Models, code, and papers for "Manfred Paulini":
We describe the construction of a class of general, end-to-end, image-based physics event classifiers that directly use simulated raw detector data to discriminate signal and background processes in collision events at the LHC. To better understand what such classifiers are able to learn and to address some of the challenges associated with their use, we attempt to distinguish the Standard Model Higgs Boson decaying to two photons from its leading backgrounds using high-fidelity simulated detector data from the 2012 CMS Open Data. We demonstrate the ability of end-to-end classifiers to learn from the angular distribution of the electromagnetic showers, their shape, and the energy scale of their constituent hits, even when the underlying particles are not fully resolved.
We describe the construction of end-to-end jet image classifiers based on simulated low-level detector data to discriminate quark- vs. gluon-initiated jets with high-fidelity simulated CMS Open Data. We highlight the importance of precise spatial information and demonstrate competitive performance to existing state-of-the-art jet classifiers. We further generalize the end-to-end approach to event-level classification of quark vs. gluon di-jet QCD events. We compare the fully end-to-end approach to using hand-engineered features and demonstrate that the end-to-end algorithm is robust against the effects of underlying event and pile-up.
Machine learning is an important research area in particle physics, beginning with applications to high-level physics analysis in the 1990s and 2000s, followed by an explosion of applications in particle and event identification and reconstruction in the 2010s. In this document we discuss promising future research and development areas in machine learning in particle physics with a roadmap for their implementation, software and hardware resource requirements, collaborative initiatives with the data science community, academia and industry, and training the particle physics community in data science. The main objective of the document is to connect and motivate these areas of research and development with the physics drivers of the High-Luminosity Large Hadron Collider and future neutrino experiments and identify the resource needs for their implementation. Additionally we identify areas where collaboration with external communities will be of great benefit.