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.