Deep Neural Networks for Physics Analysis on low-level whole-detector data at the LHC
This work addresses the need for more comprehensive physics analysis in particle physics experiments like ATLAS/CMS, though it appears incremental by extending existing CNN methods to whole-detector data.
The paper tackled the problem of directly classifying physics events as background or new-physics signals using deep convolutional neural networks on entire calorimeter data combined with track information, achieving results in a case study on RPV-Supersymmetry analysis with computational exploration on GPU and CPU architectures.
There has been considerable recent activity applying deep convolutional neural nets (CNNs) to data from particle physics experiments. Current approaches on ATLAS/CMS have largely focussed on a subset of the calorimeter, and for identifying objects or particular particle types. We explore approaches that use the entire calorimeter, combined with track information, for directly conducting physics analyses: i.e. classifying events as known-physics background or new-physics signals. We use an existing RPV-Supersymmetry analysis as a case study and explore CNNs on multi-channel, high-resolution sparse images: applied on GPU and multi-node CPU architectures (including Knights Landing (KNL) Xeon Phi nodes) on the Cori supercomputer at NERSC.