Application of Neural Networks for Energy Reconstruction

The possibility to use Neural Networks for reconstruction ofthe energy deposited in the calorimetry system of the CMS detector is investigated. It is shown that using feed-forward neural network, good linearity, Gaussian energy distribution and good energy resolution can be achieved. Significant imp...

Descripción completa

Detalles Bibliográficos
Autores principales: Damgov, J., Litov, L.
Lenguaje:eng
Publicado: 2000
Materias:
Detectors and Experimental Techniques
Particle Physics - Experiment
Acceso en línea:https://dx.doi.org/10.1016/S0168-9002(01)01851-4
http://cds.cern.ch/record/687287
_version_ 1780901726316920832
author Damgov, J.
Litov, L.
author_facet Damgov, J.
Litov, L.
author_sort Damgov, J.
collection CERN
description The possibility to use Neural Networks for reconstruction ofthe energy deposited in the calorimetry system of the CMS detector is investigated. It is shown that using feed-forward neural network, good linearity, Gaussian energy distribution and good energy resolution can be achieved. Significant improvement of the energy resolution and linearity is reached in comparison with other weighting methods for energy reconstruction.
id cern-687287
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2000
record_format invenio
spelling cern-6872872023-03-20T14:29:36Zdoi:10.1016/S0168-9002(01)01851-4http://cds.cern.ch/record/687287engDamgov, J.Litov, L.Application of Neural Networks for Energy ReconstructionDetectors and Experimental TechniquesParticle Physics - ExperimentThe possibility to use Neural Networks for reconstruction ofthe energy deposited in the calorimetry system of the CMS detector is investigated. It is shown that using feed-forward neural network, good linearity, Gaussian energy distribution and good energy resolution can be achieved. Significant improvement of the energy resolution and linearity is reached in comparison with other weighting methods for energy reconstruction.The possibility to use Neural Networks for reconstruction of the energy deposited in the calorimetry system of the CMS detector is investigated. It is shown that using feed - forward neural network, good linearity, Gaussian energy distribution and good energy resolution can be achieved. Significant improvement of the energy resolution and linearity is reached in comparison with other weighting methods for energy reconstruction.hep-ex/0012003CMS-NOTE-2000-066CMS-NOTE-2000-066oai:cds.cern.ch:6872872000-10-27
spellingShingle Detectors and Experimental Techniques
Particle Physics - Experiment
Damgov, J.
Litov, L.
Application of Neural Networks for Energy Reconstruction
title Application of Neural Networks for Energy Reconstruction
title_full Application of Neural Networks for Energy Reconstruction
title_fullStr Application of Neural Networks for Energy Reconstruction
title_full_unstemmed Application of Neural Networks for Energy Reconstruction
title_short Application of Neural Networks for Energy Reconstruction
title_sort application of neural networks for energy reconstruction
topic Detectors and Experimental Techniques
Particle Physics - Experiment
url https://dx.doi.org/10.1016/S0168-9002(01)01851-4
http://cds.cern.ch/record/687287
work_keys_str_mv AT damgovj applicationofneuralnetworksforenergyreconstruction
AT litovl applicationofneuralnetworksforenergyreconstruction

Ejemplares similares