Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
This report presents a project of TPIVb at LPHE in which I used deep neural networks (DNN) to distinguish heavy neutral leptons decays with 3 leptons in the final state from various types of background. At least one of the 3 leptons is required to be a hadronic tau. The events used to train the DNN were created through a Monte Carlo simulation. Several kinematic variables were created out of variables that can typically be extracted from the quantities reconstructed by CMS, to be used as features for the DNN. A feature selection was done to determine which of these features plays a significant role in the DNN's ability to distinguish signal versus background. Finally, the performance of the DNN was evaluated in the different signal points.