Moving NN triggers to level-1 at LHC rates

Although the use of neural network hardware for level 2 triggering at hadron colliders has been established for many years, there has been little investigation of neural techniques for level 1 triggers at LHC experiments. In addition, commercially available NN solutions with appropriate timing const...

Descripción completa

Detalles Bibliográficos
Autores principales: Prevotet, J C, Denby, B, Garda, P, Granado, B, Kiesling, C
Lenguaje:eng
Publicado: 2003
Materias:
Detectors and Experimental Techniques
Acceso en línea:https://dx.doi.org/10.1016/S0168-9002(03)00484-4
http://cds.cern.ch/record/624970
_version_ 1780900504058986496
author Prevotet, J C
Denby, B
Garda, P
Granado, B
Kiesling, C
author_facet Prevotet, J C
Denby, B
Garda, P
Granado, B
Kiesling, C
author_sort Prevotet, J C
collection CERN
description Although the use of neural network hardware for level 2 triggering at hadron colliders has been established for many years, there has been little investigation of neural techniques for level 1 triggers at LHC experiments. In addition, commercially available NN solutions with appropriate timing constraints do not exist. Presented here is a new FPGA-based method for implementing multilayer perceptrons with hundreds of neurons in a 25 ns pipeline structure having only 600 ns latency. Possible implementation in an LHC level 1 trigger scenario is discussed.
id cern-624970
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2003
record_format invenio
spelling cern-6249702019-09-30T06:29:59Zdoi:10.1016/S0168-9002(03)00484-4http://cds.cern.ch/record/624970engPrevotet, J CDenby, BGarda, PGranado, BKiesling, CMoving NN triggers to level-1 at LHC ratesDetectors and Experimental TechniquesAlthough the use of neural network hardware for level 2 triggering at hadron colliders has been established for many years, there has been little investigation of neural techniques for level 1 triggers at LHC experiments. In addition, commercially available NN solutions with appropriate timing constraints do not exist. Presented here is a new FPGA-based method for implementing multilayer perceptrons with hundreds of neurons in a 25 ns pipeline structure having only 600 ns latency. Possible implementation in an LHC level 1 trigger scenario is discussed.oai:cds.cern.ch:6249702003
spellingShingle Detectors and Experimental Techniques
Prevotet, J C
Denby, B
Garda, P
Granado, B
Kiesling, C
Moving NN triggers to level-1 at LHC rates
title Moving NN triggers to level-1 at LHC rates
title_full Moving NN triggers to level-1 at LHC rates
title_fullStr Moving NN triggers to level-1 at LHC rates
title_full_unstemmed Moving NN triggers to level-1 at LHC rates
title_short Moving NN triggers to level-1 at LHC rates
title_sort moving nn triggers to level-1 at lhc rates
topic Detectors and Experimental Techniques
url https://dx.doi.org/10.1016/S0168-9002(03)00484-4
http://cds.cern.ch/record/624970
work_keys_str_mv AT prevotetjc movingnntriggerstolevel1atlhcrates
AT denbyb movingnntriggerstolevel1atlhcrates
AT gardap movingnntriggerstolevel1atlhcrates
AT granadob movingnntriggerstolevel1atlhcrates
AT kieslingc movingnntriggerstolevel1atlhcrates

Ejemplares similares