PhysicsGP: A Genetic Programming Approach to Event Selection

We present a novel multivariate classification technique based on Genetic Programming. The technique is distinct from Genetic Algorithms and offers several advantages compared to Neural Networks and Support Vector Machines. The technique optimizes a set of human-readable classifiers with respect to...

Descripción completa

Detalles Bibliográficos
Autores principales: Cranmer, Kyle, Bowman, R. Sean
Lenguaje:eng
Publicado: 2004
Materias:
Other Fields of Physics
Acceso en línea:https://dx.doi.org/10.1016/j.cpc.2004.12.006
http://cds.cern.ch/record/711048
_version_ 1780902648484986880
author Cranmer, Kyle
Bowman, R. Sean
author_facet Cranmer, Kyle
Bowman, R. Sean
author_sort Cranmer, Kyle
collection CERN
description We present a novel multivariate classification technique based on Genetic Programming. The technique is distinct from Genetic Algorithms and offers several advantages compared to Neural Networks and Support Vector Machines. The technique optimizes a set of human-readable classifiers with respect to some user-defined performance measure. We calculate the Vapnik-Chervonenkis dimension of this class of learning machines and consider a practical example: the search for the Standard Model Higgs Boson at the LHC. The resulting classifier is very fast to evaluate, human-readable, and easily portable. The software may be downloaded at: http://cern.ch/~cranmer/PhysicsGP.html
id cern-711048
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2004
record_format invenio
spelling cern-7110482023-03-14T16:29:28Zdoi:10.1016/j.cpc.2004.12.006http://cds.cern.ch/record/711048engCranmer, KyleBowman, R. SeanPhysicsGP: A Genetic Programming Approach to Event SelectionOther Fields of PhysicsWe present a novel multivariate classification technique based on Genetic Programming. The technique is distinct from Genetic Algorithms and offers several advantages compared to Neural Networks and Support Vector Machines. The technique optimizes a set of human-readable classifiers with respect to some user-defined performance measure. We calculate the Vapnik-Chervonenkis dimension of this class of learning machines and consider a practical example: the search for the Standard Model Higgs Boson at the LHC. The resulting classifier is very fast to evaluate, human-readable, and easily portable. The software may be downloaded at: http://cern.ch/~cranmer/PhysicsGP.htmlWe present a novel multivariate classification technique based on Genetic Programming. The technique is distinct from Genetic Algorithms and offers several advantages compared to Neural Networks and Support Vector Machines. The technique optimizes a set of human-readable classifiers with respect to some user-defined performance measure. We calculate the Vapnik-Chervonenkis dimension of this class of learning machines and consider a practical example: the search for the Standard Model Higgs Boson at the LHC. The resulting classifier is very fast to evaluate, human-readable, and easily portable. The software may be downloaded at: http://cern.ch/~cranmer/PhysicsGP.htmlphysics/0402030oai:cds.cern.ch:7110482004-02-05
spellingShingle Other Fields of Physics
Cranmer, Kyle
Bowman, R. Sean
PhysicsGP: A Genetic Programming Approach to Event Selection
title PhysicsGP: A Genetic Programming Approach to Event Selection
title_full PhysicsGP: A Genetic Programming Approach to Event Selection
title_fullStr PhysicsGP: A Genetic Programming Approach to Event Selection
title_full_unstemmed PhysicsGP: A Genetic Programming Approach to Event Selection
title_short PhysicsGP: A Genetic Programming Approach to Event Selection
title_sort physicsgp: a genetic programming approach to event selection
topic Other Fields of Physics
url https://dx.doi.org/10.1016/j.cpc.2004.12.006
http://cds.cern.ch/record/711048
work_keys_str_mv AT cranmerkyle physicsgpageneticprogrammingapproachtoeventselection
AT bowmanrsean physicsgpageneticprogrammingapproachtoeventselection

Ejemplares similares