File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Evolutionary artificial neural network based on Chemical Reaction Optimization

TitleEvolutionary artificial neural network based on Chemical Reaction Optimization
Authors
Yu, JJQLam, AYSLi, VOK
KeywordsArtificial neural networks
chemical reaction optimization
evolutionary algorithm
Issue Date2011
PublisherIEEE.
Citation
The 2011 IEEE Congress on Evolutionary Computation (CEC 2011), New Orleans, LA., 5-8 June 2011. In Proceedings of CEC 2011, 2011, p. 2083-2090 How to Cite?
DOI: http://dx.doi.org/10.1109/CEC.2011.5949872
AbstractEvolutionary algorithms (EAs) are very popular tools to design and evolve artificial neural networks (ANNs), especially to train them. These methods have advantages over the conventional backpropagation (BP) method because of their low computational requirement when searching in a large solution space. In this paper, we employ Chemical Reaction Optimization (CRO), a newly developed global optimization method, to replace BP in training neural networks. CRO is a population-based metaheuristics mimicking the transition of molecules and their interactions in a chemical reaction. Simulation results show that CRO outperforms many EA strategies commonly used to train neural networks. © 2011 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/142813
ISBN
978-1-4244-7835-4
References
References in Scopus

 

DC FieldValueLanguage
dc.contributor.authorYu, JJQen_HK
dc.contributor.authorLam, AYSen_HK
dc.contributor.authorLi, VOKen_HK
dc.date.accessioned2011-10-28T02:56:04Z-
dc.date.available2011-10-28T02:56:04Z-
dc.date.issued2011en_HK
dc.identifier.citationThe 2011 IEEE Congress on Evolutionary Computation (CEC 2011), New Orleans, LA., 5-8 June 2011. In Proceedings of CEC 2011, 2011, p. 2083-2090en_HK
dc.identifier.isbn978-1-4244-7835-4-
dc.identifier.urihttp://hdl.handle.net/10722/142813-
dc.description.abstractEvolutionary algorithms (EAs) are very popular tools to design and evolve artificial neural networks (ANNs), especially to train them. These methods have advantages over the conventional backpropagation (BP) method because of their low computational requirement when searching in a large solution space. In this paper, we employ Chemical Reaction Optimization (CRO), a newly developed global optimization method, to replace BP in training neural networks. CRO is a population-based metaheuristics mimicking the transition of molecules and their interactions in a chemical reaction. Simulation results show that CRO outperforms many EA strategies commonly used to train neural networks. © 2011 IEEE.en_HK
dc.languageengen_US
dc.publisherIEEE.-
dc.relation.ispartofProceedings of the Congress on Evolutionary Computation, CEC 2011en_HK
dc.subjectArtificial neural networksen_HK
dc.subjectchemical reaction optimizationen_HK
dc.subjectevolutionary algorithmen_HK
dc.titleEvolutionary artificial neural network based on Chemical Reaction Optimizationen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=978-1-4244-7835-4&volume=&spage=2083&epage=2090&date=2011&atitle=Evolutionary+artificial+neural+network+based+on+Chemical+Reaction+Optimization-
dc.identifier.emailLi, VOK:vli@eee.hku.hken_HK
dc.identifier.authorityLi, VOK=rp00150en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CEC.2011.5949872en_HK
dc.identifier.scopuseid_2-s2.0-80052008772en_HK
dc.identifier.hkuros196891en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-80052008772&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.spage2083en_HK
dc.identifier.epage2090en_HK
dc.description.otherThe 2011 IEEE Congress on Evolutionary Computation (CEC 2011), New Orleans, LA., 5-8 June 2011. In Proceedings of CEC 2011, 2011, p. 2083-2090-
dc.identifier.scopusauthoridYu, JJQ=48362019700en_HK
dc.identifier.scopusauthoridLam, AYS=35322184700en_HK
dc.identifier.scopusauthoridLi, VOK=7202621685en_HK

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats