Boosted top quark tagging and polarization measurement using machine learning

Machine learning techniques are used for treating jets as images to explore the performance of boosted top quark tagging. Tagging performances studied in both hadronic and leptonic channels decay, employing a convolutional neural network (CNN) based technique along with decision trees (BDT). This computer vision approach is also applied distinguish between left right polarized quarks. In this context, an experimentally measurable asymmetry variable proposed estimate polarization. Results indicate that CNN classifier more sensitive polarization than standard kinematic variables. It observed overall tagging channel better case, former serves probe studying