A survey of randomized algorithms for training neural networks

As a powerful tool for data regression and classification, neural networks have received considerable attention from researchers in fields such as machine learning, statistics, computer vision and so on. There exists a large body of research work on network training, among which most of them tune th...

Full description

Saved in:
Bibliographic Details
Published in:Information sciences Vol. 364-365; pp. 146 - 155
Main Authors: Zhang, Le, Suganthan, P.N.
Format: Journal Article
Language:English
Published: Elsevier Inc 10.10.2016
Subjects:
ISSN:0020-0255, 1872-6291
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract As a powerful tool for data regression and classification, neural networks have received considerable attention from researchers in fields such as machine learning, statistics, computer vision and so on. There exists a large body of research work on network training, among which most of them tune the parameters iteratively. Such methods often suffer from local minima and slow convergence. It has been shown that randomization based training methods can significantly boost the performance or efficiency of neural networks. Among these methods, most approaches use randomization either to change the data distributions, and/or to fix a part of the parameters or network configurations. This article presents a comprehensive survey of the earliest work and recent advances as well as some suggestions for future research.
AbstractList As a powerful tool for data regression and classification, neural networks have received considerable attention from researchers in fields such as machine learning, statistics, computer vision and so on. There exists a large body of research work on network training, among which most of them tune the parameters iteratively. Such methods often suffer from local minima and slow convergence. It has been shown that randomization based training methods can significantly boost the performance or efficiency of neural networks. Among these methods, most approaches use randomization either to change the data distributions, and/or to fix a part of the parameters or network configurations. This article presents a comprehensive survey of the earliest work and recent advances as well as some suggestions for future research.
As a powerful tool for data regression and classification, neural networks have received considerable attention from researchers in fields such as machine learning, statistics, computer vision and so on. There exists a large body of research work on network training, among which most of them tune the parameters iteratively. Such methods often suffer from local minima and slow convergence. It has been shown that randomization based training methods can significantly boost the performance or efficiency of neural networks. Among these methods, most approaches use randomization either to change the data distributions, and/or to fix a part of the parameters or network configurations. This article presents a comprehensive survey of the earliest work and recent advances as well as some suggestions for future research.
Author Suganthan, P.N.
Zhang, Le
Author_xml – sequence: 1
  givenname: Le
  surname: Zhang
  fullname: Zhang, Le
– sequence: 2
  givenname: P.N.
  orcidid: 0000-0003-0901-5105
  surname: Suganthan
  fullname: Suganthan, P.N.
  email: epnsugan@ntu.edu.sg
BookMark eNp9kD1PwzAQhi1UJNrCD2DLyJJwthPHERJSVfElVWKB2XKTS3FJ7GInReXXk6hMDJ3uhve50_POyMQ6i4RcU0goUHG7TYwNCRvWBGgCvDgjUypzFgtW0AmZAjCIgWXZBZmFsAWANBdiSu4XUej9Hg-RqyOvbeVa84NVpJuN86b7aENUOx91Xhtr7Cay2HvdDKP7dv4zXJLzWjcBr_7mnLw_Prwtn-PV69PLcrGKS16ILkYUEtMKSgE1gGayquuiALZOudTIMGVS5OuCZkJnomaMDwKcMVHla-Q8Z3xObo53d9599Rg61ZpQYtNoi64PispBjVEp-RDNj9HSuxA81qo0ne6Ms6NEoyiosTG1VUNjamxMAVXjwzmh_8idN632h5PM3ZHBwX5v0KtQGrQlVsZj2anKmRP0LzPUhVU
CitedBy_id crossref_primary_10_1007_s12145_024_01532_y
crossref_primary_10_1109_JAS_2021_1004284
crossref_primary_10_1002_ima_22537
crossref_primary_10_1016_j_ins_2016_09_016
crossref_primary_10_3390_app7090868
crossref_primary_10_1007_s00521_019_04290_x
crossref_primary_10_1016_j_asoc_2017_09_020
crossref_primary_10_1016_j_asoc_2018_07_013
crossref_primary_10_1155_2024_5648897
crossref_primary_10_1007_s10489_020_02006_6
crossref_primary_10_1109_TCSS_2022_3146974
crossref_primary_10_1016_j_bspc_2018_07_014
crossref_primary_10_1155_2022_5832043
crossref_primary_10_1016_j_knosys_2025_113879
crossref_primary_10_1002_ima_22400
crossref_primary_10_1007_s00500_020_05080_7
crossref_primary_10_1007_s12530_022_09429_1
crossref_primary_10_1016_j_jhydrol_2019_05_073
crossref_primary_10_1109_MCI_2017_2742867
crossref_primary_10_1016_j_ins_2017_08_051
crossref_primary_10_1016_j_neucom_2017_11_070
crossref_primary_10_1109_TSMC_2022_3158276
crossref_primary_10_1109_LGRS_2021_3132020
crossref_primary_10_3390_s17020414
crossref_primary_10_1016_j_neunet_2018_01_007
crossref_primary_10_1016_j_neunet_2019_03_013
crossref_primary_10_1016_j_ins_2019_08_059
crossref_primary_10_7717_peerj_cs_2590
crossref_primary_10_1287_ijoc_2021_1107
crossref_primary_10_1016_j_engappai_2018_12_005
crossref_primary_10_1016_j_engappai_2022_105535
crossref_primary_10_1016_j_jpdc_2017_06_001
crossref_primary_10_1007_s00521_017_3218_y
crossref_primary_10_1016_j_ins_2025_122162
crossref_primary_10_1016_j_eswa_2022_116867
crossref_primary_10_1016_j_asoc_2018_03_013
crossref_primary_10_1007_s00521_022_07824_y
crossref_primary_10_1007_s11265_023_01895_3
crossref_primary_10_1007_s13198_016_0526_z
crossref_primary_10_1016_j_engappai_2023_106237
crossref_primary_10_1038_s41598_024_66676_9
crossref_primary_10_1016_j_asoc_2022_108526
crossref_primary_10_1109_TSMC_2022_3213628
crossref_primary_10_1016_j_asoc_2017_08_007
crossref_primary_10_1016_j_asoc_2017_08_006
crossref_primary_10_3390_computation5030040
crossref_primary_10_1109_ACCESS_2020_3005247
crossref_primary_10_1016_j_swevo_2017_03_005
crossref_primary_10_1007_s12559_019_09710_7
crossref_primary_10_1016_j_energy_2018_05_146
crossref_primary_10_1016_j_jiec_2016_09_017
crossref_primary_10_1109_TFUZZ_2024_3400898
crossref_primary_10_1007_s11630_021_1497_1
crossref_primary_10_1149_1945_7111_ad69c5
crossref_primary_10_1016_j_asoc_2017_10_010
crossref_primary_10_1007_s10921_025_01179_9
crossref_primary_10_1109_TCYB_2018_2863020
crossref_primary_10_1016_j_asoc_2017_08_016
crossref_primary_10_1155_2018_6381610
crossref_primary_10_1016_j_eswa_2022_118502
crossref_primary_10_3390_s19081864
crossref_primary_10_1016_j_neucom_2020_07_127
crossref_primary_10_1007_s00521_021_06359_y
crossref_primary_10_1109_TCYB_2021_3079906
crossref_primary_10_1109_TCYB_2021_3126711
crossref_primary_10_1109_TCBB_2022_3202707
crossref_primary_10_1016_j_engappai_2022_105509
crossref_primary_10_1515_med_2020_0131
crossref_primary_10_1109_JPHOT_2018_2817843
crossref_primary_10_1016_j_saa_2022_121348
crossref_primary_10_3390_mca30040067
crossref_primary_10_1038_s41598_024_61552_y
crossref_primary_10_1155_2020_5604246
crossref_primary_10_1016_j_jhydrol_2022_129034
crossref_primary_10_1016_j_ins_2017_02_003
crossref_primary_10_1016_j_neucom_2017_10_063
crossref_primary_10_1016_j_engappai_2020_103633
crossref_primary_10_3390_genes10020087
crossref_primary_10_1109_TIM_2023_3348909
crossref_primary_10_3390_electronics10091062
crossref_primary_10_1016_j_neucom_2023_126618
crossref_primary_10_1016_j_asoc_2023_110377
crossref_primary_10_1016_j_neucom_2017_08_040
crossref_primary_10_47164_ijngc_v13i3_820
crossref_primary_10_1016_j_cnsns_2017_09_004
crossref_primary_10_1515_med_2020_0006
crossref_primary_10_1002_cpe_5945
crossref_primary_10_1007_s10723_022_09609_y
crossref_primary_10_1016_j_asoc_2019_105854
crossref_primary_10_1016_j_neucom_2018_09_012
crossref_primary_10_3390_math8050766
crossref_primary_10_1007_s12553_019_00315_6
crossref_primary_10_1016_j_engappai_2023_106676
crossref_primary_10_1371_journal_pone_0194889
crossref_primary_10_1088_1361_665X_ad67bc
crossref_primary_10_1109_TIM_2022_3216409
crossref_primary_10_3390_bdcc3040051
crossref_primary_10_1016_j_renene_2025_123878
crossref_primary_10_1016_j_compbiomed_2017_07_018
crossref_primary_10_1007_s00500_020_05390_w
crossref_primary_10_1016_j_scs_2020_102275
crossref_primary_10_1016_j_asoc_2017_08_053
crossref_primary_10_1109_ACCESS_2019_2944682
crossref_primary_10_1016_j_neunet_2025_108032
crossref_primary_10_1016_j_asoc_2017_08_055
crossref_primary_10_1049_iet_gtd_2016_2010
crossref_primary_10_3390_mca29030040
crossref_primary_10_1007_s43069_022_00179_z
crossref_primary_10_1016_j_asoc_2018_09_023
crossref_primary_10_1016_j_compag_2024_109414
crossref_primary_10_1016_j_asoc_2021_107797
crossref_primary_10_1109_TIM_2021_3132053
crossref_primary_10_3390_su10010219
crossref_primary_10_1016_j_asoc_2021_107438
crossref_primary_10_1002_ima_22484
crossref_primary_10_1080_10589759_2024_2375575
crossref_primary_10_1088_1757_899X_450_5_052007
crossref_primary_10_1007_s00521_020_04994_5
crossref_primary_10_1109_TCYB_2016_2588526
crossref_primary_10_1016_j_asoc_2024_111759
crossref_primary_10_1016_j_asoc_2017_07_027
crossref_primary_10_1007_s13042_021_01331_7
crossref_primary_10_1049_iet_ipr_2018_5371
crossref_primary_10_1515_tnsci_2019_0021
crossref_primary_10_1016_j_neucom_2019_08_058
crossref_primary_10_1007_s11063_019_10012_0
crossref_primary_10_1016_j_neunet_2019_09_039
crossref_primary_10_1016_j_neucom_2018_07_080
crossref_primary_10_1007_s11063_017_9752_x
crossref_primary_10_1109_TNNLS_2022_3190043
crossref_primary_10_1016_j_apenergy_2019_04_126
crossref_primary_10_1016_j_applthermaleng_2018_12_092
crossref_primary_10_1122_8_0000831
crossref_primary_10_1016_j_asoc_2019_105534
crossref_primary_10_1109_TNNLS_2024_3512492
crossref_primary_10_1109_JBHI_2024_3491593
crossref_primary_10_1007_s12530_021_09409_x
crossref_primary_10_1016_j_eswa_2022_119164
crossref_primary_10_1016_j_ins_2018_07_015
crossref_primary_10_1002_ima_22468
crossref_primary_10_1016_j_eswa_2022_117784
crossref_primary_10_1016_j_energy_2019_116589
crossref_primary_10_1016_j_neunet_2023_06_042
crossref_primary_10_1016_j_ins_2017_10_044
crossref_primary_10_1063_1_5136269
crossref_primary_10_1016_j_neucom_2025_131515
crossref_primary_10_1109_TPEL_2024_3494858
crossref_primary_10_1016_j_neunet_2019_01_007
crossref_primary_10_1016_j_apenergy_2022_119277
crossref_primary_10_1016_j_engappai_2022_105353
crossref_primary_10_1109_TNNLS_2018_2846646
crossref_primary_10_1016_j_nxener_2025_100256
crossref_primary_10_1007_s00500_019_04647_3
crossref_primary_10_1007_s10489_023_04765_4
crossref_primary_10_1016_j_applthermaleng_2017_11_061
crossref_primary_10_1007_s00170_019_04729_4
crossref_primary_10_1007_s00521_021_06851_5
crossref_primary_10_1109_TCDS_2018_2796940
crossref_primary_10_1016_j_neucom_2018_10_090
crossref_primary_10_1007_s13369_017_2907_2
crossref_primary_10_1016_j_asoc_2021_107239
crossref_primary_10_1016_j_neucom_2018_10_098
crossref_primary_10_1007_s40846_018_0411_0
crossref_primary_10_1016_j_compbiolchem_2021_107566
crossref_primary_10_1016_j_asoc_2017_07_061
crossref_primary_10_1109_ACCESS_2024_3515481
crossref_primary_10_3390_app7020164
crossref_primary_10_1016_j_eswa_2019_112912
crossref_primary_10_1109_TCOMM_2022_3184158
crossref_primary_10_1155_2016_9742483
crossref_primary_10_1002_widm_1200
crossref_primary_10_1108_DTA_08_2023_0437
crossref_primary_10_1016_j_eswa_2023_120279
crossref_primary_10_1016_j_ins_2019_10_069
crossref_primary_10_1016_j_neucom_2020_07_074
crossref_primary_10_7717_peerj_2684
crossref_primary_10_1109_TIM_2021_3063200
crossref_primary_10_1007_s00500_019_04499_x
crossref_primary_10_1016_j_engappai_2023_106700
crossref_primary_10_1016_j_ins_2025_121947
crossref_primary_10_3390_app11093867
crossref_primary_10_1016_j_asoc_2020_106756
crossref_primary_10_1016_j_ins_2020_11_028
crossref_primary_10_3390_sym12081272
crossref_primary_10_3390_s20164493
crossref_primary_10_1016_j_compeleceng_2024_109499
crossref_primary_10_1109_MDAT_2020_3031857
crossref_primary_10_1088_1402_4896_acf004
crossref_primary_10_1016_j_asoc_2021_107455
crossref_primary_10_1016_j_imu_2018_07_002
crossref_primary_10_3390_s20041070
crossref_primary_10_1007_s00521_021_06793_y
crossref_primary_10_1177_0734242X211017974
crossref_primary_10_1016_j_asoc_2025_113063
crossref_primary_10_1109_TII_2017_2760915
crossref_primary_10_1186_s13677_020_00167_w
crossref_primary_10_1016_j_knosys_2025_113622
crossref_primary_10_1016_j_heliyon_2024_e32572
Cites_doi 10.1109/72.125861
10.1016/0893-6080(88)90003-2
10.1016/0925-2312(95)00066-F
10.1162/089976602760407955
10.1109/5.58326
10.1016/0925-2312(94)90053-1
10.1016/j.neucom.2006.10.111
10.1142/S1469026801000238
10.1109/TNN.2010.2066286
10.1109/MSP.2007.4286571
10.1103/RevModPhys.34.123
10.1109/MCI.2015.2405352
10.1109/72.471375
10.7551/mitpress/7496.003.0016
10.1016/j.peva.2010.07.006
10.1109/5.726791
10.1016/0893-6080(91)90009-T
10.1109/72.536316
10.1109/2.144401
10.1037/h0042519
10.1109/3477.740166
10.1162/neco.1989.1.4.502
10.1162/neco.2010.08-09-1081
10.1109/TSMC.2014.2332305
10.1109/TIT.2006.885507
10.1109/34.107014
10.1016/S0893-6080(97)00089-0
10.1177/105971230601400204
10.1016/j.ins.2013.12.016
10.1126/science.1127647
10.1109/TIT.2005.858979
10.1371/journal.pcbi.1000579
10.1016/S0377-2217(99)00481-6
10.1093/comjnl/bxp032
10.1016/S0925-2312(99)00115-0
10.1016/j.neucom.2008.07.002
ContentType Journal Article
Copyright 2016 Elsevier Inc.
Copyright_xml – notice: 2016 Elsevier Inc.
DBID AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1016/j.ins.2016.01.039
DatabaseName CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Computer and Information Systems Abstracts
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Library & Information Science
Statistics
EISSN 1872-6291
EndPage 155
ExternalDocumentID 10_1016_j_ins_2016_01_039
S002002551600058X
GroupedDBID --K
--M
--Z
-~X
.DC
.~1
0R~
1B1
1RT
1~.
1~5
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
9JO
AAAKF
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARIN
AAXUO
AAYFN
ABAOU
ABBOA
ABFNM
ABJNI
ABMAC
ABUCO
ABYKQ
ACAZW
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
ADGUI
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIGVJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
APLSM
ARUGR
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HAMUX
IHE
J1W
JJJVA
KOM
LG9
LY1
M41
MHUIS
MO0
MS~
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RIG
ROL
RPZ
SDF
SDG
SDP
SES
SPC
SPCBC
SSB
SSD
SST
SSV
SSW
SSZ
T5K
TN5
TWZ
WH7
XPP
ZMT
~02
~G-
1OL
29I
77I
9DU
AAAKG
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABEFU
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
ADVLN
AEIPS
AEUPX
AFFNX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
FEDTE
FGOYB
HLZ
HVGLF
HZ~
H~9
R2-
SBC
SDS
SEW
UHS
WUQ
YYP
ZY4
~HD
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c396t-ee68e4d0c60f00a28dff9902b438ae2e42867b9156a56f2230393226d7be33723
ISICitedReferencesCount 281
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000378969400010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0020-0255
IngestDate Sun Nov 09 14:31:13 EST 2025
Sat Nov 29 06:24:59 EST 2025
Tue Nov 18 22:25:52 EST 2025
Fri Feb 23 02:33:55 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Recurrent neural networks
Randomized neural networks
Convolutional neural networks
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c396t-ee68e4d0c60f00a28dff9902b438ae2e42867b9156a56f2230393226d7be33723
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0003-0901-5105
PQID 1825521883
PQPubID 23500
PageCount 10
ParticipantIDs proquest_miscellaneous_1825521883
crossref_citationtrail_10_1016_j_ins_2016_01_039
crossref_primary_10_1016_j_ins_2016_01_039
elsevier_sciencedirect_doi_10_1016_j_ins_2016_01_039
PublicationCentury 2000
PublicationDate 2016-10-10
PublicationDateYYYYMMDD 2016-10-10
PublicationDate_xml – month: 10
  year: 2016
  text: 2016-10-10
  day: 10
PublicationDecade 2010
PublicationTitle Information sciences
PublicationYear 2016
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References Huang, Ramesh, Berg, Learned-Miller (bib0035) 2007
Fan, Xu, Wu, Gong (bib0025) 2010; 21
Moody, Darken (bib0052) 1988
Alhamdoosh, Wang (bib0002) 2014; 264
Bengio, LeCun (bib0007) 2007; 34
Chiam, Tan, Al Mamun (bib0018) 2007
Zhang (bib0079) 2014
Li, Wang, Chai (bib0046) 2015; 45
Albers (bib0001) 1996
Boese, Kahng (bib0011) 1993
Wang, Courant (bib0075) 2002
T.P. Lillicrap, D. Cownden, D.B. Tweed, C.J. Akerman, Random feedback weights support learning in deep neural networks, arXiv preprint arXiv:1411.0247(2014).
Candes, Tao (bib0013) 2005; 51
Rahimi, Recht (bib0062) 2009
Vincent, Larochelle, Lajoie, Bengio, Manzagol (bib0073) 2010; 11
Pao (bib0053) 1989
Luenberger (bib0049) 1973; 28
Jaeger (bib0039) 2002
Srivastava, Hinton, Krizhevsky, Sutskever, Salakhutdinov (bib0070) 2014; 15
Broomhead, Lowe (bib0012) 1988
Timotheou (bib0072) 2010; 53
Hu (bib0033) 2009; 72
Hu, Tseng (bib0034) 2007; 70
Principe, Chen (bib0060) 2015; 10
Block (bib0010) 1962; 34
Bakırcıoğlu, Koçak (bib0003) 2000; 126
Kennedy (bib0041) 2010
Zhang, Suganthan (bib0078) 2015
Pao, Takefuji (bib0056) 1992; 25
Barlett, Downs (bib0005) 1992; 3
Mendes, Cortez, Rocha, Neves (bib0051) 2002; 6
Coates, Ng (bib0019) 2011
Berry, Quoy (bib0009) 2006; 14
Chen, Cao, Wen, Sun (bib0017) 2013
Le Roux, Bengio (bib0042) 2010; 22
Pao, Park, Sobajic (bib0054) 1994; 6
Rahimi, Recht (bib0061) 2007
Lu, Dhillon, Foster, Ungar (bib0048) 2013
Saxe, Koh, Chen, Bhand, Suresh, Ng (bib0068) 2011
de Castro, Von Zuben (bib0021) 2001; 1
Poggio, Girosi (bib0059) 1990; 78
Jacobs (bib0038) 1988; 1
Fernández-Delgado, Cernadas, Barro, Amorim (bib0026) 2014; 15
Pao, Phillips (bib0055) 1995; 9
Pinto, Doukhan, DiCarlo, Cox (bib0057) 2009; 5
Dai, Xie, He, Liang, Raj, Balcan, Song (bib0020) 2014
Engel (bib0024) 1988; 2
Gori, Tesi (bib0029) 1992; 14
Maass, Natschläger, Markram (bib0050) 2002; 14
Hornik (bib0032) 1991; 4
Chen (bib0015) 1996; 7
Haykin, Network (bib0030) 2004; 2
Poggio, Girosi (bib0058) 1989
Li, Hastie, Church (bib0045) 2006
Wan, Zeiler, Zhang, Cun, Fergus (bib0074) 2013
LeCun, Bottou, Bengio, Haffner (bib0043) 1998; 86
Hinton, Salakhutdinov (bib0031) 2006; 313
Gelenbe (bib0027) 1989; 1
Jarrett, Kavukcuoglu, Ranzato, LeCun (bib0040) 2009
Rosenblatt (bib0066) 1961
Zeiler, Fergus (bib0077) 2013
Li, Chen, Huang (bib0044) 2010
Ren, Zhang, Suganthan (bib0064) 2015
Baraniuk (bib0004) 2007; 24
Georgiopoulos, Li, Kocak (bib0028) 2011; 68
Rosenblatt (bib0065) 1958; 65
Tang, Salakhutdinov (bib0071) 2013
Chen, Wan (bib0016) 1999; 29
Husmeier, Taylor (bib0036) 1998; 11
Deng, Dong, Socher, Li, Li, Fei-Fei (bib0022) 2009
Ren, Suganthan, Srikanth, Amaratungac (bib0063) 2015
Bergstra, Bengio (bib0008) 2012; 13
Schmidt, Kraaijveld, Duin (bib0069) 1992
Elisseeff, Paugam-Moisy (bib0023) 1999; 29
Igelnik, Pao (bib0037) 1995; 6
Yusiong, Naval Jr (bib0076) 2006
Candes, Tao (bib0014) 2006; 52
Saunders, Gammerman, Vovk (bib0067) 1998
Bartlett, Mendelson (bib0006) 2003; 3
Chiam (10.1016/j.ins.2016.01.039_bib0018) 2007
Lu (10.1016/j.ins.2016.01.039_bib0048) 2013
Zhang (10.1016/j.ins.2016.01.039_bib0079) 2014
Jaeger (10.1016/j.ins.2016.01.039_bib0039) 2002
Gori (10.1016/j.ins.2016.01.039_bib0029) 1992; 14
Principe (10.1016/j.ins.2016.01.039_bib0060) 2015; 10
Mendes (10.1016/j.ins.2016.01.039_bib0051) 2002; 6
Gelenbe (10.1016/j.ins.2016.01.039_bib0027) 1989; 1
Poggio (10.1016/j.ins.2016.01.039_bib0058) 1989
Pao (10.1016/j.ins.2016.01.039_bib0053) 1989
Saunders (10.1016/j.ins.2016.01.039_bib0067) 1998
Luenberger (10.1016/j.ins.2016.01.039_bib0049) 1973; 28
Srivastava (10.1016/j.ins.2016.01.039_bib0070) 2014; 15
Li (10.1016/j.ins.2016.01.039_bib0046) 2015; 45
Haykin (10.1016/j.ins.2016.01.039_bib0030) 2004; 2
Saxe (10.1016/j.ins.2016.01.039_bib0068) 2011
Rosenblatt (10.1016/j.ins.2016.01.039_bib0066) 1961
Engel (10.1016/j.ins.2016.01.039_bib0024) 1988; 2
Bengio (10.1016/j.ins.2016.01.039_bib0007) 2007; 34
Huang (10.1016/j.ins.2016.01.039_bib0035) 2007
Igelnik (10.1016/j.ins.2016.01.039_bib0037) 1995; 6
Bartlett (10.1016/j.ins.2016.01.039_bib0006) 2003; 3
Zhang (10.1016/j.ins.2016.01.039_bib0078) 2015
Rahimi (10.1016/j.ins.2016.01.039_bib0061) 2007
Alhamdoosh (10.1016/j.ins.2016.01.039_bib0002) 2014; 264
Pao (10.1016/j.ins.2016.01.039_bib0054) 1994; 6
10.1016/j.ins.2016.01.039_bib0047
Barlett (10.1016/j.ins.2016.01.039_bib0005) 1992; 3
Poggio (10.1016/j.ins.2016.01.039_bib0059) 1990; 78
Fan (10.1016/j.ins.2016.01.039_bib0025) 2010; 21
Maass (10.1016/j.ins.2016.01.039_bib0050) 2002; 14
Ren (10.1016/j.ins.2016.01.039_bib0063) 2015
Schmidt (10.1016/j.ins.2016.01.039_bib0069) 1992
Hu (10.1016/j.ins.2016.01.039_bib0034) 2007; 70
Moody (10.1016/j.ins.2016.01.039_bib0052) 1988
Hinton (10.1016/j.ins.2016.01.039_bib0031) 2006; 313
Georgiopoulos (10.1016/j.ins.2016.01.039_bib0028) 2011; 68
Hu (10.1016/j.ins.2016.01.039_bib0033) 2009; 72
Chen (10.1016/j.ins.2016.01.039_bib0016) 1999; 29
Pinto (10.1016/j.ins.2016.01.039_bib0057) 2009; 5
Yusiong (10.1016/j.ins.2016.01.039_bib0076) 2006
Rahimi (10.1016/j.ins.2016.01.039_bib0062) 2009
Chen (10.1016/j.ins.2016.01.039_bib0015) 1996; 7
Timotheou (10.1016/j.ins.2016.01.039_bib0072) 2010; 53
Jacobs (10.1016/j.ins.2016.01.039_bib0038) 1988; 1
Zeiler (10.1016/j.ins.2016.01.039_bib0077) 2013
Pao (10.1016/j.ins.2016.01.039_bib0056) 1992; 25
de Castro (10.1016/j.ins.2016.01.039_bib0021) 2001; 1
Vincent (10.1016/j.ins.2016.01.039_bib0073) 2010; 11
Kennedy (10.1016/j.ins.2016.01.039_bib0041) 2010
Hornik (10.1016/j.ins.2016.01.039_bib0032) 1991; 4
Ren (10.1016/j.ins.2016.01.039_bib0064) 2015
Candes (10.1016/j.ins.2016.01.039_bib0014) 2006; 52
Chen (10.1016/j.ins.2016.01.039_bib0017) 2013
LeCun (10.1016/j.ins.2016.01.039_bib0043) 1998; 86
Li (10.1016/j.ins.2016.01.039_bib0044) 2010
Rosenblatt (10.1016/j.ins.2016.01.039_bib0065) 1958; 65
Tang (10.1016/j.ins.2016.01.039_bib0071) 2013
Pao (10.1016/j.ins.2016.01.039_bib0055) 1995; 9
Baraniuk (10.1016/j.ins.2016.01.039_bib0004) 2007; 24
Broomhead (10.1016/j.ins.2016.01.039_bib0012) 1988
Dai (10.1016/j.ins.2016.01.039_bib0020) 2014
Jarrett (10.1016/j.ins.2016.01.039_bib0040) 2009
Le Roux (10.1016/j.ins.2016.01.039_bib0042) 2010; 22
Candes (10.1016/j.ins.2016.01.039_bib0013) 2005; 51
Fernández-Delgado (10.1016/j.ins.2016.01.039_bib0026) 2014; 15
Boese (10.1016/j.ins.2016.01.039_bib0011) 1993
Albers (10.1016/j.ins.2016.01.039_bib0001) 1996
Wan (10.1016/j.ins.2016.01.039_bib0074) 2013
Li (10.1016/j.ins.2016.01.039_bib0045) 2006
Berry (10.1016/j.ins.2016.01.039_bib0009) 2006; 14
Wang (10.1016/j.ins.2016.01.039_bib0075) 2002
Coates (10.1016/j.ins.2016.01.039_bib0019) 2011
Block (10.1016/j.ins.2016.01.039_bib0010) 1962; 34
Elisseeff (10.1016/j.ins.2016.01.039_bib0023) 1999; 29
Bergstra (10.1016/j.ins.2016.01.039_bib0008) 2012; 13
Bakırcıoğlu (10.1016/j.ins.2016.01.039_bib0003) 2000; 126
Deng (10.1016/j.ins.2016.01.039_bib0022) 2009
Husmeier (10.1016/j.ins.2016.01.039_bib0036) 1998; 11
References_xml – volume: 2
  start-page: 641
  year: 1988
  end-page: 648
  ident: bib0024
  article-title: Teaching feed-forward neural networks by simulated annealing
  publication-title: Complex Syst.
– start-page: 346
  year: 2007
  end-page: 360
  ident: bib0018
  article-title: Multiobjective evolutionary neural networks for time series forecasting
  publication-title: Evolutionary Multi-Criterion Optimization
– volume: 13
  start-page: 281
  year: 2012
  end-page: 305
  ident: bib0008
  article-title: Random search for hyper-parameter optimization
  publication-title: J. Mach. Learn. Res.
– start-page: 1
  year: 1992
  end-page: 4
  ident: bib0069
  article-title: Feedforward neural networks with random weights
  publication-title: Proceedings of the 11th IAPR International Conference on Pattern Recognition,
– volume: 78
  start-page: 1481
  year: 1990
  end-page: 1497
  ident: bib0059
  article-title: Networks for approximation and learning
  publication-title: Proc. IEEE
– start-page: 2528
  year: 2011
  end-page: 2536
  ident: bib0019
  article-title: Selecting receptive fields in deep networks
  publication-title: Proceedings of the Advances in Neural Information Processing Systems
– volume: 24
  year: 2007
  ident: bib0004
  article-title: Compressive sensing
  publication-title: IEEE Signal Process. Mag.
– volume: 72
  start-page: 1808
  year: 2009
  end-page: 1816
  ident: bib0033
  article-title: Functional-link nets with genetic-algorithm-based learning for robust nonlinear interval regression analysis
  publication-title: Neurocomputing
– volume: 22
  start-page: 2192
  year: 2010
  end-page: 2207
  ident: bib0042
  article-title: Deep belief networks are compact universal approximators
  publication-title: Neural Comput.
– volume: 34
  year: 2007
  ident: bib0007
  article-title: Scaling learning algorithms towards AI
  publication-title: Large-Scale Kernel Mach.
– volume: 14
  start-page: 76
  year: 1992
  end-page: 86
  ident: bib0029
  article-title: On the problem of local minima in backpropagation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 1058
  year: 2013
  end-page: 1066
  ident: bib0074
  article-title: Regularization of neural networks using dropconnect
  publication-title: Proceedings of the 30th International Conference on Machine Learning (ICML-13)
– volume: 11
  start-page: 89
  year: 1998
  end-page: 116
  ident: bib0036
  article-title: Neural networks for predicting conditional probability densities: Improved training scheme combining EM and RVFL
  publication-title: Neural Netw.
– volume: 1
  start-page: 295
  year: 1988
  end-page: 307
  ident: bib0038
  article-title: Increased rates of convergence through learning rate adaptation
  publication-title: Neural Netw.
– volume: 14
  start-page: 2531
  year: 2002
  end-page: 2560
  ident: bib0050
  article-title: Real-time computing without stable states: A new framework for neural computation based on perturbations
  publication-title: Neural Comput.
– year: 2015
  ident: bib0064
  article-title: Ensemble classification and regression – recent developments, applications and future directions
  publication-title: IEEE Comput. Intell. Mag.
– volume: 3
  start-page: 202
  year: 1992
  end-page: 210
  ident: bib0005
  article-title: Using random weights to train multilayer networks of hard-limiting units
  publication-title: IEEE Trans. Neural Netw.
– volume: 29
  start-page: 3
  year: 1999
  end-page: 24
  ident: bib0023
  article-title: JNN, a randomized algorithm for training multilayer networks in polynomial time
  publication-title: Neurocomputing
– volume: 9
  start-page: 149
  year: 1995
  end-page: 164
  ident: bib0055
  article-title: The functional link net and learning optimal control
  publication-title: Neurocomputing
– volume: 313
  start-page: 504
  year: 2006
  end-page: 507
  ident: bib0031
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
– volume: 52
  start-page: 5406
  year: 2006
  end-page: 5425
  ident: bib0014
  article-title: Near-optimal signal recovery from random projections: Universal encoding strategies?
  publication-title: IEEE Trans. Inf. Theory
– volume: 6
  start-page: 1320
  year: 1995
  end-page: 1329
  ident: bib0037
  article-title: Stochastic choice of basis functions in adaptive function approximation and the functional-link net
  publication-title: IEEE Trans. Neural Netw.
– volume: 65
  start-page: 386
  year: 1958
  ident: bib0065
  article-title: The perceptron: a probabilistic model for information storage and organization in the brain.
  publication-title: Psychol. Rev.
– volume: 86
  start-page: 2278
  year: 1998
  end-page: 2324
  ident: bib0043
  article-title: Gradient-based learning applied to document recognition
  publication-title: Proc. IEEE
– year: 2015
  ident: bib0078
  article-title: A comprehensive evaluation of random vector functional link networks
  publication-title: Inf. Sci.
– volume: 29
  start-page: 62
  year: 1999
  end-page: 72
  ident: bib0016
  article-title: A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction
  publication-title: IEEE Trans. Syst., Man, Cybern., Part B: Cybern.
– year: 1961
  ident: bib0066
  article-title: Principles of neurodynamics. perceptrons and the theory of brain mechanisms
  publication-title: Technical Report
– volume: 5
  start-page: e1000579
  year: 2009
  ident: bib0057
  article-title: A high-throughput screening approach to discovering good forms of biologically inspired visual representation
  publication-title: PLoS Comput Biol
– volume: 21
  start-page: 1610
  year: 2010
  end-page: 1623
  ident: bib0025
  article-title: Human tracking using convolutional neural networks
  publication-title: IEEE Trans. Neural Netw.
– volume: 68
  start-page: 361
  year: 2011
  end-page: 384
  ident: bib0028
  article-title: Learning in the feed-forward random neural network: A critical review
  publication-title: Perform. Eval.
– volume: 10
  start-page: 68
  year: 2015
  end-page: 77
  ident: bib0060
  article-title: Universal approximation with convex optimization: Gimmick or reality?[discussion forum]
  publication-title: IEEE Comput. Intell. Mag.
– start-page: 1089
  year: 2011
  end-page: 1096
  ident: bib0068
  article-title: On random weights and unsupervised feature learning
  publication-title: Proceedings of the 28th International Conference on Machine Learning (ICML-11)
– volume: 14
  start-page: 129
  year: 2006
  end-page: 137
  ident: bib0009
  article-title: Structure and dynamics of random recurrent neural networks
  publication-title: Adapt. Behav.
– volume: 4
  start-page: 251
  year: 1991
  end-page: 257
  ident: bib0032
  article-title: Approximation capabilities of multilayer feedforward networks
  publication-title: Neural Netw.
– start-page: 760
  year: 2010
  end-page: 766
  ident: bib0041
  article-title: Particle swarm optimization
  publication-title: Encyclopedia of Machine Learning
– volume: 126
  start-page: 319
  year: 2000
  end-page: 330
  ident: bib0003
  article-title: Survey of random neural network applications
  publication-title: Eur. J. Oper. Res.
– start-page: 1177
  year: 2007
  end-page: 1184
  ident: bib0061
  article-title: Random features for large-scale kernel machines
  publication-title: Proceedings of the Advances in Neural Information Processing Systems
– year: 1989
  ident: bib0053
  publication-title: Adaptive Pattern Recognition and Neural Networks
– volume: 25
  start-page: 76
  year: 1992
  end-page: 79
  ident: bib0056
  article-title: Functional-link net computing
  publication-title: IEEE Comput.
– volume: 2
  year: 2004
  ident: bib0030
  article-title: Neural Networks: A comprehensive foundation
  publication-title: Neural Netw.
– volume: 70
  start-page: 2959
  year: 2007
  end-page: 2968
  ident: bib0034
  article-title: Functional-link net with fuzzy integral for bankruptcy prediction
  publication-title: Neurocomputing
– volume: 45
  start-page: 303
  year: 2015
  end-page: 314
  ident: bib0046
  article-title: Multisource data ensemble modeling for clinker free lime content estimate in rotary kiln sintering processes
  publication-title: IEEE Trans. Syst., Man, Cybern.: Syst.
– year: 2010
  ident: bib0044
  publication-title: Fuzzy Neural Intelligent Systems: Mathematical Foundation and the Applications in Engineering
– start-page: 369
  year: 2013
  end-page: 377
  ident: bib0048
  article-title: Faster ridge regression via the subsampled randomized hadamard transform
  publication-title: Proceedings of the Advances in Neural Information Processing Systems
– start-page: 879
  year: 2006
  end-page: 888
  ident: bib0076
  article-title: Training neural networks using multiobjective particle swarm optimization
  publication-title: Advances in Natural Computation
– volume: 1
  start-page: 502
  year: 1989
  end-page: 510
  ident: bib0027
  article-title: Random neural networks with negative and positive signals and product form solution
  publication-title: Neural Comput.
– year: 2013
  ident: bib0077
  article-title: Stochastic pooling for regularization of deep convolutional neural networks
  publication-title: Proceedings of the International Conference on Learning Representations
– year: 1989
  ident: bib0058
  article-title: A theory of networks for approximation and learning
  publication-title: Technical Report
– volume: 51
  start-page: 4203
  year: 2005
  end-page: 4215
  ident: bib0013
  article-title: Decoding by linear programming
  publication-title: IEEE Trans. Inf. Theory
– year: 2007
  ident: bib0035
  article-title: Labeled faces in the wild: A database for studying face recognition in unconstrained environments
  publication-title: Technical Report 07-49
– start-page: 593
  year: 2002
  end-page: 600
  ident: bib0039
  article-title: Adaptive nonlinear system identification with echo state networks
  publication-title: Proceedings of the Advances in Neural Information Processing Systems
– start-page: 287
  year: 2006
  end-page: 296
  ident: bib0045
  article-title: Very sparse random projections
  publication-title: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
– volume: 34
  start-page: 123
  year: 1962
  end-page: 135
  ident: bib0010
  article-title: The perceptron: A model for brain functioning. i
  publication-title: Rev. Mod. Phys.
– start-page: 147
  year: 2002
  end-page: 153
  ident: bib0075
  article-title: A novel neural network based on immunity.
  publication-title: Proceedings of the IC-AI
– volume: 264
  start-page: 104
  year: 2014
  end-page: 117
  ident: bib0002
  article-title: Fast decorrelated neural network ensembles with random weights
  publication-title: Inf. Sci.
– start-page: 248
  year: 2009
  end-page: 255
  ident: bib0022
  article-title: Imagenet: A large-scale hierarchical image database
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’09)
– start-page: 17
  year: 1996
  end-page: 22
  ident: bib0001
  article-title: Dynamical behavior of artificial neural networks with random weights
  publication-title: Intelligent Engineering Systems Through Artificial NeuralNetworks
– year: 1988
  ident: bib0012
  article-title: Radial basis functions, multi-variable functional interpolation and adaptive networks
  publication-title: Technical Report
– volume: 53
  start-page: 251
  year: 2010
  end-page: 267
  ident: bib0072
  article-title: The random neural network: a survey
  publication-title: Comput. J.
– volume: 11
  start-page: 3371
  year: 2010
  end-page: 3408
  ident: bib0073
  article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
  publication-title: J. Mach. Learn. Res.
– volume: 1
  start-page: 239
  year: 2001
  end-page: 257
  ident: bib0021
  article-title: Immune and neural network models: theoretical and empirical comparisons
  publication-title: Int. J. Comput. Intell. Appl.
– reference: T.P. Lillicrap, D. Cownden, D.B. Tweed, C.J. Akerman, Random feedback weights support learning in deep neural networks, arXiv preprint arXiv:1411.0247(2014).
– start-page: 1313
  year: 2009
  end-page: 1320
  ident: bib0062
  article-title: Weighted sums of random kitchen sinks: Replacing minimization with randomization in learning
  publication-title: Proceedings of the Advances in Neural Information Processing Systems
– start-page: 530
  year: 2013
  end-page: 538
  ident: bib0071
  article-title: Learning stochastic feedforward neural networks
  publication-title: Proceedings of the Advances in Neural Information Processing Systems
– start-page: 3025
  year: 2013
  end-page: 3032
  ident: bib0017
  article-title: Blessing of dimensionality: High-dimensional feature and its efficient compression for face verification
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 515
  year: 1998
  end-page: 521
  ident: bib0067
  article-title: Ridge regression learning algorithm in dual variables
  publication-title: Proceedings of the 15th International Conference on Machine Learning
– volume: 15
  start-page: 3133
  year: 2014
  end-page: 3181
  ident: bib0026
  article-title: Do we need hundreds of classifiers to solve real world classification problems?
  publication-title: J. Mach. Learn. Res.
– volume: 7
  start-page: 1220
  year: 1996
  end-page: 1230
  ident: bib0015
  article-title: A rapid supervised learning neural network for function interpolation and approximation
  publication-title: IEEE Trans. Neural Netw.
– volume: 6
  start-page: 163
  year: 1994
  end-page: 180
  ident: bib0054
  article-title: Learning and generalization characteristics of the random vector functional-link net
  publication-title: Neurocomputing
– start-page: 2572
  year: 1993
  end-page: 2575
  ident: bib0011
  article-title: Simulated annealing of neural networks: the cooling’strategy reconsidered
  publication-title: Proceedings of the IEEE International Symposium on Circuits and Systems
– volume: 28
  year: 1973
  ident: bib0049
  publication-title: Introduction to Linear and Nonlinear Programming
– volume: 15
  start-page: 1929
  year: 2014
  end-page: 1958
  ident: bib0070
  article-title: Dropout: A simple way to prevent neural networks from overfitting
  publication-title: J. Mach. Learn. Res.
– year: 2014
  ident: bib0079
  article-title: Nonlinear dimensionality reduction of data by deep distributed random samplings
  publication-title: Proceedings of the Sixth Asian Conference on Machine Learning
– start-page: 3041
  year: 2014
  end-page: 3049
  ident: bib0020
  article-title: Scalable kernel methods via doubly stochastic gradients
  publication-title: Proceedings of the Advances in Neural Information Processing Systems
– year: 2015
  ident: bib0063
  article-title: Random vector functional link network for short-term electricity load demand forecasting
  publication-title: Inf. Sci.
– year: 1988
  ident: bib0052
  publication-title: Learning with Localized Receptive Fields
– volume: 3
  start-page: 463
  year: 2003
  end-page: 482
  ident: bib0006
  article-title: Rademacher and gaussian complexities: Risk bounds and structural results
  publication-title: J. Mach. Learn. Res.
– start-page: 2146
  year: 2009
  end-page: 2153
  ident: bib0040
  article-title: What is the best multi-stage architecture for object recognition?
  publication-title: Proceedings of IEEE 12th International Conference on Computer Vision
– volume: 6
  year: 2002
  ident: bib0051
  article-title: Particle swarms for feedforward neural network training
  publication-title: Learning
– start-page: 2146
  year: 2009
  ident: 10.1016/j.ins.2016.01.039_bib0040
  article-title: What is the best multi-stage architecture for object recognition?
– year: 2013
  ident: 10.1016/j.ins.2016.01.039_bib0077
  article-title: Stochastic pooling for regularization of deep convolutional neural networks
– volume: 3
  start-page: 202
  issue: 2
  year: 1992
  ident: 10.1016/j.ins.2016.01.039_bib0005
  article-title: Using random weights to train multilayer networks of hard-limiting units
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/72.125861
– start-page: 760
  year: 2010
  ident: 10.1016/j.ins.2016.01.039_bib0041
  article-title: Particle swarm optimization
– volume: 1
  start-page: 295
  issue: 4
  year: 1988
  ident: 10.1016/j.ins.2016.01.039_bib0038
  article-title: Increased rates of convergence through learning rate adaptation
  publication-title: Neural Netw.
  doi: 10.1016/0893-6080(88)90003-2
– year: 2015
  ident: 10.1016/j.ins.2016.01.039_bib0078
  article-title: A comprehensive evaluation of random vector functional link networks
  publication-title: Inf. Sci.
– volume: 2
  issue: 2004
  year: 2004
  ident: 10.1016/j.ins.2016.01.039_bib0030
  article-title: Neural Networks: A comprehensive foundation
  publication-title: Neural Netw.
– volume: 9
  start-page: 149
  issue: 2
  year: 1995
  ident: 10.1016/j.ins.2016.01.039_bib0055
  article-title: The functional link net and learning optimal control
  publication-title: Neurocomputing
  doi: 10.1016/0925-2312(95)00066-F
– volume: 14
  start-page: 2531
  issue: 11
  year: 2002
  ident: 10.1016/j.ins.2016.01.039_bib0050
  article-title: Real-time computing without stable states: A new framework for neural computation based on perturbations
  publication-title: Neural Comput.
  doi: 10.1162/089976602760407955
– start-page: 1058
  year: 2013
  ident: 10.1016/j.ins.2016.01.039_bib0074
  article-title: Regularization of neural networks using dropconnect
– volume: 78
  start-page: 1481
  issue: 9
  year: 1990
  ident: 10.1016/j.ins.2016.01.039_bib0059
  article-title: Networks for approximation and learning
  publication-title: Proc. IEEE
  doi: 10.1109/5.58326
– volume: 6
  start-page: 163
  issue: 2
  year: 1994
  ident: 10.1016/j.ins.2016.01.039_bib0054
  article-title: Learning and generalization characteristics of the random vector functional-link net
  publication-title: Neurocomputing
  doi: 10.1016/0925-2312(94)90053-1
– volume: 70
  start-page: 2959
  issue: 16
  year: 2007
  ident: 10.1016/j.ins.2016.01.039_bib0034
  article-title: Functional-link net with fuzzy integral for bankruptcy prediction
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2006.10.111
– start-page: 1
  year: 1992
  ident: 10.1016/j.ins.2016.01.039_bib0069
  article-title: Feedforward neural networks with random weights
– volume: 3
  start-page: 463
  year: 2003
  ident: 10.1016/j.ins.2016.01.039_bib0006
  article-title: Rademacher and gaussian complexities: Risk bounds and structural results
  publication-title: J. Mach. Learn. Res.
– start-page: 530
  year: 2013
  ident: 10.1016/j.ins.2016.01.039_bib0071
  article-title: Learning stochastic feedforward neural networks
– start-page: 147
  year: 2002
  ident: 10.1016/j.ins.2016.01.039_bib0075
  article-title: A novel neural network based on immunity.
– volume: 1
  start-page: 239
  issue: 03
  year: 2001
  ident: 10.1016/j.ins.2016.01.039_bib0021
  article-title: Immune and neural network models: theoretical and empirical comparisons
  publication-title: Int. J. Comput. Intell. Appl.
  doi: 10.1142/S1469026801000238
– start-page: 593
  year: 2002
  ident: 10.1016/j.ins.2016.01.039_bib0039
  article-title: Adaptive nonlinear system identification with echo state networks
– volume: 21
  start-page: 1610
  issue: 10
  year: 2010
  ident: 10.1016/j.ins.2016.01.039_bib0025
  article-title: Human tracking using convolutional neural networks
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/TNN.2010.2066286
– volume: 24
  issue: 4
  year: 2007
  ident: 10.1016/j.ins.2016.01.039_bib0004
  article-title: Compressive sensing
  publication-title: IEEE Signal Process. Mag.
  doi: 10.1109/MSP.2007.4286571
– start-page: 2572
  year: 1993
  ident: 10.1016/j.ins.2016.01.039_bib0011
  article-title: Simulated annealing of neural networks: the cooling’strategy reconsidered
– volume: 15
  start-page: 1929
  issue: 1
  year: 2014
  ident: 10.1016/j.ins.2016.01.039_bib0070
  article-title: Dropout: A simple way to prevent neural networks from overfitting
  publication-title: J. Mach. Learn. Res.
– start-page: 879
  year: 2006
  ident: 10.1016/j.ins.2016.01.039_bib0076
  article-title: Training neural networks using multiobjective particle swarm optimization
– start-page: 346
  year: 2007
  ident: 10.1016/j.ins.2016.01.039_bib0018
  article-title: Multiobjective evolutionary neural networks for time series forecasting
– year: 1989
  ident: 10.1016/j.ins.2016.01.039_bib0058
  article-title: A theory of networks for approximation and learning
– volume: 34
  start-page: 123
  year: 1962
  ident: 10.1016/j.ins.2016.01.039_bib0010
  article-title: The perceptron: A model for brain functioning. i
  publication-title: Rev. Mod. Phys.
  doi: 10.1103/RevModPhys.34.123
– volume: 13
  start-page: 281
  issue: 1
  year: 2012
  ident: 10.1016/j.ins.2016.01.039_bib0008
  article-title: Random search for hyper-parameter optimization
  publication-title: J. Mach. Learn. Res.
– start-page: 2528
  year: 2011
  ident: 10.1016/j.ins.2016.01.039_bib0019
  article-title: Selecting receptive fields in deep networks
– volume: 10
  start-page: 68
  issue: 2
  year: 2015
  ident: 10.1016/j.ins.2016.01.039_bib0060
  article-title: Universal approximation with convex optimization: Gimmick or reality?[discussion forum]
  publication-title: IEEE Comput. Intell. Mag.
  doi: 10.1109/MCI.2015.2405352
– volume: 6
  start-page: 1320
  issue: 6
  year: 1995
  ident: 10.1016/j.ins.2016.01.039_bib0037
  article-title: Stochastic choice of basis functions in adaptive function approximation and the functional-link net
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/72.471375
– volume: 34
  issue: 5
  year: 2007
  ident: 10.1016/j.ins.2016.01.039_bib0007
  article-title: Scaling learning algorithms towards AI
  publication-title: Large-Scale Kernel Mach.
  doi: 10.7551/mitpress/7496.003.0016
– volume: 68
  start-page: 361
  issue: 4
  year: 2011
  ident: 10.1016/j.ins.2016.01.039_bib0028
  article-title: Learning in the feed-forward random neural network: A critical review
  publication-title: Perform. Eval.
  doi: 10.1016/j.peva.2010.07.006
– ident: 10.1016/j.ins.2016.01.039_bib0047
– start-page: 515
  year: 1998
  ident: 10.1016/j.ins.2016.01.039_bib0067
  article-title: Ridge regression learning algorithm in dual variables
– volume: 86
  start-page: 2278
  issue: 11
  year: 1998
  ident: 10.1016/j.ins.2016.01.039_bib0043
  article-title: Gradient-based learning applied to document recognition
  publication-title: Proc. IEEE
  doi: 10.1109/5.726791
– start-page: 1089
  year: 2011
  ident: 10.1016/j.ins.2016.01.039_bib0068
  article-title: On random weights and unsupervised feature learning
– volume: 4
  start-page: 251
  issue: 2
  year: 1991
  ident: 10.1016/j.ins.2016.01.039_bib0032
  article-title: Approximation capabilities of multilayer feedforward networks
  publication-title: Neural Netw.
  doi: 10.1016/0893-6080(91)90009-T
– start-page: 287
  year: 2006
  ident: 10.1016/j.ins.2016.01.039_bib0045
  article-title: Very sparse random projections
– volume: 7
  start-page: 1220
  issue: 5
  year: 1996
  ident: 10.1016/j.ins.2016.01.039_bib0015
  article-title: A rapid supervised learning neural network for function interpolation and approximation
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/72.536316
– volume: 25
  start-page: 76
  issue: 5
  year: 1992
  ident: 10.1016/j.ins.2016.01.039_bib0056
  article-title: Functional-link net computing
  publication-title: IEEE Comput.
  doi: 10.1109/2.144401
– volume: 65
  start-page: 386
  issue: 6
  year: 1958
  ident: 10.1016/j.ins.2016.01.039_bib0065
  article-title: The perceptron: a probabilistic model for information storage and organization in the brain.
  publication-title: Psychol. Rev.
  doi: 10.1037/h0042519
– volume: 29
  start-page: 62
  issue: 1
  year: 1999
  ident: 10.1016/j.ins.2016.01.039_bib0016
  article-title: A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction
  publication-title: IEEE Trans. Syst., Man, Cybern., Part B: Cybern.
  doi: 10.1109/3477.740166
– volume: 1
  start-page: 502
  issue: 4
  year: 1989
  ident: 10.1016/j.ins.2016.01.039_bib0027
  article-title: Random neural networks with negative and positive signals and product form solution
  publication-title: Neural Comput.
  doi: 10.1162/neco.1989.1.4.502
– volume: 15
  start-page: 3133
  issue: 1
  year: 2014
  ident: 10.1016/j.ins.2016.01.039_bib0026
  article-title: Do we need hundreds of classifiers to solve real world classification problems?
  publication-title: J. Mach. Learn. Res.
– year: 2015
  ident: 10.1016/j.ins.2016.01.039_bib0063
  article-title: Random vector functional link network for short-term electricity load demand forecasting
  publication-title: Inf. Sci.
– start-page: 1177
  year: 2007
  ident: 10.1016/j.ins.2016.01.039_bib0061
  article-title: Random features for large-scale kernel machines
– volume: 22
  start-page: 2192
  issue: 8
  year: 2010
  ident: 10.1016/j.ins.2016.01.039_bib0042
  article-title: Deep belief networks are compact universal approximators
  publication-title: Neural Comput.
  doi: 10.1162/neco.2010.08-09-1081
– year: 2007
  ident: 10.1016/j.ins.2016.01.039_bib0035
  article-title: Labeled faces in the wild: A database for studying face recognition in unconstrained environments
– volume: 45
  start-page: 303
  issue: 2
  year: 2015
  ident: 10.1016/j.ins.2016.01.039_bib0046
  article-title: Multisource data ensemble modeling for clinker free lime content estimate in rotary kiln sintering processes
  publication-title: IEEE Trans. Syst., Man, Cybern.: Syst.
  doi: 10.1109/TSMC.2014.2332305
– start-page: 369
  year: 2013
  ident: 10.1016/j.ins.2016.01.039_bib0048
  article-title: Faster ridge regression via the subsampled randomized hadamard transform
– year: 1989
  ident: 10.1016/j.ins.2016.01.039_bib0053
– year: 1988
  ident: 10.1016/j.ins.2016.01.039_bib0052
– volume: 11
  start-page: 3371
  year: 2010
  ident: 10.1016/j.ins.2016.01.039_bib0073
  article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
  publication-title: J. Mach. Learn. Res.
– start-page: 17
  year: 1996
  ident: 10.1016/j.ins.2016.01.039_bib0001
  article-title: Dynamical behavior of artificial neural networks with random weights
– volume: 52
  start-page: 5406
  issue: 12
  year: 2006
  ident: 10.1016/j.ins.2016.01.039_bib0014
  article-title: Near-optimal signal recovery from random projections: Universal encoding strategies?
  publication-title: IEEE Trans. Inf. Theory
  doi: 10.1109/TIT.2006.885507
– start-page: 3025
  year: 2013
  ident: 10.1016/j.ins.2016.01.039_bib0017
  article-title: Blessing of dimensionality: High-dimensional feature and its efficient compression for face verification
– volume: 14
  start-page: 76
  issue: 1
  year: 1992
  ident: 10.1016/j.ins.2016.01.039_bib0029
  article-title: On the problem of local minima in backpropagation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/34.107014
– start-page: 1313
  year: 2009
  ident: 10.1016/j.ins.2016.01.039_bib0062
  article-title: Weighted sums of random kitchen sinks: Replacing minimization with randomization in learning
– volume: 11
  start-page: 89
  issue: 1
  year: 1998
  ident: 10.1016/j.ins.2016.01.039_bib0036
  article-title: Neural networks for predicting conditional probability densities: Improved training scheme combining EM and RVFL
  publication-title: Neural Netw.
  doi: 10.1016/S0893-6080(97)00089-0
– volume: 14
  start-page: 129
  issue: 2
  year: 2006
  ident: 10.1016/j.ins.2016.01.039_bib0009
  article-title: Structure and dynamics of random recurrent neural networks
  publication-title: Adapt. Behav.
  doi: 10.1177/105971230601400204
– start-page: 248
  year: 2009
  ident: 10.1016/j.ins.2016.01.039_bib0022
  article-title: Imagenet: A large-scale hierarchical image database
– volume: 264
  start-page: 104
  year: 2014
  ident: 10.1016/j.ins.2016.01.039_bib0002
  article-title: Fast decorrelated neural network ensembles with random weights
  publication-title: Inf. Sci.
  doi: 10.1016/j.ins.2013.12.016
– start-page: 3041
  year: 2014
  ident: 10.1016/j.ins.2016.01.039_bib0020
  article-title: Scalable kernel methods via doubly stochastic gradients
– year: 1961
  ident: 10.1016/j.ins.2016.01.039_bib0066
  article-title: Principles of neurodynamics. perceptrons and the theory of brain mechanisms
– volume: 313
  start-page: 504
  issue: 5786
  year: 2006
  ident: 10.1016/j.ins.2016.01.039_bib0031
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
  doi: 10.1126/science.1127647
– volume: 28
  year: 1973
  ident: 10.1016/j.ins.2016.01.039_bib0049
– volume: 2
  start-page: 641
  issue: 6
  year: 1988
  ident: 10.1016/j.ins.2016.01.039_bib0024
  article-title: Teaching feed-forward neural networks by simulated annealing
  publication-title: Complex Syst.
– volume: 6
  issue: 1
  year: 2002
  ident: 10.1016/j.ins.2016.01.039_bib0051
  article-title: Particle swarms for feedforward neural network training
  publication-title: Learning
– year: 1988
  ident: 10.1016/j.ins.2016.01.039_bib0012
  article-title: Radial basis functions, multi-variable functional interpolation and adaptive networks
– volume: 51
  start-page: 4203
  issue: 12
  year: 2005
  ident: 10.1016/j.ins.2016.01.039_bib0013
  article-title: Decoding by linear programming
  publication-title: IEEE Trans. Inf. Theory
  doi: 10.1109/TIT.2005.858979
– year: 2010
  ident: 10.1016/j.ins.2016.01.039_bib0044
– volume: 5
  start-page: e1000579
  issue: 11
  year: 2009
  ident: 10.1016/j.ins.2016.01.039_bib0057
  article-title: A high-throughput screening approach to discovering good forms of biologically inspired visual representation
  publication-title: PLoS Comput Biol
  doi: 10.1371/journal.pcbi.1000579
– volume: 126
  start-page: 319
  issue: 2
  year: 2000
  ident: 10.1016/j.ins.2016.01.039_bib0003
  article-title: Survey of random neural network applications
  publication-title: Eur. J. Oper. Res.
  doi: 10.1016/S0377-2217(99)00481-6
– volume: 53
  start-page: 251
  issue: 3
  year: 2010
  ident: 10.1016/j.ins.2016.01.039_bib0072
  article-title: The random neural network: a survey
  publication-title: Comput. J.
  doi: 10.1093/comjnl/bxp032
– volume: 29
  start-page: 3
  issue: 1
  year: 1999
  ident: 10.1016/j.ins.2016.01.039_bib0023
  article-title: JNN, a randomized algorithm for training multilayer networks in polynomial time
  publication-title: Neurocomputing
  doi: 10.1016/S0925-2312(99)00115-0
– year: 2015
  ident: 10.1016/j.ins.2016.01.039_bib0064
  article-title: Ensemble classification and regression – recent developments, applications and future directions
  publication-title: IEEE Comput. Intell. Mag.
– volume: 72
  start-page: 1808
  issue: 7
  year: 2009
  ident: 10.1016/j.ins.2016.01.039_bib0033
  article-title: Functional-link nets with genetic-algorithm-based learning for robust nonlinear interval regression analysis
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2008.07.002
– year: 2014
  ident: 10.1016/j.ins.2016.01.039_bib0079
  article-title: Nonlinear dimensionality reduction of data by deep distributed random samplings
SSID ssj0004766
Score 2.6195045
Snippet As a powerful tool for data regression and classification, neural networks have received considerable attention from researchers in fields such as machine...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 146
SubjectTerms Classification
Convergence
Convolutional neural networks
Deep learning
Networks
Neural networks
Randomization
Randomized neural networks
Recurrent neural networks
Regression
Statistics
Training
Title A survey of randomized algorithms for training neural networks
URI https://dx.doi.org/10.1016/j.ins.2016.01.039
https://www.proquest.com/docview/1825521883
Volume 364-365
WOSCitedRecordID wos000378969400010&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-6291
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004766
  issn: 0020-0255
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bi9QwFA4668P6IDoqrroSQfbBJdA2mVxehEFmURnGBWdh3kKmTffC2o5zWRZ_vSdN0qkrLuuDL6WU9EK-9ORcv4PQu4FKbCkGGUlZZgjLuSQmFYZYRR3fmKHMFwqPxWQiZzN1HLrwrZp2AqKq5PW1WvxXqOEagO1KZ_8B7vahcAHOAXQ4AuxwvBPww8PVZnllm8g5bERF_f38J2iV5vK0Xp6vzzwBQ9sa4tARWgJMlU8HX3WV1VCq1KyQsFO2GnjraB63K-Pb5hRgOvMe1eMQ4wkOhZQ7SRxSS2OCf0KcqdEVkpSzjpiLbkO_Y6Z-6B_C2PsFLsCCcLzoKW_4UT110e_E15Ov-uhkPNbT0Wx6sPhBXE8wFzsPDVLuo51MgOHTQzvDz6PZl23dq_Cx6PjBMWrd5O_deOvf9I4bO3CjVkwfo0fBHsBDj-MTdM9WffSwwxLZR_uhtgQf4A4iOEjlPtp1BoPn236KPgyxhx_XJd7Cj7fwY3gEjvBjDz-O8D9DJ0ej6cdPJPTIIDlVfE2s5dKyIsl5UiaJyWRRlqBgZHNGpbGZBeuSi7kCK90MeAm6oKvFBpW7EHNLqcjoc9Sr6sq-QHiumLCKS2aLlImCG5PaUvISTIqiyJXZQ0mcQZ0HAnn3tZc6ZgpeaJh07SZdJ6mGN-2h9-0tC8-ecttgFmHRYVF7tU7DgrrttrcRQg2i0cW7TGXrzUqD6TwA7VRK-vIOY16h3e3f8Br11suN3UcP8itAcPkmLL1f692E4A
linkProvider Elsevier
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+survey+of+randomized+algorithms+for+training+neural+networks&rft.jtitle=Information+sciences&rft.au=Zhang%2C+Le&rft.au=Suganthan%2C+P+N&rft.date=2016-10-10&rft.issn=0020-0255&rft.volume=364&rft.spage=146&rft.epage=155&rft_id=info:doi/10.1016%2Fj.ins.2016.01.039&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0020-0255&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0020-0255&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0020-0255&client=summon