A new growing pruning deep learning neural network algorithm (GP-DLNN)

During the last decade, a significant research progress has been drawn in both the theoretical aspects and the applications of Deep Learning Neural Networks. Besides their spectacular applications, optimal architectures of these neural networks may speed up the learning process and exhibit better ge...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Neural computing & applications Ročník 32; číslo 24; s. 18143 - 18159
Hlavní autori: Zemouri, Ryad, Omri, Nabil, Fnaiech, Farhat, Zerhouni, Noureddine, Fnaiech, Nader
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: London Springer London 01.12.2020
Springer Nature B.V
Springer Verlag
Predmet:
ISSN:0941-0643, 1433-3058
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract During the last decade, a significant research progress has been drawn in both the theoretical aspects and the applications of Deep Learning Neural Networks. Besides their spectacular applications, optimal architectures of these neural networks may speed up the learning process and exhibit better generalization results. So far, many growing and pruning algorithms have been proposed by many researchers to deal with the optimization of standard Feedforward Neural Network architectures. However, applying both the growing and the pruning on the same net may lead a good model for a big data set and hence good selection results. This work is devoted to propose a new Growing and pruning Learning algorithm for Deep Neural Networks. This new algorithm is presented and applied on diverse medical data sets. It is shown that this algorithm outperforms various other artificial intelligent techniques in terms of accuracy and simplicity of the resulting architecture.
AbstractList During the last decade, a significant research progress has been drawn in both the theoretical aspects and the applications of Deep Learning Neural Networks. Besides their spectacular applications, optimal architectures of these neural networks may speed up the learning process and exhibit better generalization results. So far, many growing and pruning algorithms have been proposed by many researchers to deal with the optimization of standard Feedforward Neural Network architectures. However, applying both the growing and the pruning on the same net may lead a good model for a big data set and hence good selection results. This work is devoted to propose a new Growing and pruning Learning algorithm for Deep Neural Networks. This new algorithm is presented and applied on diverse medical data sets. It is shown that this algorithm outperforms various other artificial intelligent techniques in terms of accuracy and simplicity of the resulting architecture.
Author Omri, Nabil
Zerhouni, Noureddine
Fnaiech, Farhat
Zemouri, Ryad
Fnaiech, Nader
Author_xml – sequence: 1
  givenname: Ryad
  orcidid: 0000-0002-3283-9391
  surname: Zemouri
  fullname: Zemouri, Ryad
  email: ryad.zemouri@cnam.fr
  organization: Cedric-Lab, CNAM, HESAM Université
– sequence: 2
  givenname: Nabil
  surname: Omri
  fullname: Omri, Nabil
  organization: FEMTO-ST, University of Bourgogne-Franche-Comté
– sequence: 3
  givenname: Farhat
  surname: Fnaiech
  fullname: Fnaiech, Farhat
  organization: ENSIT, LR13ES03 SIME, Université de Tunis
– sequence: 4
  givenname: Noureddine
  surname: Zerhouni
  fullname: Zerhouni, Noureddine
  organization: FEMTO-ST, University of Bourgogne-Franche-Comté
– sequence: 5
  givenname: Nader
  surname: Fnaiech
  fullname: Fnaiech, Nader
  organization: ISIMa- Institut supérieur d’informatique de Mahdia
BackLink https://hal.science/hal-02462260$$DView record in HAL
BookMark eNp9kE9PwjAchhuDiYB-AU9LvMhh-uvfrUeCAiYEPei5KV0Hw9FiNyR-ewfTmHjg9Kbt8zRv3h7qOO8sQtcY7jBAcl8BcIJjwDIGhqWI0zPUxYzSmAJPO6gLkjXPgtEL1KuqNQAwkfIuGg8jZ_fRMvh94ZbRNuzcITNrt1FpdTienN0FXTZR7314j3S59KGoV5vodvISP8zm88ElOs91Wdmrn-yjt_Hj62gaz54nT6PhLDYMcB0n1iQkEwtDs5wyqYFzq4nWTAosJDa5zCVmXNIsY3QhrOH5gmNLOBiRmIWmfTRo_13pUm1DsdHhS3ldqOlwpg53QJggRMAnbtiblt0G_7GzVa3WfhdcU08RllAqWJIcqLSlTPBVFWyuTFHruvCuDrooFQZ1WFi1C6tmYXVcWKWNSv6pv41OSrSVqgZ2Sxv-Wp2wvgFAd43g
CitedBy_id crossref_primary_10_1155_2021_5570945
crossref_primary_10_1016_j_conbuildmat_2023_131827
crossref_primary_10_1111_exsy_13793
crossref_primary_10_1016_j_engappai_2023_107713
crossref_primary_10_1109_ACCESS_2020_2985257
crossref_primary_10_1108_K_04_2024_0982
crossref_primary_10_7717_peerj_cs_1903
crossref_primary_10_1016_j_engappai_2024_108034
crossref_primary_10_1016_j_geothermics_2024_103004
crossref_primary_10_3390_app11188628
crossref_primary_10_1016_j_engappai_2024_107903
crossref_primary_10_1016_j_tins_2022_06_002
crossref_primary_10_1007_s00521_024_10932_6
crossref_primary_10_1007_s10706_023_02535_0
crossref_primary_10_1016_j_tins_2023_07_008
crossref_primary_10_1016_j_envsoft_2022_105399
crossref_primary_10_3390_a14050158
crossref_primary_10_3390_app9081526
crossref_primary_10_48175_IJARSCT_28835
crossref_primary_10_1016_j_ifacol_2023_10_1112
crossref_primary_10_1007_s11030_021_10256_w
crossref_primary_10_1016_j_engappai_2024_109552
crossref_primary_10_1371_journal_pone_0293196
crossref_primary_10_3390_axioms12020164
crossref_primary_10_1007_s00521_024_09592_3
Cites_doi 10.1109/MECBME.2018.8402426
10.1109/TPAMI.2013.50
10.1109/72.248452
10.1109/TMI.2016.2553401
10.1109/TNNLS.2011.2178124
10.1109/ICICIP.2010.5564272
10.1002/int.4550080406
10.1007/s00521-011-0585-7
10.1109/TNNLS.2018.2790388
10.1016/j.asoc.2008.01.013
10.1016/j.amc.2008.05.049
10.1109/WSOM.2017.8020002
10.1109/ISCCSP.2004.1296579
10.1109/72.572102
10.1007/s11063-011-9196-7
10.1016/j.neucom.2005.04.010
10.1016/j.compbiomed.2017.04.012
10.1016/j.eswa.2016.05.022
10.1109/TFUZZ.2010.2070841
10.1162/neco.1997.9.1.185
10.1109/TNN.2006.878121
10.1109/TNNLS.2014.2350957
10.1007/s10462-016-9526-2
10.1109/IJCNN.2008.4634268
10.1016/j.neunet.2014.12.001
10.1007/s00521-013-1367-1
10.1109/TNN.2008.2005604
10.1016/j.compmedimag.2016.07.004
10.1016/0925-2312(94)90055-8
10.1109/72.963775
10.1016/j.neunet.2014.09.003
10.1016/j.media.2016.07.007
10.1007/s10489-016-0767-1
10.1016/j.neucom.2017.02.038
10.1016/j.neucom.2012.07.023
10.1016/j.neunet.2011.10.003
10.1109/ICNN.1993.298572
10.1109/HSI.2008.4581409
10.1109/TSMCB.2009.2021849
10.1109/72.774273
10.1016/j.neucom.2005.11.005
10.1016/j.neunet.2016.10.011
10.1016/j.neucom.2016.01.034
10.1016/j.neucom.2008.04.004
10.1109/IWACI.2011.6160018
10.1016/j.compmedimag.2017.12.001
10.1016/j.neucom.2011.05.025
10.1109/TNN.2003.813832
10.1109/IJCNN.2003.1223407
10.1109/TNN.2009.2036259
10.1109/ICCIAutom.2011.6356672
10.1109/TNNLS.2015.2479223
10.1109/72.572092
10.1109/IJCNN.2016.7727519
10.1073/pnas.87.23.9193
10.1109/TNNLS.2017.2716952
10.1109/ACCESS.2016.2624938
10.1109/TNNLS.2011.2178315
10.1016/j.media.2017.01.009
10.1109/TKDE.2008.239
10.1109/TMI.2016.2528120
10.1109/TSMCB.2004.834428
10.1109/IJCNN.2002.1007808
10.1016/j.neucom.2015.12.003
10.1038/nature14539
10.1109/72.80290
10.1109/72.623214
10.1016/j.neucom.2007.09.016
10.1016/j.ymssp.2015.10.025
10.1038/s41598-017-03405-5
10.1109/TNN.2006.871707
10.1109/72.839013
10.1016/j.neucom.2007.08.026
10.1109/TSMCB.2008.2008724
10.1109/ICNN.1988.23864
10.1016/j.neucom.2010.05.022
10.1038/s41598-017-04075-z
10.1016/j.image.2016.05.007
ContentType Journal Article
Copyright Springer-Verlag London Ltd., part of Springer Nature 2019
Springer-Verlag London Ltd., part of Springer Nature 2019.
Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml – notice: Springer-Verlag London Ltd., part of Springer Nature 2019
– notice: Springer-Verlag London Ltd., part of Springer Nature 2019.
– notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID AAYXX
CITATION
8FE
8FG
AFKRA
ARAPS
BENPR
BGLVJ
CCPQU
DWQXO
HCIFZ
P5Z
P62
PHGZM
PHGZT
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
1XC
DOI 10.1007/s00521-019-04196-8
DatabaseName CrossRef
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central
Technology Collection
ProQuest One Community College
ProQuest Central
SciTech Premium Collection
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic (New)
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
Hyper Article en Ligne (HAL)
DatabaseTitle CrossRef
Advanced Technologies & Aerospace Collection
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest One Academic Eastern Edition
SciTech Premium Collection
ProQuest One Community College
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
Advanced Technologies & Aerospace Database
ProQuest One Applied & Life Sciences
ProQuest One Academic UKI Edition
ProQuest Central Korea
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList
Advanced Technologies & Aerospace Collection
Database_xml – sequence: 1
  dbid: P5Z
  name: Advanced Technologies & Aerospace Database
  url: https://search.proquest.com/hightechjournals
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1433-3058
EndPage 18159
ExternalDocumentID oai:HAL:hal-02462260v1
10_1007_s00521_019_04196_8
GroupedDBID -4Z
-59
-5G
-BR
-EM
-Y2
-~C
.4S
.86
.DC
.VR
06D
0R~
0VY
123
1N0
1SB
2.D
203
28-
29N
2J2
2JN
2JY
2KG
2LR
2P1
2VQ
2~H
30V
4.4
406
408
409
40D
40E
53G
5QI
5VS
67Z
6NX
8FE
8FG
8TC
8UJ
95-
95.
95~
96X
AAAVM
AABHQ
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AAOBN
AARHV
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
AAYTO
AAYZH
ABAKF
ABBBX
ABBXA
ABDBF
ABDZT
ABECU
ABFTD
ABFTV
ABHLI
ABHQN
ABJNI
ABJOX
ABKCH
ABKTR
ABLJU
ABMNI
ABMQK
ABNWP
ABQBU
ABQSL
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABWNU
ABXPI
ACAOD
ACBXY
ACDTI
ACGFS
ACHSB
ACHXU
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACPIV
ACSNA
ACUHS
ACZOJ
ADHHG
ADHIR
ADIMF
ADINQ
ADKNI
ADKPE
ADMLS
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFIE
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEKMD
AEMSY
AENEX
AEOHA
AEPYU
AESKC
AETLH
AEVLU
AEXYK
AFBBN
AFEXP
AFGCZ
AFKRA
AFLOW
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGGDS
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHSBF
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJBLW
AJRNO
AJZVZ
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMXSW
AMYLF
AMYQR
AOCGG
ARAPS
ARCSS
ARMRJ
ASPBG
AVWKF
AXYYD
AYJHY
AZFZN
B-.
B0M
BA0
BBWZM
BDATZ
BENPR
BGLVJ
BGNMA
BSONS
CAG
CCPQU
COF
CS3
CSCUP
DDRTE
DL5
DNIVK
DPUIP
DU5
EAD
EAP
EBLON
EBS
ECS
EDO
EIOEI
EJD
EMI
EMK
EPL
ESBYG
EST
ESX
F5P
FEDTE
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRRFC
FSGXE
FWDCC
GGCAI
GGRSB
GJIRD
GNWQR
GQ6
GQ7
GQ8
GXS
H13
HCIFZ
HF~
HG5
HG6
HMJXF
HQYDN
HRMNR
HVGLF
HZ~
I-F
I09
IHE
IJ-
IKXTQ
ITM
IWAJR
IXC
IZIGR
IZQ
I~X
I~Z
J-C
J0Z
JBSCW
JCJTX
JZLTJ
KDC
KOV
KOW
LAS
LLZTM
M4Y
MA-
N2Q
N9A
NB0
NDZJH
NPVJJ
NQJWS
NU0
O9-
O93
O9G
O9I
O9J
OAM
P19
P2P
P62
P9O
PF0
PT4
PT5
QOK
QOS
R4E
R89
R9I
RHV
RIG
RNI
RNS
ROL
RPX
RSV
RZK
S16
S1Z
S26
S27
S28
S3B
SAP
SCJ
SCLPG
SCO
SDH
SDM
SHX
SISQX
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
SZN
T13
T16
TSG
TSK
TSV
TUC
TUS
U2A
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W23
W48
WK8
YLTOR
Z45
Z5O
Z7R
Z7S
Z7V
Z7W
Z7X
Z7Y
Z7Z
Z81
Z83
Z86
Z88
Z8M
Z8N
Z8P
Z8Q
Z8R
Z8S
Z8T
Z8U
Z8W
Z92
ZMTXR
~8M
~EX
AAPKM
AAYXX
ABBRH
ABDBE
ABFSG
ABRTQ
ACSTC
ADHKG
ADKFA
AEZWR
AFDZB
AFFHD
AFHIU
AFOHR
AGQPQ
AHPBZ
AHWEU
AIXLP
ATHPR
AYFIA
CITATION
PHGZM
PHGZT
PQGLB
DWQXO
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
1XC
ID FETCH-LOGICAL-c401t-7ec72d6bc3df349a055ea2aa4961691cf9f914593dd43b6ec5fb51e250c67cba3
IEDL.DBID P5Z
ISICitedReferencesCount 24
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000595603200023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0941-0643
IngestDate Sat Nov 29 15:01:32 EST 2025
Tue Nov 04 23:00:05 EST 2025
Tue Nov 18 22:41:04 EST 2025
Sat Nov 29 02:59:12 EST 2025
Fri Feb 21 02:35:52 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 24
Keywords Deep learning
Constructive neural networks
Deep neural networks
Growing algorithm
Pruning algorithm
Language English
License Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c401t-7ec72d6bc3df349a055ea2aa4961691cf9f914593dd43b6ec5fb51e250c67cba3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-3283-9391
PQID 2473364771
PQPubID 2043988
PageCount 17
ParticipantIDs hal_primary_oai_HAL_hal_02462260v1
proquest_journals_2473364771
crossref_citationtrail_10_1007_s00521_019_04196_8
crossref_primary_10_1007_s00521_019_04196_8
springer_journals_10_1007_s00521_019_04196_8
PublicationCentury 2000
PublicationDate 2020-12-01
PublicationDateYYYYMMDD 2020-12-01
PublicationDate_xml – month: 12
  year: 2020
  text: 2020-12-01
  day: 01
PublicationDecade 2020
PublicationPlace London
PublicationPlace_xml – name: London
– name: Heidelberg
PublicationTitle Neural computing & applications
PublicationTitleAbbrev Neural Comput & Applic
PublicationYear 2020
Publisher Springer London
Springer Nature B.V
Springer Verlag
Publisher_xml – name: Springer London
– name: Springer Nature B.V
– name: Springer Verlag
References CastellanoGFanelliAMPelilloMAn iterative pruning algorithm for feedforward neural networksIEEE Trans Neural Netw199783519531
Ai F (2011) A new pruning algorithm for feedforward neural networks. In: The fourth international workshop on advanced computational intelligence, pp 286–289
XuJLuoXWangGGilmoreHMadabhushiAA deep convolutional neural network for segmenting and classifying epithelial and stromal regions in histopathological imagesNeurocomputing2016191214223
AugastaMGKathirvalavakumarTA novel pruning algorithm for optimizing feedforward neural network of classification problemsNeural Process Lett2011343241
IslamMMSattarMAAminMFYaoXMuraseKA new adaptive merging and growing algorithm for designing artificial neural networksIEEE Trans Syst Man Cybern Part B (Cybern)2009393705722
ZhangRLanYHuangGBXuZBUniversal approximation of extreme learning machine with adaptive growth of hidden nodesIEEE Trans Neural Netw Learn Syst2012232365371
ReedRPruning algorithms—a surveyIEEE Trans Neural Netw199345740747
EngelbrechtAPA new pruning heuristic based on variance analysis of sensitivity informationIEEE Trans Neural Netw200112613861399
FarisHAljarahIMirjaliliSTraining feedforward neural networks using multi-verse optimizer for binary classification problemsAppl Intell2016452322332
CireşanDCGiustiAGambardellaLMSchmidhuberJMitosis detection in breast cancer histology images with deep neural networks2013BerlinSpringer411418
Spanhol FA, Oliveira LS, Petitjean C, Heutte L (2016) Breast cancer histopathological image classification using convolutional neural networks. In: 2016 international joint conference on neural networks (IJCNN), pp 2560–2567
WahabNKhanALeeYSTwo-phase deep convolutional neural network for reducing class skewness in histopathological images based breast cancer detectionComput Biol Med2017858697
YaoXA review of evolutionary artificial neural networksInt J Intell Syst199384539567
FnaiechNFnaiechFJervisBCherietMThe combined statistical stepwise and iterative neural network pruning algorithmIntell Autom Soft Comput2009154573589
Sun W, Tseng TLB, Zhang J, Qian W (2017) Enhancing deep convolutional neural network scheme for breast cancer diagnosis with unlabeled data. Comput Med Imaging Graph 57, 4–9. Recent developments in machine learning for medical imaging applications
van der MaatenLHintonGVisualizing data using t-sneJ Mach Learn Res2008911257926051225.68219
DuffnerSGarciaCAn online backpropagation algorithm with validation error-based adaptive learning rate2007BerlinSpringer249258
Qiao J, Zhang Y, Han H (2008) Fast unit pruning algorithm for feedforward neural network design. Appl Math Comput 205(2):622 – 627. Special issue on advanced intelligent computing theory and methodology in applied mathematics and computation
AlbarqouniSBaurCAchillesFBelagiannisVDemirciSNavabNAggnet: deep learning from crowds for mitosis detection in breast cancer histology imagesIEEE Trans Med Imaging201635513131321
SetionoRA penalty-function approach for pruning feedforward neural networksNeural Comput1997911852040872.68154
ChenCLPLiuZBroad learning system: an effective and efficient incremental learning system without the need for deep architectureIEEE Trans Neural Netw Learn Syst201829110243746789
HanHQiaoJA self-organizing fuzzy neural network based on a growing-and-pruning algorithmIEEE Trans Fuzzy Syst201018611291143
Jacek C, Zarzycki H (2003) Application of rough sets in the presumptive diagnosis of urinary system diseases. In: Artificial intelligence and security in computing systems, ACS’2002 9th international conference proceedings. Kluwer Academic Publishers, pp 41–51
SubiratsJLFrancoLJerezJMC-mantec: a novel constructive neural network algorithm incorporating competition between neuronsNeural Netw201226130140
TomèDMontiFBaroffioLBondiLTagliasacchiMTubaroSDeep convolutional neural networks for pedestrian detectionSignal Process Image Commun201647482489
Goodfellow IJ, Warde-farley D, Mirza M, Courville A, Bengio Y (2013) Maxout networks. In: In ICML
HanHGZhangSQiaoJFAn adaptive growing and pruning algorithm for designing recurrent neural networkNeurocomputing20172425162
Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Gordon GJ, Dunson DB (eds) Proceedings of the fourteenth international conference on artificial intelligence and statistics (AISTATS-11), vol 15, Journal of machine learning research—workshop and conference proceedings, pp 315–323
ZhangRXuZBHuangGBWangDGlobal convergence of online bp training with dynamic learning rateIEEE Trans Neural Netw Learn Syst2012232330341
Montana DJ, Davis L (1989) Training feedforward neural networks using genetic algorithms. In: Proceedings of the 11th international joint conference on artificial intelligence-volume 1, IJCAI’89. Morgan Kaufmann Publishers Inc., San Francisco, pp 762–767
LauretPFockEMaraTAA node pruning algorithm based on a Fourier amplitude sensitivity test methodIEEE Trans Neural Netw2006172273293
ShresthaSBSongQRobust learning in spikepropNeural Netw20178654681428.68254
BengioYCourvilleAVincentPRepresentation learning: a review and new perspectivesIEEE Trans Pattern Anal Mach Intell201335817981828
Lichman M (2013) UCI machine learning repository
Zeiler MD (2012) Adadelta: an adaptive learning rate method. abs/1212.5701
IslamMMSattarMAAminMFYaoXMuraseKA new constructive algorithm for architectural and functional adaptation of artificial neural networksIEEE Trans Syst Man Cybern Part B (Cybern)200939615901605
Zhang Z, Qiao J (2010) A node pruning algorithm for feedforward neural network based on neural complexity. In: 2010 international conference on intelligent control and information processing, pp 406–410
FrancoLJerezJMConstructive neural networks2009Berlin, HeidelbergSpringer
MicheYSorjamaaABasPSimulaOJuttenCLendasseAOp-elm: optimally pruned extreme learning machineIEEE Trans Neural Netw2010211158162
WolbergWHMangasarianOMultisurface method of pattern separation for medical diagnosis applied to breast cytologyProc Natl Acad Sci USA199087919391960709.92537
GreenspanHvan GinnekenBSummersRMGuest editorial deep learning in medical imaging: overview and future promise of an exciting new techniqueIEEE Trans Med Imaging201635511531159
XingHJHuBGTwo-phase construction of multilayer perceptrons using information theoryIEEE Trans Neural Netw2009204715721
Sietsma J, Dow RJF (1988) Neural net pruning-why and how. In: IEEE 1988 international conference on neural networks, vol 1, pp 325–333
HanHGQiaoJFA structure optimisation algorithm for feedforward neural network constructionNeurocomputing201399347357
ShresthaSBSongQAdaptive learning rate of spikeprop based on weight convergence analysisNeural Netw2015631851981325.68197
ParekhRYangJHonavarVConstructive neural-network learning algorithms for pattern classificationIEEE Trans Neural Netw2000112436451
PonnapalliPVSHoKCThomsonMA formal selection and pruning algorithm for feedforward artificial neural network optimizationIEEE Trans Neural Netw1999104964968
QiaoJLiFHanHLiWConstructive algorithm for fully connected cascade feedforward neural networksNeurocomputing2016182154164
Sabo D, Yu XH (2008) A new pruning algorithm for neural network dimension analysis. In: 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence), pp 3313–3318
WanWMabuSShimadaKHirasawaKHuJEnhancing the generalization ability of neural networks through controlling the hidden layersAppl Soft Comput200991404414
AugastaMGKathirvalavakumarTPruning algorithms of neural networks—a comparative studyCent Eur J Comput Sci201333105115
WuXRóżyckiPWilamowskiBMA hybrid constructive algorithm for single-layer feedforward networks learningIEEE Trans Neural Netw Learn Syst2015268165916683454963
MahmudMKaiserMHussainAVassanelliSApplications of deep learning and reinforcement learning to biological dataIEEE Trans Neural Netw Learn Syst201829206320793811399
XuJHoDWA new training and pruning algorithm based on node dependence and Jacobian rank deficiencyNeurocomputing2006701544558
WangGA perspective on deep imagingIEEE Access2016489148924
Nielsen AB, Hansen LK (2008) Structure learning by pruning in independent component analysis. Neurocomputing 71(10):2281–2290. Neurocomputing for vision research advances in blind signal processing
KwokTYYeungDYObjective functions for training new hidden units in constructive neural networksIEEE Trans Neural Netw19978511311148
NayakJNaikBBeheraHA novel nature inspired firefly algorithm with higher order neural network: performance analysisInt J Eng Sci Technol2016191197211
HanZWeiBZhengYYinYLiKLiSBreast cancer multi-classification from histopathological images with structured deep learning modelSci Rep2017714172
SridharSSPonnavaikkoMA novel constructive neural network architecture based on improved adaptive learning strategy for pattern classification2012BerlinSpringer423433
Thivierge JP, Rivest F, Shultz TR (2003) A dual-phase technique for pruning constructive networks. In: Proceedings of the international joint conference on neural networks, 2003, vol 1, pp 559–564
YangXSDebSCuckoo search: recent advances and applicationsNeural Comput Appl2014241169174
Rifai S, Vincent P, Muller X, Glorot X, Bengio Y (2011) Contractive auto-en- coders: explicit invariance during feature extraction. In: Proceedings of the 28th international conference on machine learning (ICML-11), pp 833–840
Zemouri R, Omri N, Devalland C, Arnould L, Morello B, Zerhouni N, Fnaiech F (2018) Breast cancer diagnosis based on joint variable selection and constructive deep neural network. In: 4th IEEE middle east conference on biomedical engineering (MECBME 2018)
Zeraatkar E, Soltani M, Karimaghaee P (2011) A fast convergence algorithm for bpnn based on optimal control theory based learning rate. In: The 2nd international conference on control, instrumentation and automation, pp 292–297
Puma-Villanueva WJ, dos Santos EP, Zuben FJV (2012) A constructive algorithm to synthesize arbitrarily connected feedforward neural networks. Neurocomputing 75(1), 14–32. B
H Yu (4196_CR90) 2018; 99
J Xu (4196_CR86) 2006; 70
S Duffner (4196_CR13) 2007
4196_CR1
E Hosseini-Asl (4196_CR30) 2016; 27
GB Huang (4196_CR31) 2004; 34
MM Islam (4196_CR34) 2009; 39
X Yao (4196_CR89) 1993; 8
P Vincent (4196_CR79) 2010; 11
4196_CR33
DC Cireşan (4196_CR11) 2013
4196_CR37
R Zemouri (4196_CR94) 2012; 21
MM Islam (4196_CR35) 2009; 39
D Tomè (4196_CR78) 2016; 47
AP Engelbrecht (4196_CR14) 2001; 12
M Mahmud (4196_CR48) 2018; 29
4196_CR42
B Pérez-Sánchez (4196_CR57) 2016; 49
4196_CR46
MM Islam (4196_CR36) 2003; 14
T Kooi (4196_CR39) 2017; 35
4196_CR49
SC Huang (4196_CR32) 1991; 2
MG Augasta (4196_CR3) 2011; 34
M Saha (4196_CR65) 2017; 7
M Saha (4196_CR66) 2018; 64
SB Shrestha (4196_CR69) 2015; 63
W Wan (4196_CR81) 2009; 9
J Xu (4196_CR87) 2016; 191
R Setiono (4196_CR68) 1997; 9
4196_CR93
4196_CR92
4196_CR91
4196_CR10
4196_CR96
4196_CR95
F Jia (4196_CR38) 2016; 72–73
4196_CR99
4196_CR18
WH Wolberg (4196_CR83) 1990; 87
4196_CR16
TY Kwok (4196_CR41) 1997; 8
P Lauret (4196_CR43) 2006; 17
R Zhang (4196_CR97) 2012; 23
N Fnaiech (4196_CR17) 2009; 15
HJ Xing (4196_CR85) 2009; 20
N Dhungel (4196_CR12) 2017; 37
4196_CR21
4196_CR20
H He (4196_CR29) 2009; 21
(4196_CR19) 2009
HG Han (4196_CR25) 2013; 99
4196_CR28
G Wang (4196_CR82) 2016; 4
S Albarqouni (4196_CR2) 2016; 35
G Castellano (4196_CR7) 1997; 8
R Zhang (4196_CR98) 2012; 23
CLP Chen (4196_CR9) 2018; 29
L van der Maaten (4196_CR47) 2008; 9
B Chandra (4196_CR8) 2016; 63
4196_CR72
X Wu (4196_CR84) 2015; 26
4196_CR71
4196_CR76
R Reed (4196_CR62) 1993; 4
4196_CR73
4196_CR77
TY Kwok (4196_CR40) 1997; 8
H Faris (4196_CR15) 2016; 45
JL Subirats (4196_CR75) 2012; 26
H Han (4196_CR24) 2010; 18
Y LeCun (4196_CR44) 2015; 521
PVS Ponnapalli (4196_CR58) 1999; 10
Y Miche (4196_CR50) 2010; 21
XS Yang (4196_CR88) 2014; 24
L Behera (4196_CR5) 2006; 17
Y LeCun (4196_CR45) 1990
R Parekh (4196_CR55) 2000; 11
SS Sridhar (4196_CR74) 2012
J Schmidhuber (4196_CR67) 2015; 61
HG Han (4196_CR26) 2017; 242
H Greenspan (4196_CR22) 2016; 35
4196_CR54
4196_CR52
4196_CR51
Z Han (4196_CR27) 2017; 7
4196_CR56
4196_CR59
J Nayak (4196_CR53) 2016; 19
SB Shrestha (4196_CR70) 2017; 86
4196_CR61
4196_CR64
N Wahab (4196_CR80) 2017; 85
4196_CR63
MG Augasta (4196_CR4) 2013; 3
J Qiao (4196_CR60) 2016; 182
Y Bengio (4196_CR6) 2013; 35
M Hagiwara (4196_CR23) 1994; 6
References_xml – reference: Thivierge JP, Rivest F, Shultz TR (2003) A dual-phase technique for pruning constructive networks. In: Proceedings of the international joint conference on neural networks, 2003, vol 1, pp 559–564
– reference: KwokTYYeungDYConstructive algorithms for structure learning in feedforward neural networks for regression problemsIEEE Trans Neural Netw199783630645
– reference: Zhang Z, Qiao J (2010) A node pruning algorithm for feedforward neural network based on neural complexity. In: 2010 international conference on intelligent control and information processing, pp 406–410
– reference: KwokTYYeungDYObjective functions for training new hidden units in constructive neural networksIEEE Trans Neural Netw19978511311148
– reference: Lan Y, Soh YC, Huang GB (2010) Constructive hidden nodes selection of extreme learning machine for regression. Neurocomputing 73(16):3191–3199. 10th Brazilian symposium on neural networks (SBRN2008)
– reference: Montana DJ, Davis L (1989) Training feedforward neural networks using genetic algorithms. In: Proceedings of the 11th international joint conference on artificial intelligence-volume 1, IJCAI’89. Morgan Kaufmann Publishers Inc., San Francisco, pp 762–767
– reference: Sietsma J, Dow RJF (1988) Neural net pruning-why and how. In: IEEE 1988 international conference on neural networks, vol 1, pp 325–333
– reference: Narasimha PL, Delashmit WH, Manry MT, Li J, Maldonado F (2008) An integrated growing-pruning method for feedforward network training. Neurocomputing 71(13), 2831 – 2847. Artificial neural networks (ICANN 2006)/engineering of intelligent systems (ICEIS 2006)
– reference: Sabo D, Yu XH (2008) A new pruning algorithm for neural network dimension analysis. In: 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence), pp 3313–3318
– reference: HanZWeiBZhengYYinYLiKLiSBreast cancer multi-classification from histopathological images with structured deep learning modelSci Rep2017714172
– reference: Lichman M (2013) UCI machine learning repository
– reference: MicheYSorjamaaABasPSimulaOJuttenCLendasseAOp-elm: optimally pruned extreme learning machineIEEE Trans Neural Netw2010211158162
– reference: SetionoRA penalty-function approach for pruning feedforward neural networksNeural Comput1997911852040872.68154
– reference: IslamMMYaoXMuraseKA constructive algorithm for training cooperative neural network ensemblesIEEE Trans Neural Netw2003144820834
– reference: HanHQiaoJA self-organizing fuzzy neural network based on a growing-and-pruning algorithmIEEE Trans Fuzzy Syst201018611291143
– reference: AugastaMGKathirvalavakumarTPruning algorithms of neural networks—a comparative studyCent Eur J Comput Sci201333105115
– reference: FarisHAljarahIMirjaliliSTraining feedforward neural networks using multi-verse optimizer for binary classification problemsAppl Intell2016452322332
– reference: Qiao J, Zhang Y, Han H (2008) Fast unit pruning algorithm for feedforward neural network design. Appl Math Comput 205(2):622 – 627. Special issue on advanced intelligent computing theory and methodology in applied mathematics and computation
– reference: MahmudMKaiserMHussainAVassanelliSApplications of deep learning and reinforcement learning to biological dataIEEE Trans Neural Netw Learn Syst201829206320793811399
– reference: KooiTLitjensGvan GinnekenBGubern-MéridaASánchezCIMannRden HeetenAKarssemeijerNLarge scale deep learning for computer aided detection of mammographic lesionsMed Image Anal201735303312
– reference: FnaiechNFnaiechFJervisBCherietMThe combined statistical stepwise and iterative neural network pruning algorithmIntell Autom Soft Comput2009154573589
– reference: Zeraatkar E, Soltani M, Karimaghaee P (2011) A fast convergence algorithm for bpnn based on optimal control theory based learning rate. In: The 2nd international conference on control, instrumentation and automation, pp 292–297
– reference: HagiwaraMA simple and effective method for removal of hidden units and weights. Backpropagation, part IVNeurocomputing199462207218
– reference: ZemouriRZerhouniNAutonomous and adaptive procedure for cumulative failure predictionNeural Comput Appl2012212319331
– reference: Hassibi B, Stork DG, Wolff GJ (1993) Optimal brain surgeon and general network pruning. In: IEEE international conference on neural networks, vol 1, pp 293–299
– reference: DhungelNCarneiroGBradleyAPA deep learning approach for the analysis of masses in mammograms with minimal user interventionMed Image Anal201737114128
– reference: Sun W, Tseng TLB, Zhang J, Qian W (2017) Enhancing deep convolutional neural network scheme for breast cancer diagnosis with unlabeled data. Comput Med Imaging Graph 57, 4–9. Recent developments in machine learning for medical imaging applications
– reference: Zeiler MD (2012) Adadelta: an adaptive learning rate method. abs/1212.5701
– reference: Slowik A, Bialko M (2008) Training of artificial neural networks using differential evolution algorithm. In: 2008 conference on human system interactions, pp 60–65
– reference: YuHYangXZhengSSunCActive learning from imbalanced data: a solution of online weighted extreme learning machineIEEE Trans Neural Netw Learn Syst201899116
– reference: IslamMMSattarMAAminMFYaoXMuraseKA new constructive algorithm for architectural and functional adaptation of artificial neural networksIEEE Trans Syst Man Cybern Part B (Cybern)200939615901605
– reference: LeCunYBengioYHintonGDeep learningNature20155217553436444
– reference: YaoXA review of evolutionary artificial neural networksInt J Intell Syst199384539567
– reference: SahaMChakrabortyCRacoceanuDEfficient deep learning model for mitosis detection using breast histopathology imagesComput Med Imaging Graph2018642940
– reference: FrancoLJerezJMConstructive neural networks2009Berlin, HeidelbergSpringer
– reference: HeHGarciaEALearning from imbalanced dataIEEE Trans Knowl Data Eng200921912631284
– reference: TomèDMontiFBaroffioLBondiLTagliasacchiMTubaroSDeep convolutional neural networks for pedestrian detectionSignal Process Image Commun201647482489
– reference: Fnaiech N, Abid S, Fnaiech F, Cheriet M (2004) A modified version of a formal pruning algorithm based on local relative variance analysis. In: First international symposium on control, communications and signal processing 2004, pp 849–852
– reference: ChenCLPLiuZBroad learning system: an effective and efficient incremental learning system without the need for deep architectureIEEE Trans Neural Netw Learn Syst201829110243746789
– reference: SridharSSPonnavaikkoMA novel constructive neural network architecture based on improved adaptive learning strategy for pattern classification2012BerlinSpringer423433
– reference: HanHGZhangSQiaoJFAn adaptive growing and pruning algorithm for designing recurrent neural networkNeurocomputing20172425162
– reference: AugastaMGKathirvalavakumarTA novel pruning algorithm for optimizing feedforward neural network of classification problemsNeural Process Lett2011343241
– reference: EngelbrechtAPA new pruning heuristic based on variance analysis of sensitivity informationIEEE Trans Neural Netw200112613861399
– reference: LauretPFockEMaraTAA node pruning algorithm based on a Fourier amplitude sensitivity test methodIEEE Trans Neural Netw2006172273293
– reference: SchmidhuberJDeep learning in neural networks: an overviewNeural Netw20156185117
– reference: YangXSDebSCuckoo search: recent advances and applicationsNeural Comput Appl2014241169174
– reference: HuangSCHuangYFBounds on the number of hidden neurons in multilayer perceptronsIEEE Trans Neural Netw1991214755
– reference: ChandraBSharmaRKDeep learning with adaptive learning rate using Laplacian scoreExpert Syst Appl20166317
– reference: Hosseini-AslEZuradaJMNasraouiODeep learning of part-based representation of data using sparse autoencoders with nonnegativity constraintsIEEE Trans Neural Netw Learn Syst2016271224862498
– reference: HuangGBSaratchandranPSundararajanNAn efficient sequential learning algorithm for growing and pruning rbf (gap-rbf) networksIEEE Trans Syst Man Cybern Part B (Cybern)200434622842292
– reference: ZhangRLanYHuangGBXuZBUniversal approximation of extreme learning machine with adaptive growth of hidden nodesIEEE Trans Neural Netw Learn Syst2012232365371
– reference: XuJHoDWA new training and pruning algorithm based on node dependence and Jacobian rank deficiencyNeurocomputing2006701544558
– reference: SahaMChakrabortyCArunIAhmedRChatterjeeSAn advanced deep learning approach for ki-67 stained hotspot detection and proliferation rate scoring for prognostic evaluation of breast cancerSci Rep2017713213
– reference: NayakJNaikBBeheraHA novel nature inspired firefly algorithm with higher order neural network: performance analysisInt J Eng Sci Technol2016191197211
– reference: WanWMabuSShimadaKHirasawaKHuJEnhancing the generalization ability of neural networks through controlling the hidden layersAppl Soft Comput200991404414
– reference: QiaoJLiFHanHLiWConstructive algorithm for fully connected cascade feedforward neural networksNeurocomputing2016182154164
– reference: JiaFLeiYLinJZhouXLuNDeep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive dataMech Syst Signal Process201672–73303315
– reference: Ai F (2011) A new pruning algorithm for feedforward neural networks. In: The fourth international workshop on advanced computational intelligence, pp 286–289
– reference: LeCunYDenkerJSSollaSATouretzkyDSOptimal brain damageAdvances in neural information processing systems 21990BurlingtonMorgan-Kaufmann598605
– reference: Rifai S, Vincent P, Muller X, Glorot X, Bengio Y (2011) Contractive auto-en- coders: explicit invariance during feature extraction. In: Proceedings of the 28th international conference on machine learning (ICML-11), pp 833–840
– reference: Zemouri R, Omri N, Devalland C, Arnould L, Morello B, Zerhouni N, Fnaiech F (2018) Breast cancer diagnosis based on joint variable selection and constructive deep neural network. In: 4th IEEE middle east conference on biomedical engineering (MECBME 2018)
– reference: Puma-Villanueva WJ, dos Santos EP, Zuben FJV (2012) A constructive algorithm to synthesize arbitrarily connected feedforward neural networks. Neurocomputing 75(1), 14–32. Brazilian symposium on neural networks (SBRN 2010) international conference on hybrid artificial intelligence systems (HAIS 2010)
– reference: Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Gordon GJ, Dunson DB (eds) Proceedings of the fourteenth international conference on artificial intelligence and statistics (AISTATS-11), vol 15, Journal of machine learning research—workshop and conference proceedings, pp 315–323
– reference: SubiratsJLFrancoLJerezJMC-mantec: a novel constructive neural network algorithm incorporating competition between neuronsNeural Netw201226130140
– reference: WuXRóżyckiPWilamowskiBMA hybrid constructive algorithm for single-layer feedforward networks learningIEEE Trans Neural Netw Learn Syst2015268165916683454963
– reference: DuffnerSGarciaCAn online backpropagation algorithm with validation error-based adaptive learning rate2007BerlinSpringer249258
– reference: Parekh RG, Yang J, Honavar V (1997) Constructive neural network learning algorithms for multi-category real-valued pattern classification. Technical report. ISU-CS- TR97-06 146. Department of Computer Science, Iowa State Univ
– reference: ShresthaSBSongQRobust learning in spikepropNeural Netw20178654681428.68254
– reference: CireşanDCGiustiAGambardellaLMSchmidhuberJMitosis detection in breast cancer histology images with deep neural networks2013BerlinSpringer411418
– reference: Spanhol FA, Oliveira LS, Petitjean C, Heutte L (2016) Breast cancer histopathological image classification using convolutional neural networks. In: 2016 international joint conference on neural networks (IJCNN), pp 2560–2567
– reference: Zeng X, Yeung DS (2006) Hidden neuron pruning of multilayer perceptrons using a quantified sensitivity measure. Neurocomputing 69(7):825–837 (2006). New issues in neurocomputing: 13th European symposium on artificial neural networks
– reference: Pérez-SánchezBFontenla-RomeroOGuijarro-BerdiñasBA review of adaptive online learning for artificial neural networksArtif Intell Rev201649281299
– reference: Jacek C, Zarzycki H (2003) Application of rough sets in the presumptive diagnosis of urinary system diseases. In: Artificial intelligence and security in computing systems, ACS’2002 9th international conference proceedings. Kluwer Academic Publishers, pp 41–51
– reference: PonnapalliPVSHoKCThomsonMA formal selection and pruning algorithm for feedforward artificial neural network optimizationIEEE Trans Neural Netw1999104964968
– reference: IslamMMSattarMAAminMFYaoXMuraseKA new adaptive merging and growing algorithm for designing artificial neural networksIEEE Trans Syst Man Cybern Part B (Cybern)2009393705722
– reference: HanHGQiaoJFA structure optimisation algorithm for feedforward neural network constructionNeurocomputing201399347357
– reference: Choi B, Lee JH, Kim DH (2008) Solving local minima problem with large number of hidden nodes on two-layered feed-forward artificial neural networks. Neurocomputing 71(16), 3640–3643 (2008). Advances in Neural Information Processing (ICONIP 2006)/Brazilian Symposium on Neural Networks (SBRN 2006)
– reference: BengioYCourvilleAVincentPRepresentation learning: a review and new perspectivesIEEE Trans Pattern Anal Mach Intell201335817981828
– reference: Mendes R, Cortez P, Rocha M, Neves J (2002) Particle swarms for feedforward neural network training. In: Proceedings of the 2002 international joint conference on neural networks, 2002. IJCNN ’02, vol 2, pp 1895–1899
– reference: XingHJHuBGTwo-phase construction of multilayer perceptrons using information theoryIEEE Trans Neural Netw2009204715721
– reference: Huynh TQ, Setiono R (2005) Effective neural network pruning using cross-validation. In: Proceedings of the 2005 IEEE international joint conference on neural networks, 2005, vol 2, pp 972–977
– reference: ReedRPruning algorithms—a surveyIEEE Trans Neural Netw199345740747
– reference: VincentPLarochelleHLajoieIBengioYManzagolPAStacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterionJ Mach Learn Res2010113371340827561881242.68256
– reference: CastellanoGFanelliAMPelilloMAn iterative pruning algorithm for feedforward neural networksIEEE Trans Neural Netw199783519531
– reference: WangGA perspective on deep imagingIEEE Access2016489148924
– reference: Zemouri R (2017) An evolutionary building algorithm for deep neural networks. In: 2017 12th international workshop on self-organizing maps and learning vector quantization, clustering and data visualization (WSOM), pp 1–7
– reference: van der MaatenLHintonGVisualizing data using t-sneJ Mach Learn Res2008911257926051225.68219
– reference: WolbergWHMangasarianOMultisurface method of pattern separation for medical diagnosis applied to breast cytologyProc Natl Acad Sci USA199087919391960709.92537
– reference: ShresthaSBSongQAdaptive learning rate of spikeprop based on weight convergence analysisNeural Netw2015631851981325.68197
– reference: GreenspanHvan GinnekenBSummersRMGuest editorial deep learning in medical imaging: overview and future promise of an exciting new techniqueIEEE Trans Med Imaging201635511531159
– reference: ZhangRXuZBHuangGBWangDGlobal convergence of online bp training with dynamic learning rateIEEE Trans Neural Netw Learn Syst2012232330341
– reference: Goodfellow IJ, Warde-farley D, Mirza M, Courville A, Bengio Y (2013) Maxout networks. In: In ICML
– reference: Fnaiech N, Fnaiech F, Jervis BW (2011) Feedforward neural networks pruning algorithms, industrial electronics handbook, 2nd edn., vol 5, j.d. irwin, chap. 15, pp 15–1 to 15–15
– reference: ParekhRYangJHonavarVConstructive neural-network learning algorithms for pattern classificationIEEE Trans Neural Netw2000112436451
– reference: AlbarqouniSBaurCAchillesFBelagiannisVDemirciSNavabNAggnet: deep learning from crowds for mitosis detection in breast cancer histology imagesIEEE Trans Med Imaging201635513131321
– reference: WahabNKhanALeeYSTwo-phase deep convolutional neural network for reducing class skewness in histopathological images based breast cancer detectionComput Biol Med2017858697
– reference: BeheraLKumarSPatnaikAOn adaptive learning rate that guarantees convergence in feedforward networksIEEE Trans Neural Netw200617511161125
– reference: XuJLuoXWangGGilmoreHMadabhushiAA deep convolutional neural network for segmenting and classifying epithelial and stromal regions in histopathological imagesNeurocomputing2016191214223
– reference: Nielsen AB, Hansen LK (2008) Structure learning by pruning in independent component analysis. Neurocomputing 71(10):2281–2290. Neurocomputing for vision research advances in blind signal processing
– ident: 4196_CR93
  doi: 10.1109/MECBME.2018.8402426
– volume: 35
  start-page: 1798
  issue: 8
  year: 2013
  ident: 4196_CR6
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2013.50
– volume: 4
  start-page: 740
  issue: 5
  year: 1993
  ident: 4196_CR62
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.248452
– volume: 35
  start-page: 1153
  issue: 5
  year: 2016
  ident: 4196_CR22
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2016.2553401
– volume: 23
  start-page: 365
  issue: 2
  year: 2012
  ident: 4196_CR97
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2011.2178124
– ident: 4196_CR99
  doi: 10.1109/ICICIP.2010.5564272
– volume: 8
  start-page: 539
  issue: 4
  year: 1993
  ident: 4196_CR89
  publication-title: Int J Intell Syst
  doi: 10.1002/int.4550080406
– volume: 21
  start-page: 319
  issue: 2
  year: 2012
  ident: 4196_CR94
  publication-title: Neural Comput Appl
  doi: 10.1007/s00521-011-0585-7
– start-page: 598
  volume-title: Advances in neural information processing systems 2
  year: 1990
  ident: 4196_CR45
– volume: 29
  start-page: 2063
  year: 2018
  ident: 4196_CR48
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2018.2790388
– volume: 9
  start-page: 404
  issue: 1
  year: 2009
  ident: 4196_CR81
  publication-title: Appl Soft Comput
  doi: 10.1016/j.asoc.2008.01.013
– ident: 4196_CR61
  doi: 10.1016/j.amc.2008.05.049
– ident: 4196_CR92
  doi: 10.1109/WSOM.2017.8020002
– ident: 4196_CR16
  doi: 10.1109/ISCCSP.2004.1296579
– volume: 8
  start-page: 630
  issue: 3
  year: 1997
  ident: 4196_CR40
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.572102
– volume: 34
  start-page: 241
  issue: 3
  year: 2011
  ident: 4196_CR3
  publication-title: Neural Process Lett
  doi: 10.1007/s11063-011-9196-7
– ident: 4196_CR95
  doi: 10.1016/j.neucom.2005.04.010
– ident: 4196_CR21
– volume: 85
  start-page: 86
  year: 2017
  ident: 4196_CR80
  publication-title: Comput Biol Med
  doi: 10.1016/j.compbiomed.2017.04.012
– volume: 63
  start-page: 1
  year: 2016
  ident: 4196_CR8
  publication-title: Expert Syst Appl
  doi: 10.1016/j.eswa.2016.05.022
– volume: 18
  start-page: 1129
  issue: 6
  year: 2010
  ident: 4196_CR24
  publication-title: IEEE Trans Fuzzy Syst
  doi: 10.1109/TFUZZ.2010.2070841
– volume: 19
  start-page: 197
  issue: 1
  year: 2016
  ident: 4196_CR53
  publication-title: Int J Eng Sci Technol
– volume: 9
  start-page: 185
  issue: 1
  year: 1997
  ident: 4196_CR68
  publication-title: Neural Comput
  doi: 10.1162/neco.1997.9.1.185
– volume: 17
  start-page: 1116
  issue: 5
  year: 2006
  ident: 4196_CR5
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/TNN.2006.878121
– volume: 26
  start-page: 1659
  issue: 8
  year: 2015
  ident: 4196_CR84
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2014.2350957
– volume: 49
  start-page: 281
  year: 2016
  ident: 4196_CR57
  publication-title: Artif Intell Rev
  doi: 10.1007/s10462-016-9526-2
– ident: 4196_CR20
– ident: 4196_CR64
  doi: 10.1109/IJCNN.2008.4634268
– volume: 63
  start-page: 185
  year: 2015
  ident: 4196_CR69
  publication-title: Neural Netw
  doi: 10.1016/j.neunet.2014.12.001
– volume: 24
  start-page: 169
  issue: 1
  year: 2014
  ident: 4196_CR88
  publication-title: Neural Comput Appl
  doi: 10.1007/s00521-013-1367-1
– volume: 20
  start-page: 715
  issue: 4
  year: 2009
  ident: 4196_CR85
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/TNN.2008.2005604
– ident: 4196_CR91
– ident: 4196_CR37
– ident: 4196_CR76
  doi: 10.1016/j.compmedimag.2016.07.004
– ident: 4196_CR18
– volume: 6
  start-page: 207
  issue: 2
  year: 1994
  ident: 4196_CR23
  publication-title: Neurocomputing
  doi: 10.1016/0925-2312(94)90055-8
– volume: 12
  start-page: 1386
  issue: 6
  year: 2001
  ident: 4196_CR14
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.963775
– volume: 61
  start-page: 85
  year: 2015
  ident: 4196_CR67
  publication-title: Neural Netw
  doi: 10.1016/j.neunet.2014.09.003
– volume: 35
  start-page: 303
  year: 2017
  ident: 4196_CR39
  publication-title: Med Image Anal
  doi: 10.1016/j.media.2016.07.007
– volume: 45
  start-page: 322
  issue: 2
  year: 2016
  ident: 4196_CR15
  publication-title: Appl Intell
  doi: 10.1007/s10489-016-0767-1
– ident: 4196_CR63
– volume: 242
  start-page: 51
  year: 2017
  ident: 4196_CR26
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2017.02.038
– volume-title: Constructive neural networks
  year: 2009
  ident: 4196_CR19
– ident: 4196_CR46
– volume: 99
  start-page: 347
  year: 2013
  ident: 4196_CR25
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2012.07.023
– volume: 26
  start-page: 130
  year: 2012
  ident: 4196_CR75
  publication-title: Neural Netw
  doi: 10.1016/j.neunet.2011.10.003
– ident: 4196_CR28
  doi: 10.1109/ICNN.1993.298572
– ident: 4196_CR72
  doi: 10.1109/HSI.2008.4581409
– volume: 39
  start-page: 1590
  issue: 6
  year: 2009
  ident: 4196_CR35
  publication-title: IEEE Trans Syst Man Cybern Part B (Cybern)
  doi: 10.1109/TSMCB.2009.2021849
– volume: 10
  start-page: 964
  issue: 4
  year: 1999
  ident: 4196_CR58
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.774273
– volume: 70
  start-page: 544
  issue: 1
  year: 2006
  ident: 4196_CR86
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2005.11.005
– volume: 86
  start-page: 54
  year: 2017
  ident: 4196_CR70
  publication-title: Neural Netw
  doi: 10.1016/j.neunet.2016.10.011
– volume: 191
  start-page: 214
  year: 2016
  ident: 4196_CR87
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.01.034
– ident: 4196_CR10
  doi: 10.1016/j.neucom.2008.04.004
– ident: 4196_CR1
  doi: 10.1109/IWACI.2011.6160018
– volume: 64
  start-page: 29
  year: 2018
  ident: 4196_CR66
  publication-title: Comput Med Imaging Graph
  doi: 10.1016/j.compmedimag.2017.12.001
– ident: 4196_CR59
  doi: 10.1016/j.neucom.2011.05.025
– volume: 14
  start-page: 820
  issue: 4
  year: 2003
  ident: 4196_CR36
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/TNN.2003.813832
– ident: 4196_CR77
  doi: 10.1109/IJCNN.2003.1223407
– volume: 11
  start-page: 3371
  year: 2010
  ident: 4196_CR79
  publication-title: J Mach Learn Res
– volume: 21
  start-page: 158
  issue: 1
  year: 2010
  ident: 4196_CR50
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/TNN.2009.2036259
– start-page: 423
  volume-title: A novel constructive neural network architecture based on improved adaptive learning strategy for pattern classification
  year: 2012
  ident: 4196_CR74
– ident: 4196_CR51
– ident: 4196_CR96
  doi: 10.1109/ICCIAutom.2011.6356672
– volume: 27
  start-page: 2486
  issue: 12
  year: 2016
  ident: 4196_CR30
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2015.2479223
– volume: 8
  start-page: 519
  issue: 3
  year: 1997
  ident: 4196_CR7
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.572092
– ident: 4196_CR73
  doi: 10.1109/IJCNN.2016.7727519
– volume: 87
  start-page: 9193
  year: 1990
  ident: 4196_CR83
  publication-title: Proc Natl Acad Sci USA
  doi: 10.1073/pnas.87.23.9193
– volume: 29
  start-page: 10
  issue: 1
  year: 2018
  ident: 4196_CR9
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2017.2716952
– volume: 4
  start-page: 8914
  year: 2016
  ident: 4196_CR82
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2016.2624938
– volume: 23
  start-page: 330
  issue: 2
  year: 2012
  ident: 4196_CR98
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2011.2178315
– volume: 99
  start-page: 1
  year: 2018
  ident: 4196_CR90
  publication-title: IEEE Trans Neural Netw Learn Syst
– ident: 4196_CR56
– volume: 37
  start-page: 114
  year: 2017
  ident: 4196_CR12
  publication-title: Med Image Anal
  doi: 10.1016/j.media.2017.01.009
– volume: 21
  start-page: 1263
  issue: 9
  year: 2009
  ident: 4196_CR29
  publication-title: IEEE Trans Knowl Data Eng
  doi: 10.1109/TKDE.2008.239
– volume: 35
  start-page: 1313
  issue: 5
  year: 2016
  ident: 4196_CR2
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2016.2528120
– volume: 34
  start-page: 2284
  issue: 6
  year: 2004
  ident: 4196_CR31
  publication-title: IEEE Trans Syst Man Cybern Part B (Cybern)
  doi: 10.1109/TSMCB.2004.834428
– ident: 4196_CR49
  doi: 10.1109/IJCNN.2002.1007808
– volume: 182
  start-page: 154
  year: 2016
  ident: 4196_CR60
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.12.003
– volume: 521
  start-page: 436
  issue: 7553
  year: 2015
  ident: 4196_CR44
  publication-title: Nature
  doi: 10.1038/nature14539
– volume: 2
  start-page: 47
  issue: 1
  year: 1991
  ident: 4196_CR32
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.80290
– volume: 8
  start-page: 1131
  issue: 5
  year: 1997
  ident: 4196_CR41
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.623214
– ident: 4196_CR54
  doi: 10.1016/j.neucom.2007.09.016
– volume: 72–73
  start-page: 303
  year: 2016
  ident: 4196_CR38
  publication-title: Mech Syst Signal Process
  doi: 10.1016/j.ymssp.2015.10.025
– start-page: 249
  volume-title: An online backpropagation algorithm with validation error-based adaptive learning rate
  year: 2007
  ident: 4196_CR13
– volume: 7
  start-page: 3213
  issue: 1
  year: 2017
  ident: 4196_CR65
  publication-title: Sci Rep
  doi: 10.1038/s41598-017-03405-5
– start-page: 411
  volume-title: Mitosis detection in breast cancer histology images with deep neural networks
  year: 2013
  ident: 4196_CR11
– volume: 17
  start-page: 273
  issue: 2
  year: 2006
  ident: 4196_CR43
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/TNN.2006.871707
– volume: 11
  start-page: 436
  issue: 2
  year: 2000
  ident: 4196_CR55
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.839013
– ident: 4196_CR52
  doi: 10.1016/j.neucom.2007.08.026
– volume: 15
  start-page: 573
  issue: 4
  year: 2009
  ident: 4196_CR17
  publication-title: Intell Autom Soft Comput
– volume: 9
  start-page: 2579
  issue: 11
  year: 2008
  ident: 4196_CR47
  publication-title: J Mach Learn Res
– volume: 39
  start-page: 705
  issue: 3
  year: 2009
  ident: 4196_CR34
  publication-title: IEEE Trans Syst Man Cybern Part B (Cybern)
  doi: 10.1109/TSMCB.2008.2008724
– ident: 4196_CR71
  doi: 10.1109/ICNN.1988.23864
– ident: 4196_CR42
  doi: 10.1016/j.neucom.2010.05.022
– ident: 4196_CR33
– volume: 3
  start-page: 105
  issue: 3
  year: 2013
  ident: 4196_CR4
  publication-title: Cent Eur J Comput Sci
– volume: 7
  start-page: 4172
  issue: 1
  year: 2017
  ident: 4196_CR27
  publication-title: Sci Rep
  doi: 10.1038/s41598-017-04075-z
– volume: 47
  start-page: 482
  year: 2016
  ident: 4196_CR78
  publication-title: Signal Process Image Commun
  doi: 10.1016/j.image.2016.05.007
SSID ssj0004685
Score 2.416892
Snippet During the last decade, a significant research progress has been drawn in both the theoretical aspects and the applications of Deep Learning Neural Networks....
SourceID hal
proquest
crossref
springer
SourceType Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 18143
SubjectTerms Algorithms
Artificial Intelligence
Artificial neural networks
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer architecture
Computer Science
Data Mining and Knowledge Discovery
Datasets
Deep learning
Image Processing and Computer Vision
Machine Learning
Neural networks
Optimization
Probability and Statistics in Computer Science
Wsom 2017
SummonAdditionalLinks – databaseName: SpringerLINK Contemporary 1997-Present
  dbid: RSV
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3PS8MwFA46PXhx_sTplCAeFC0sTdq0x6HOHUYZqGO3kqbpNpjd6H78_b5kbZ2igl6bNA0vSfN9yXvfQ-iKuMpThAnLs_0ECIqILc-F9WgTgAMytoVv8pD1OjwIvH7f7-ZBYbPC2724kjR_6jLYTZ9gauqrD_Nh3ljeJtpytNqM5ujPvbVoSJOIE3iL9ulhNA-V-b6NT9vR5lA7Q64hzS-Xo2bPaVX_19s9tJtjTNxcTYp9tKHSA1Qt8jfgfDkfolYTA6jGA2Di0DSeZgt9SIJjpaY4zyYxwFrwEhpLV-7iWIwHk2w0H77h66eu9dAJgpsj9Np6fLlvW3leBUsCm5pbXElux24kaZxQ5ouG4yhhC8F8V0vnyMRPfMIcn8Yxo5GrpJNEDlEAlqTLZSToMaqkk1SdIBxFQlKViFhRzlzFPUEpl5wIbkvuJaSGSGHeUOai4zr3xTgs5ZKNoUIwVGgMFXo1dFu-M11Jbvxa-xJGrayo1bLbzU6onwH8cAFdNpbQjXoxqGG-RmehzbQUJOMciu-KQfwo_vmTp3-rfoZ2bE3SjQ9MHVXm2UKdo225nI9m2YWZu--HD-TS
  priority: 102
  providerName: Springer Nature
Title A new growing pruning deep learning neural network algorithm (GP-DLNN)
URI https://link.springer.com/article/10.1007/s00521-019-04196-8
https://www.proquest.com/docview/2473364771
https://hal.science/hal-02462260
Volume 32
WOSCitedRecordID wos000595603200023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1433-3058
  dateEnd: 20241214
  omitProxy: false
  ssIdentifier: ssj0004685
  issn: 0941-0643
  databaseCode: P5Z
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1433-3058
  dateEnd: 20241214
  omitProxy: false
  ssIdentifier: ssj0004685
  issn: 0941-0643
  databaseCode: BENPR
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 1433-3058
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004685
  issn: 0941-0643
  databaseCode: RSV
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NT9wwEB2VjwMXaAuIBYosxKEVRODYiZNTtW3ZclhFKwoIcYkc21mQYFl2F34_M15ngUrl0ksOieNYGX-8GY_fA9jjqcsclzrK4rxGB0XbKEtxPMYc4YCxsc69DtlFVxVFdnmZ90LAbRzSKps50U_U9t5QjPwwlkTcJ5Xi34cPEalG0e5qkNCYgwViSSDphl5y9epcpJfkRA-GsnukCIdm_NE5ioeSI01bA9gLo-zNwjR3TWmRrzDnX9ukfvXprPxvuz_CcsCdrD3tKJ_ggxt8hpVG04GFIb4KnTZDoM366J1jQ9hw9EiBE2adG7KgMNFnRIKJlQ2mKeRM3_bxi5PrO_b1dy_61S2Kb2tw3jk--3kSBa2FyKCHNYmUMyq2aWWErYXM9VGSOB1rLfOU6HRMndc5l0kurJWiSp1J6irhDgGUSZWptFiH-cH9wG0AqypthKu1dULJ1KlMC6GM4lrFRmU1bwFvfnRpAhE56WHcljMKZW-cEo1TeuOUWQv2Z-8MpzQc75beRfvNChKD9km7W9I9hCQpIs6jJ2zGdmOwMozbcflirRYcNCZ_efzvT26-X9sWLMXkqPs8mG2Yn4we3RdYNE-Tm_FoBxZ-HBe90x3fe_F6-ufiGW-r8Z8
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3db9MwED9tHRJ72fgUZQMsBBIIIuaP2MkDQoWtdFqIKjTQ3oxjO92k0XZtt2n_FH8j5zTpBhJ72wOviePE8c_nu_Pd_QBeUOkTT4WJEpaWaKAYFyUS1yOjqA5Yx0xa8ZB9z1SeJwcHaX8JfjW5MCGsspGJlaB2Ixt85O-YCIX7hFL0w_gkCqxR4XS1odCYw2LPX5yjyTZ9v7uN8_uSse7O_qdeVLMKRBZtiVmkvFXMycJyV3KRmq049oYZI1IZCsfYMi1TKuKUOyd4Ib2NyyKmHlUFK5UtDMd-l2FFcCHjFqx83Mn7X69kYlYkoGgzhXgiwes0nSpZL3hgg-keDiMQ91Hyx1a4fBgCMa9ouX8dzFb7XXf9f_tTd2Ct1qxJZ74U7sKSH96D9Ya1gtRC7D50OwRNCTKYjM5x4GQ8OQ2uIeK8H5OaQ2NAQplP7Gw4D5In5niAI5wd_iSvPvej7SzPXz-AbzcymofQGo6G_hGQojCW-9I4z5WQXiWGc2UVNYpZlZS0DbSZWG3rUuuB8eNYL4pEV2DQCAZdgUEnbXizeGY8LzRybevniJdFw1AjvNfJdLiGSpdEnXrrDD9jswGIriXTVF-iow1vG4hd3v73Kx9f39szuN3b_5LpbDff24BVFtwSVdTPJrRmk1P_BG7Zs9nRdPK0XjMEftw0-H4Dig5Odg
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFA7eEF-8i_MaxAdFy2yTNu3jUKfiKMPL2FtIk3QOZldmt9_vSdfOKSqIr02ahJOEfF9yzncQOrY97WubCst3ghgIilCW78F-dGyAA1I5IsjzkLUaLAz9djtoTkXx597u5ZPkOKbBqDQlWTVVcXUS-GZuMw0NNhf7sIYsfxbNU2Ayxqnr4bE1FRmZJ-UEDmP8eygpwma-b-PT0TT7Yhwjp1Dnl4fS_Pypr_x_5KtoucCeuDZeLGtoRifraKXM64CLbb6B6jUMYBt3gKFDNzgdDM3lCVZap7jIMtHBRggTGkvGbuRY9Dr9QTd7ecUnN03rqhGGp5vouX79dHlrFfkWLAksK7OYlsxRXiSJigkNxIXrauEIQQPPSOrIOIgDm7oBUYqSyNPSjSPX1gCipMdkJMgWmkv6id5GOIqEJDoWShNGPc18QQiTzBbMkcyP7QqyS1NzWYiRm5wYPT6RUc4NxcFQPDcU9yvobPJPOpbi-LX2EczgpKJR0b6tNbj5BrDEA9R5MYJh7JUTzIu9-8YdaiQiKWNQfF5O6Efxz13u_K36IVpsXtV54y6830VLjuHxuZvMHprLBkO9jxbkKOu-DQ7yJf0Ow6_wmg
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=A+new+growing+pruning+deep+learning+neural+network+algorithm+%28GP-DLNN%29&rft.jtitle=Neural+computing+%26+applications&rft.au=Zemouri+Ryad&rft.au=Omri+Nabil&rft.au=Farhat%2C+Fnaiech&rft.au=Zerhouni+Noureddine&rft.date=2020-12-01&rft.pub=Springer+Nature+B.V&rft.issn=0941-0643&rft.eissn=1433-3058&rft.volume=32&rft.issue=24&rft.spage=18143&rft.epage=18159&rft_id=info:doi/10.1007%2Fs00521-019-04196-8
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0941-0643&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0941-0643&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0941-0643&client=summon