File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Neural network correction for heats of formation with a larger experimental training set and new descriptors

TitleNeural network correction for heats of formation with a larger experimental training set and new descriptors
Authors
Issue Date2005
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/cplett
Citation
Chemical Physics Letters, 2005, v. 410 n. 1-3, p. 125-130 How to Cite?
AbstractA neural-network-based approach was applied to correct the systematic deviations of the calculated heats of formation for 180 organic molecules and led to greatly improved calculation results compared to the first-principles methods [J. Chem. Phys. 119 (2003) 11501]. In this work, this neural network approach has been improved by using new descriptors obtained from natural bond orbital analysis and an enlarged training set including organic, inorganic molecules and radicals. After the neural network correction, the root-mean-square deviations for the enlarged set decreases from 11.2, 15.2, 327.1 to 4.4, 3.5, 9.5 kcal/mol for the B3LYP/6-31G(d), B3LYP/6-311G(2d,d,p) and HF/6-31G(d) methods, respectively. © 2005 Elsevier B.V. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/70189
ISSN
2023 Impact Factor: 2.8
2023 SCImago Journal Rankings: 0.502
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorDuan, XMen_HK
dc.contributor.authorLi, ZHen_HK
dc.contributor.authorSong, GLen_HK
dc.contributor.authorWang, WNen_HK
dc.contributor.authorChen, GHen_HK
dc.contributor.authorFan, KNen_HK
dc.date.accessioned2010-09-06T06:20:33Z-
dc.date.available2010-09-06T06:20:33Z-
dc.date.issued2005en_HK
dc.identifier.citationChemical Physics Letters, 2005, v. 410 n. 1-3, p. 125-130en_HK
dc.identifier.issn0009-2614en_HK
dc.identifier.urihttp://hdl.handle.net/10722/70189-
dc.description.abstractA neural-network-based approach was applied to correct the systematic deviations of the calculated heats of formation for 180 organic molecules and led to greatly improved calculation results compared to the first-principles methods [J. Chem. Phys. 119 (2003) 11501]. In this work, this neural network approach has been improved by using new descriptors obtained from natural bond orbital analysis and an enlarged training set including organic, inorganic molecules and radicals. After the neural network correction, the root-mean-square deviations for the enlarged set decreases from 11.2, 15.2, 327.1 to 4.4, 3.5, 9.5 kcal/mol for the B3LYP/6-31G(d), B3LYP/6-311G(2d,d,p) and HF/6-31G(d) methods, respectively. © 2005 Elsevier B.V. All rights reserved.en_HK
dc.languageengen_HK
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/cpletten_HK
dc.relation.ispartofChemical Physics Lettersen_HK
dc.rightsChemical Physics Letters . Copyright © Elsevier BV.en_HK
dc.titleNeural network correction for heats of formation with a larger experimental training set and new descriptorsen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0009-2614&volume=410&spage=125&epage=130&date=2005&atitle=Neural+network+correction+for+heats+of+formation+with+a+larger+experimental+training+set+and+new+descriptors+en_HK
dc.identifier.emailChen, GH:ghc@yangtze.hku.hken_HK
dc.identifier.authorityChen, GH=rp00671en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.cplett.2005.05.046en_HK
dc.identifier.scopuseid_2-s2.0-20444489624en_HK
dc.identifier.hkuros116186en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-20444489624&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume410en_HK
dc.identifier.issue1-3en_HK
dc.identifier.spage125en_HK
dc.identifier.epage130en_HK
dc.identifier.isiWOS:000230330600025-
dc.publisher.placeNetherlandsen_HK
dc.identifier.scopusauthoridDuan, XM=35263610200en_HK
dc.identifier.scopusauthoridLi, ZH=8881429300en_HK
dc.identifier.scopusauthoridSong, GL=36799475100en_HK
dc.identifier.scopusauthoridWang, WN=7501758643en_HK
dc.identifier.scopusauthoridChen, GH=35253368600en_HK
dc.identifier.scopusauthoridFan, KN=7202978313en_HK
dc.identifier.issnl0009-2614-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats