A Comparison of the Use of Binary Decision Trees and Neural Networks in Top Quark Detection

Abstract

The use of neural networks for signal vs.~background discrimination in high-energy physics experiment has been investigated and has compared favorably with the efficiency of traditional kinematic cuts. Recent work in top quark identification produced a neural network that, for a given top quark mass, yielded a higher signal to background ratio in Monte Carlo simulation than a corresponding set of conventional cuts. In this article we discuss another pattern-recognition algorithm, the binary decision tree. We have applied a binary decision tree to top quark identification at the Tevatron and found it to be comparable in performance to the neural network. Furthermore, reservations about the "black box" nature of neural network discriminators do not apply to binary decision trees; a binary decision tree may be reduced to a set of kinematic cuts subject to conventional error analysis.