ROLE OF NEURAL NETWORKS IN THE SEARCH OF THE HIGGS-BOSON AT LHC

We show that neural network classifiers can be helpful to discriminate Higgs production from background at LHC in the Higgs mass range M-H s imilar to 200 GeV. We employ a common feed-forward neural network trai ned by the backpropagation algorithm for off-line analysis and the neu ral chip TOTEM, trained by the Reactive Tabu Search algorithm, which c ould be used for on-line analysis. (C) 1997 Published by Elsevier Scie nce B.V.