https://doi.org/10.1140/epjc/s10052-017-5224-8
Regular Article - Theoretical Physics
SCYNet: testing supersymmetric models at the LHC with neural networks
1
Universität Bonn, Nussallee 12, Bonn, Germany
2
Universität Hamburg, Luruper Chaussee 149, Hamburg, Germany
3
Institute for Theoretical Particle Physics and Cosmology, RWTH Aachen University, 52074, Aachen, Germany
* e-mail: tattersall@physik.rwth-aachen.de
Received:
14
March
2017
Accepted:
16
September
2017
Published online:
25
October
2017
SCYNet (SUSY Calculating Yield Net) is a tool for testing supersymmetric models against LHC data. It uses neural network regression for a fast evaluation of the profile likelihood ratio. Two neural network approaches have been developed: one network has been trained using the parameters of the 11-dimensional phenomenological Minimal Supersymmetric Standard Model (pMSSM-11) as an input and evaluates the corresponding profile likelihood ratio within milliseconds. It can thus be used in global pMSSM-11 fits without time penalty. In the second approach, the neural network has been trained using model-independent signature-related objects, such as energies and particle multiplicities, which were estimated from the parameters of a given new physics model.
© The Author(s), 2017