Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2002 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Materials research (São Carlos. Online) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-14392002000300011 |
Resumo: | Theoretical determination of the ground-state geometry of Si clusters is a difficult task. As the number of local minima grows exponentially with the number of atoms, to find the global minimum is a real challenge. One may start the search procedure from a random distribution of atoms but it is probably wiser to make use of any available information to restrict the search space. Here, we introduce a new approach, the Assisted Genetic Optimization (AGO) that couples an Artificial Neural Network (ANN) to a Genetic Algorithm (GA). Using available information on small Silicon clusters, we trained an ANN to predict good starting points (initial population) for the GA. AGO is applied to Si10 and Si20 and compared to pure GA. Our results indicate: i) AGO is, at least, 5 times faster than pure GA in our test case; ii) ANN training can be made very fast and successfully plays the role of an experienced investigator; iii) AGO can easily be adapted to other optimization problems. |
id |
ABMABCABPOL-1_bd6ff0d3e37403fd887462eb0e9f337d |
---|---|
oai_identifier_str |
oai:scielo:S1516-14392002000300011 |
network_acronym_str |
ABMABCABPOL-1 |
network_name_str |
Materials research (São Carlos. Online) |
repository_id_str |
|
spelling |
Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networkssilicon clustersgenetic algoritmneural networkTheoretical determination of the ground-state geometry of Si clusters is a difficult task. As the number of local minima grows exponentially with the number of atoms, to find the global minimum is a real challenge. One may start the search procedure from a random distribution of atoms but it is probably wiser to make use of any available information to restrict the search space. Here, we introduce a new approach, the Assisted Genetic Optimization (AGO) that couples an Artificial Neural Network (ANN) to a Genetic Algorithm (GA). Using available information on small Silicon clusters, we trained an ANN to predict good starting points (initial population) for the GA. AGO is applied to Si10 and Si20 and compared to pure GA. Our results indicate: i) AGO is, at least, 5 times faster than pure GA in our test case; ii) ANN training can be made very fast and successfully plays the role of an experienced investigator; iii) AGO can easily be adapted to other optimization problems.ABM, ABC, ABPol2002-09-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-14392002000300011Materials Research v.5 n.3 2002reponame:Materials research (São Carlos. Online)instname:Universidade Federal de São Carlos (UFSCAR)instacron:ABM ABC ABPOL10.1590/S1516-14392002000300011info:eu-repo/semantics/openAccessLemes,M.R.Marim,L.R.Dal Pino Jr.,A.eng2002-11-20T00:00:00Zoai:scielo:S1516-14392002000300011Revistahttp://www.scielo.br/mrPUBhttps://old.scielo.br/oai/scielo-oai.phpdedz@power.ufscar.br1980-53731516-1439opendoar:2002-11-20T00:00Materials research (São Carlos. Online) - Universidade Federal de São Carlos (UFSCAR)false |
dc.title.none.fl_str_mv |
Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networks |
title |
Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networks |
spellingShingle |
Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networks Lemes,M.R. silicon clusters genetic algoritm neural network |
title_short |
Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networks |
title_full |
Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networks |
title_fullStr |
Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networks |
title_full_unstemmed |
Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networks |
title_sort |
Study of the Ground-State Geometry of Silicon Clusters Using Artificial Neural Networks |
author |
Lemes,M.R. |
author_facet |
Lemes,M.R. Marim,L.R. Dal Pino Jr.,A. |
author_role |
author |
author2 |
Marim,L.R. Dal Pino Jr.,A. |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Lemes,M.R. Marim,L.R. Dal Pino Jr.,A. |
dc.subject.por.fl_str_mv |
silicon clusters genetic algoritm neural network |
topic |
silicon clusters genetic algoritm neural network |
description |
Theoretical determination of the ground-state geometry of Si clusters is a difficult task. As the number of local minima grows exponentially with the number of atoms, to find the global minimum is a real challenge. One may start the search procedure from a random distribution of atoms but it is probably wiser to make use of any available information to restrict the search space. Here, we introduce a new approach, the Assisted Genetic Optimization (AGO) that couples an Artificial Neural Network (ANN) to a Genetic Algorithm (GA). Using available information on small Silicon clusters, we trained an ANN to predict good starting points (initial population) for the GA. AGO is applied to Si10 and Si20 and compared to pure GA. Our results indicate: i) AGO is, at least, 5 times faster than pure GA in our test case; ii) ANN training can be made very fast and successfully plays the role of an experienced investigator; iii) AGO can easily be adapted to other optimization problems. |
publishDate |
2002 |
dc.date.none.fl_str_mv |
2002-09-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-14392002000300011 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-14392002000300011 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/S1516-14392002000300011 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
ABM, ABC, ABPol |
publisher.none.fl_str_mv |
ABM, ABC, ABPol |
dc.source.none.fl_str_mv |
Materials Research v.5 n.3 2002 reponame:Materials research (São Carlos. Online) instname:Universidade Federal de São Carlos (UFSCAR) instacron:ABM ABC ABPOL |
instname_str |
Universidade Federal de São Carlos (UFSCAR) |
instacron_str |
ABM ABC ABPOL |
institution |
ABM ABC ABPOL |
reponame_str |
Materials research (São Carlos. Online) |
collection |
Materials research (São Carlos. Online) |
repository.name.fl_str_mv |
Materials research (São Carlos. Online) - Universidade Federal de São Carlos (UFSCAR) |
repository.mail.fl_str_mv |
dedz@power.ufscar.br |
_version_ |
1754212656981475328 |