Compact extreme learning machines for biological systems

In biological system modelling using data-driven black-box methods, it is essential to effectively and efficiently produce a parsimonious model to represent the system behaviour. The Extreme Learning Machine (ELM) is a recent development in fast learning paradigms. However, the derived model is not...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of computational biology and drug design Ročník 3; číslo 2; s. 112
Hlavní autoři: Li, Kang, Deng, Jing, He, Hai-Bo, Li, Yurong, Du, Da-Jun
Médium: Journal Article
Jazyk:angličtina
Vydáno: England 2010
Témata:
ISSN:1756-0756
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract In biological system modelling using data-driven black-box methods, it is essential to effectively and efficiently produce a parsimonious model to represent the system behaviour. The Extreme Learning Machine (ELM) is a recent development in fast learning paradigms. However, the derived model is not necessarily sparse. In this paper, an improved ELM is investigated, aiming to obtain a more compact model without significantly increasing the overall computational complexity. This is achieved by associating each model term to a regularized parameter, thus insignificant ones are automatically unselected, leading to improved model sparsity. Experimental results on biochemical data confirm its effectiveness.
AbstractList In biological system modelling using data-driven black-box methods, it is essential to effectively and efficiently produce a parsimonious model to represent the system behaviour. The Extreme Learning Machine (ELM) is a recent development in fast learning paradigms. However, the derived model is not necessarily sparse. In this paper, an improved ELM is investigated, aiming to obtain a more compact model without significantly increasing the overall computational complexity. This is achieved by associating each model term to a regularized parameter, thus insignificant ones are automatically unselected, leading to improved model sparsity. Experimental results on biochemical data confirm its effectiveness.In biological system modelling using data-driven black-box methods, it is essential to effectively and efficiently produce a parsimonious model to represent the system behaviour. The Extreme Learning Machine (ELM) is a recent development in fast learning paradigms. However, the derived model is not necessarily sparse. In this paper, an improved ELM is investigated, aiming to obtain a more compact model without significantly increasing the overall computational complexity. This is achieved by associating each model term to a regularized parameter, thus insignificant ones are automatically unselected, leading to improved model sparsity. Experimental results on biochemical data confirm its effectiveness.
In biological system modelling using data-driven black-box methods, it is essential to effectively and efficiently produce a parsimonious model to represent the system behaviour. The Extreme Learning Machine (ELM) is a recent development in fast learning paradigms. However, the derived model is not necessarily sparse. In this paper, an improved ELM is investigated, aiming to obtain a more compact model without significantly increasing the overall computational complexity. This is achieved by associating each model term to a regularized parameter, thus insignificant ones are automatically unselected, leading to improved model sparsity. Experimental results on biochemical data confirm its effectiveness.
Author Du, Da-Jun
Li, Kang
Li, Yurong
He, Hai-Bo
Deng, Jing
Author_xml – sequence: 1
  givenname: Kang
  surname: Li
  fullname: Li, Kang
  email: k.li@qub.ac.uk
  organization: School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, Belfast, UK. k.li@qub.ac.uk
– sequence: 2
  givenname: Jing
  surname: Deng
  fullname: Deng, Jing
– sequence: 3
  givenname: Hai-Bo
  surname: He
  fullname: He, Hai-Bo
– sequence: 4
  givenname: Yurong
  surname: Li
  fullname: Li, Yurong
– sequence: 5
  givenname: Da-Jun
  surname: Du
  fullname: Du, Da-Jun
BackLink https://www.ncbi.nlm.nih.gov/pubmed/20852336$$D View this record in MEDLINE/PubMed
BookMark eNo1jz1PwzAYhD0U0Q_4AwwoG1OKXztOnBHSAkWVWGCObOdNCYrjYicS_fdYoix30unR6W5JZoMbkJAboGsQNLvfvVaPm82a0RhQLhiXM7KAQuQpjTInyxC-KM2ZhPySzBmVEeH5gsjK2aMyY4I_o0eLSY_KD91wSKwyn92AIWmdT3TnenfojOqTcAoj2nBFLlrVB7w--4p8PG3fq5d0__a8qx72qclAytS0gJwVBctoBiYvWh1zA8CwjBMw1xxLikxIjrrRKDQwzaGFOB0bTQu2Ind_vUfvvicMY227YLDv1YBuCnUhBJScl2Ukb8_kpC029dF3VvlT_X-W_QJkzlY1
CitedBy_id crossref_primary_10_1016_j_neucom_2012_11_030
crossref_primary_10_1016_j_foodcont_2017_02_045
crossref_primary_10_1002_minf_201501008
crossref_primary_10_1155_2016_5197932
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1504/IJCBDD.2010.035238
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
ExternalDocumentID 20852336
Genre Journal Article
GroupedDBID ---
0R~
29J
4.4
5GY
ABJNI
ACGFS
ACIWK
ACPRK
AFRAH
ALMA_UNASSIGNED_HOLDINGS
ALSBL
CGR
CS3
CUY
CVF
DU5
EBS
ECM
EIF
EJD
F5P
H13
HZ~
MET
MIE
NPM
O9-
P2P
RTD
7X8
ID FETCH-LOGICAL-c4188-cf1e327724041c67fbc41c112e9852e6b3e90e2583ebdbe5b12b31f1175edb072
IEDL.DBID 7X8
ISSN 1756-0756
IngestDate Fri Jul 11 11:20:41 EDT 2025
Thu Jan 02 22:06:16 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c4188-cf1e327724041c67fbc41c112e9852e6b3e90e2583ebdbe5b12b31f1175edb072
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://digitalcommons.uri.edu/ele_facpubs/618
PMID 20852336
PQID 755193399
PQPubID 23479
ParticipantIDs proquest_miscellaneous_755193399
pubmed_primary_20852336
PublicationCentury 2000
PublicationDate 2010-00-00
20100101
PublicationDateYYYYMMDD 2010-01-01
PublicationDate_xml – year: 2010
  text: 2010-00-00
PublicationDecade 2010
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle International journal of computational biology and drug design
PublicationTitleAlternate Int J Comput Biol Drug Des
PublicationYear 2010
SSID ssj0062816
Score 1.7773858
Snippet In biological system modelling using data-driven black-box methods, it is essential to effectively and efficiently produce a parsimonious model to represent...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 112
SubjectTerms Algorithms
Artificial Intelligence
Computer Simulation
Humans
Models, Biological
Neural Networks (Computer)
Systems Biology - methods
Title Compact extreme learning machines for biological systems
URI https://www.ncbi.nlm.nih.gov/pubmed/20852336
https://www.proquest.com/docview/755193399
Volume 3
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELaAMrDwEK_ykgfWqI7fmRC0VICg6gCoWxQ_ghiaFlL4_ZwTtxtiYIgHS46iu_PdF9_5PoQuibCsAMefwFMmnHKdGOspKMTBNHfENPwpr49qNNKTSTaOtTl1LKtc-sTGUbuZDWfkPSUC1oBwejX_SAJpVEiuRgaNddRhgGRCRZearJIIkuqG-RQCJPw0wxDvzAjCe_cP_ZvBIFZ2AQZh-neE2USa4c4_v3EXbUeIia9bm9hDa77aR7rZ-HaBwRmHI0Ec6SLe8LQpp_Q1BviK255MQXG47fFcH6CX4e1z_y6JrAmJ5SmYvS1TzyiAZk54aqUqDcxbgFU-04J6aZjPiKdCM2-c8cKk1LC0DC07vTNE0UO0Uc0qf4wwz5zkBWAwoyyXVmQpvEuSzLECFhSqi_BSDjlYZUg1FJWffdX5ShJddNTKMp-33TPyQApKGZMnfy8-RVttsj6ceJyhTgk70p-jTfu9eK8_LxptwzgaP_0A3Tqy0Q
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Compact+extreme+learning+machines+for+biological+systems&rft.jtitle=International+journal+of+computational+biology+and+drug+design&rft.au=Li%2C+Kang&rft.au=Deng%2C+Jing&rft.au=He%2C+Hai-Bo&rft.au=Li%2C+Yurong&rft.date=2010-01-01&rft.issn=1756-0756&rft.volume=3&rft.issue=2&rft.spage=112&rft_id=info:doi/10.1504%2FIJCBDD.2010.035238&rft_id=info%3Apmid%2F20852336&rft_id=info%3Apmid%2F20852336&rft.externalDocID=20852336
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1756-0756&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1756-0756&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1756-0756&client=summon