Year of Graduation
Machine Learning Methods for Particle Identification in Data of the LHCb (CERN) Detector
In this work, the data is explored for particle identification task on LHCb detector and results are acquired for flatness boosting using gradient boosting models. I show that adding a flatness term in loss function of the model enhances its performance for high energy physics tasks and compare a set of models both with and without flatness loss. I also describe the existing particle identification systems and their features, show the improvement that can be achieved with modern supervised learning models and discuss following research.