Neural network classification of quark and gluon jets
- Physics Department, University of Illinois, 1110 W. Green St., Urbana, Illinois 61801 (United States)
- 32/132 rue Basse, 59800 Lille (France)
We demonstrate that there are characteristics common to quark jets and to gluon jets regardless of the interaction that produced them. The classification technique we use depends on the mass of the jet as well as the center-of-mass energy of the hard subprocess that produces the jet. In addition, we present the quark-gluon separability results of an artificial neural network trained on three-jet {ital e}{sup +}{ital e}{sup {minus}} events at the {ital Z}{sup 0} mass, using a back-propagation algorithm. The inputs to the network are the longitudinal momenta of the leading hadrons in the jet. We tested the network with quark and gluon jets from both {ital e}{sup +}{ital e}{sup {minus}}{r_arrow}3 jets and {ital {bar p}p}{r_arrow}2 jets. Finally, we compare the performance of the artificial neural network with the results of making well chosen physical cuts.
- DOE Contract Number:
- FG02-91ER40677
- OSTI ID:
- 44747
- Journal Information:
- Physical Review, D, Vol. 51, Issue 9; Other Information: PBD: 1 May 1995
- Country of Publication:
- United States
- Language:
- English
Similar Records
Finding gluon jets with a neural trigger
Deep learning in color: towards automated quark/gluon jet discrimination