Neural particle discrimination for triggering interesting physics channels with calorimetry data

This article introduces a triggering scheme for high input rate processors, based on neural networks. The technique is applied to the Electron/Jet discrimination problem, present at the second level trigger of the ATLAS experiment, being constructed at CERN. The proposed solution outperforms the scheme adopted nowadays at CERN, both in discrimination efficiency and performance, becoming a candidate algorithm for implementation at the experiment.