Deep Learning approach to LHCb Calorimeter reconstruction using a Cellular Automaton

The optimization of reconstruction algorithms has become a key aspect in LHCb as it is currently undergoing major upgrade that will considerably increase the data processing rate. Aiming to accelerate second most time consuming process trigger, we propose an alternative algorithm for Electromagnetic Calorimeter LHCb. Together with use deep learning techniques and understanding current algorithm, our proposal decomposes into small parts benefit generalized neural network architectures simplifies training dataset. This approach takes input full simulation calorimeter outputs list reconstructed clusters nearly constant without any dependency event complexity.