Application of Machine Learning Methods in the Data Analysis at the Large Hadron Collider (LHC) J1-3010

With the increasing complexity of the research in experimental particle physics, lookingfor new physics signatures in progressively larger and more complex data sets that arebeing analyzed at the LHC experiments, new approaches to data analysis, fromreconstruction to simulation, need to be investigated. The main objective of this projectis to develop and test state‐of‐the‐art scientific tools for HEP data simulation,reconstruction and analysis, using software technologies based on Machine Learning ingeneral and Deep Learning in particular. These tools will be executing on the newest(accelerator‐enabled) hardware solutions in the HPC super‐computing clusters, in order toaddress the challenges of speed and accuracy, crucial for the existing and nextgeneration of High Energy Physics (HEP) Collider experiments.