Jet Analysis by Neural Networks in High Energy Hadron-hadron Collisions

We study the possibility to employ neural networks to simulate jet clustering procedures in high energy hadron-hadron collisions. We concentrate our analysis on the Fermilab Tevatron energy and on the k⊥ algorithm. We employ both supervised and unsupervised neural networks. In the first case we consider a multilayer feed-forward network trained by the backpropagation algorithm: our results show that these networks can satisfactorily simulate the relevant features of the k⊥ algorithm. We consider also unsupervised learning, where the neural network autonomously organizes the events in clusters. The results of this analysis are discussed and compared with the supervised approach.