NEURAL NETWORKS TO ENHANCE THE HIGGS-BOSON SIGNAL AT HADRON COLLIDERS

Neural networks are used to help distinguish the ZZ --> l(+)l(-)-jet-j et signal produced by the decay of a 400 GeV Higgs boson at a proton-p roton collider energy of 15 TeV from the ''ordinary'' QCD Z + jets bac kground. The ideal case where only one event at a time enters the dete ctor (no pileup) and the case of multiple interactions per beam crossi ng (pileup) are examined. In both cases, when used in conjunction with the standard cuts, neural networks provide an additional signal-to-ba ckground enhancement.