Probing Higgs boson exotic decays at the LHC with machine learning

We study the tagging of Higgs exotic decay signals using different types of deep neural networks (DNNs) while focusing on the $W^±h$ associated production channel followed by Higgs decaying into $n$ $b$ quarks with $n=4$, 6, and 8. All the Higgs decay products are collected into a fat jet, to which we apply further selection using the DNNs. Three kinds of DNNs are considered - namely, the convolutional neural network, the recursive neural network, and the particle flow network (PFN). The PFN can achieve the best performance because its structure allows one to enfold more information in addition to the four-momenta of the jet constituents, such as the particle identifier, and tracks the parameters. Using the PFN as an example, we verify that it can serve as an efficient tagger even though it is trained on a different event topology with different b multiplicity from the actual signal. The projected sensitivity to the branching ratio of Higgs decaying into n b quarks at the HL-LHC are 10%, 3%, and 1%, for $n=4$, 6, and 8, respectively.