Machine Learning approach for the search of heavy diboson resonances in semi-leptonic final state at $\sqrt{s}$= 13 TeV with the ATLAS detector

A Recurrent Neural Network-based approach has been adopted for the classification of the production mechanisms in the search of heavy resonances decaying in two bosons. The search is performed using proton-proton collision data recorded with the ATLAS detector from 2015 to 2018. The investigated final state is semi-leptonic, where one boson decays in two leptons and the other decays hadronically. No excesses have been found in data with respect to the background-only hypothesis. Upper bounds on the production cross sections of heavy scalar, vector or tensor resonances are derived in the mass range 300–5000 GeV.