SCYNet: testing supersymmetric models at the LHC with neural networks
Abstract 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...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2017-10-01
|
| Series: | European Physical Journal C: Particles and Fields |
| Online Access: | http://link.springer.com/article/10.1140/epjc/s10052-017-5224-8 |
| _version_ | 1818616410931200000 |
|---|---|
| author | Philip Bechtle Sebastian Belkner Daniel Dercks Matthias Hamer Tim Keller Michael Krämer Björn Sarrazin Jan Schütte-Engel Jamie Tattersall |
| author_facet | Philip Bechtle Sebastian Belkner Daniel Dercks Matthias Hamer Tim Keller Michael Krämer Björn Sarrazin Jan Schütte-Engel Jamie Tattersall |
| author_sort | Philip Bechtle |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-12-16T16:49:22Z |
| format | Article |
| id | doaj.art-2653c64937eb495eba975567ec32da0a |
| institution | Directory Open Access Journal |
| issn | 1434-6044 1434-6052 |
| language | English |
| last_indexed | 2024-12-16T16:49:22Z |
| publishDate | 2017-10-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Physical Journal C: Particles and Fields |
| spelling | doaj.art-2653c64937eb495eba975567ec32da0a2022-12-21T22:24:05ZengSpringerOpenEuropean Physical Journal C: Particles and Fields1434-60441434-60522017-10-01771012010.1140/epjc/s10052-017-5224-8SCYNet: testing supersymmetric models at the LHC with neural networksPhilip Bechtle0Sebastian Belkner1Daniel Dercks2Matthias Hamer3Tim Keller4Michael Krämer5Björn Sarrazin6Jan Schütte-Engel7Jamie Tattersall8Universität BonnUniversität BonnUniversität HamburgUniversität BonnInstitute for Theoretical Particle Physics and Cosmology, RWTH Aachen UniversityInstitute for Theoretical Particle Physics and Cosmology, RWTH Aachen UniversityInstitute for Theoretical Particle Physics and Cosmology, RWTH Aachen UniversityInstitute for Theoretical Particle Physics and Cosmology, RWTH Aachen UniversityInstitute for Theoretical Particle Physics and Cosmology, RWTH Aachen UniversityAbstract 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.http://link.springer.com/article/10.1140/epjc/s10052-017-5224-8 |
| spellingShingle | Philip Bechtle Sebastian Belkner Daniel Dercks Matthias Hamer Tim Keller Michael Krämer Björn Sarrazin Jan Schütte-Engel Jamie Tattersall SCYNet: testing supersymmetric models at the LHC with neural networks European Physical Journal C: Particles and Fields |
| title | SCYNet: testing supersymmetric models at the LHC with neural networks |
| title_full | SCYNet: testing supersymmetric models at the LHC with neural networks |
| title_fullStr | SCYNet: testing supersymmetric models at the LHC with neural networks |
| title_full_unstemmed | SCYNet: testing supersymmetric models at the LHC with neural networks |
| title_short | SCYNet: testing supersymmetric models at the LHC with neural networks |
| title_sort | scynet testing supersymmetric models at the lhc with neural networks |
| url | http://link.springer.com/article/10.1140/epjc/s10052-017-5224-8 |
| work_keys_str_mv | AT philipbechtle scynettestingsupersymmetricmodelsatthelhcwithneuralnetworks AT sebastianbelkner scynettestingsupersymmetricmodelsatthelhcwithneuralnetworks AT danieldercks scynettestingsupersymmetricmodelsatthelhcwithneuralnetworks AT matthiashamer scynettestingsupersymmetricmodelsatthelhcwithneuralnetworks AT timkeller scynettestingsupersymmetricmodelsatthelhcwithneuralnetworks AT michaelkramer scynettestingsupersymmetricmodelsatthelhcwithneuralnetworks AT bjornsarrazin scynettestingsupersymmetricmodelsatthelhcwithneuralnetworks AT janschutteengel scynettestingsupersymmetricmodelsatthelhcwithneuralnetworks AT jamietattersall scynettestingsupersymmetricmodelsatthelhcwithneuralnetworks |