09.10.2019 Deconvolution of the Experimental Data with Machine Learning
A method for correcting the detector smearing eﬀects using machine learning technique is presented. Compared to the standard deconvolution approaches in high energy particle physics, the method can use more than one reconstructed variable to predict the value of unsmeared quantity on an event-by-event basis. In this particular study, deconvolution is interpreted as a classiﬁcation problem, and neural networks (NN) are trained to deconvolute the Z boson invariant mass spectrum generated with MadGraph and pythia8 Monte Carlo event generators. Results obtained from the deep learning method is presented and compared with the results obtained with traditional methods.