End-to-End Deep Learning Reconstruction for CMS Experiment

Developing End-to-End Deep Learning Models and optimizing them for the Reconstruction of single particles, jets and event topologies of interest in collision during collision experiment. This involves classifying electromagnetic showers of the particles developed during the experiment and their event classification. The code will be further integrated with the CMSSW inference engine. The inference of the model will be integrated with the CMSSW Particle Flow (PF) classes and will be tested on GPUs for faster Computation. This proposal shows the proposed methodology and model(which may be improvised while working on it depending on the performance and new approaches may be used) for the reconstruction for CMS experiment. It also includes timeline and some basic concepts of Physics to familiarize with the CMS experiment at Large Hadron Collider (LHC).