Learning Algorithms for Quaternion-Valued Neural Networks

This paper presents the deduction of the enhanced gradient descent, conjugate gradient, scaled conjugate gradient, quasi-Newton, and Levenberg–Marquardt methods for training quaternion-valued feedforward neural networks, using the framework of the HR calculus. The performances of these algorithms in...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Neural processing letters Ročník 47; číslo 3; s. 949 - 973
Hlavný autor: Popa, Călin-Adrian
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.06.2018
Springer Nature B.V
Predmet:
ISSN:1370-4621, 1573-773X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract This paper presents the deduction of the enhanced gradient descent, conjugate gradient, scaled conjugate gradient, quasi-Newton, and Levenberg–Marquardt methods for training quaternion-valued feedforward neural networks, using the framework of the HR calculus. The performances of these algorithms in the real- and complex-valued cases led to the idea of extending them to the quaternion domain, also. Experiments done using the proposed training methods on time series prediction applications showed a significant performance improvement over the quaternion gradient descent algorithm.
AbstractList This paper presents the deduction of the enhanced gradient descent, conjugate gradient, scaled conjugate gradient, quasi-Newton, and Levenberg–Marquardt methods for training quaternion-valued feedforward neural networks, using the framework of the HR calculus. The performances of these algorithms in the real- and complex-valued cases led to the idea of extending them to the quaternion domain, also. Experiments done using the proposed training methods on time series prediction applications showed a significant performance improvement over the quaternion gradient descent algorithm.
Author Popa, Călin-Adrian
Author_xml – sequence: 1
  givenname: Călin-Adrian
  orcidid: 0000-0003-4445-8091
  surname: Popa
  fullname: Popa, Călin-Adrian
  email: calin.popa@cs.upt.ro
  organization: Department of Computer and Software Engineering, Polytechnic University Timişoara
BookMark eNp9kF1LwzAUhoNMcJv-AO8KXkdzmrZJLsfwC4YiqHgX0iSdnV0zkxTx35tRQRD06j1w3ud8vDM06V1vEToFcg6EsIsAQCqKCTAsGFQYDtAUSkYxY_RlkmrKCC6qHI7QLIQNIYnKyRSJlVW-b_t1tujWzrfxdRuyxvnsYVDRpo7r8bPqBmuyOzt41SWJH86_hWN02Kgu2JNvnaOnq8vH5Q1e3V_fLhcrrCnPI9aMNkAp0Y0xmitR1wClqQpCNedGcSosrXVTcQJ1WYMurRKU6aoShhcGNJ2js3Huzrv3wYYoN27wfVopcwGcFkCYSC4YXdq7ELxt5M63W-U_JRC5T0iOCcmUkNwnJCEx7Bej26hiejl61Xb_kvlIhrSlX1v_c9Pf0BfGA3wE
CitedBy_id crossref_primary_10_1007_s10489_022_03849_x
crossref_primary_10_1007_s11571_021_09763_1
crossref_primary_10_1016_j_neucom_2021_03_133
crossref_primary_10_1007_s40747_022_00911_6
crossref_primary_10_1109_TNNLS_2020_2979682
crossref_primary_10_1109_ACCESS_2022_3222372
crossref_primary_10_1007_s11831_023_09925_w
crossref_primary_10_1007_s10462_019_09752_1
crossref_primary_10_1016_j_apnum_2023_08_006
crossref_primary_10_3390_machines10050333
crossref_primary_10_1080_00207721_2022_2145859
crossref_primary_10_1016_j_neucom_2019_03_026
crossref_primary_10_1007_s11063_018_9948_8
Cites_doi 10.1109/TSP.2005.845462
10.1016/S0893-6080(05)80056-5
10.1162/neco.1992.4.2.141
10.1109/72.329697
10.1016/0893-6080(88)90003-2
10.1142/S0129065708001403
10.1007/BF01593790
10.1109/TSP.2008.2010600
10.1007/978-3-319-59153-7_32
10.1016/j.renene.2010.12.013
10.1137/0111030
10.1007/978-3-642-24955-6_66
10.1142/S0129065791000261
10.1090/S0025-5718-1970-0274029-X
10.1007/978-3-540-45226-3_44
10.1093/comjnl/7.2.149
10.1002/047084535X
10.1109/TNN.2011.2157358
10.1162/0899766042321779
10.6028/jres.049.044
10.1016/j.neunet.2009.10.006
10.1051/m2an/196903R100351
10.1016/0893-6080(90)90006-7
10.1016/S0893-6080(96)00048-2
10.1093/comjnl/6.2.163
10.1109/TNNLS.2015.2440473
10.1049/ip-g-2.1992.0050
10.1109/TSP.2010.2047719
10.1109/TSP.2010.2048323
10.1109/TNN.2007.895828
10.1016/j.neunet.2007.09.015
10.1109/TNNLS.2014.2320715
10.1109/TNN.2010.2085444
10.1109/72.125864
10.1016/0920-5489(94)90017-5
10.1109/IJCNN.2015.7280450
10.1007/978-0-387-74503-9
10.1109/IJCNN.2011.6033585
10.1109/IJCNN.2010.5596629
10.1007/b105056
10.1007/978-3-319-62524-9_5
10.1109/ICNN.1993.298623
10.1109/ICSMC.1995.538035
10.1109/ICASSP.2012.6288329
10.1007/978-3-319-19824-8_18
10.1109/IJCNN.2010.5596690
10.1007/BFb0047683
10.1007/978-3-319-46675-0_27
10.1109/SYNASC.2016.050
10.1093/oso/9780198538493.001.0001
10.1109/SYNASC.2014.44
10.1109/ICASSP.2009.4960282
10.1007/978-0-387-40065-5
10.1007/978-3-319-26535-3_47
10.1007/978-3-319-58088-3_17
ContentType Journal Article
Copyright Springer Science+Business Media, LLC 2017
Copyright Springer Nature B.V. Jun 2018
Copyright_xml – notice: Springer Science+Business Media, LLC 2017
– notice: Copyright Springer Nature B.V. Jun 2018
DBID AAYXX
CITATION
8FE
8FG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
GNUQQ
HCIFZ
JQ2
K7-
P5Z
P62
PHGZM
PHGZT
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PSYQQ
DOI 10.1007/s11063-017-9716-1
DatabaseName CrossRef
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
ProQuest Central
Technology Collection
ProQuest One Community College
ProQuest Central
ProQuest Central Student
SciTech Premium Collection
ProQuest Computer Science Collection
Computer Science Database
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest One Academic
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
ProQuest One Psychology
DatabaseTitle CrossRef
Advanced Technologies & Aerospace Collection
ProQuest One Psychology
Computer Science Database
ProQuest Central Student
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science 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 1573-773X
EndPage 973
ExternalDocumentID 10_1007_s11063_017_9716_1
GroupedDBID -4Z
-5F
-5G
-BR
-EM
-Y2
-~C
.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
8TC
8UJ
95-
95.
95~
96X
AAAVM
AABHQ
AAHNG
AAIAL
AAJKR
AAJSJ
AAKKN
AANZL
AAOBN
AARHV
AARTL
AATVU
AAUYE
AAWCG
AAYIU
AAYOK
AAYQN
AAYTO
AAYZH
ABAKF
ABBBX
ABBXA
ABDZT
ABECU
ABEEZ
ABFTD
ABFTV
ABHLI
ABHQN
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMOR
ABMQK
ABNWP
ABQBU
ABQSL
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABWNU
ABXPI
ACACY
ACBXY
ACGFS
ACHSB
ACHXU
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACSNA
ACULB
ACZOJ
ADHHG
ADHIR
ADIMF
ADINQ
ADKNI
ADKPE
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFIE
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEKMD
AENEX
AEOHA
AEPYU
AESKC
AETLH
AEVLU
AEXYK
AFBBN
AFEXP
AFGCZ
AFGXO
AFKRA
AFLOW
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGGDS
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHSBF
AHYZX
AIAKS
AIIXL
AILAN
AITGF
AJBLW
AJRNO
AJZVZ
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMXSW
AMYLF
AMYQR
AOCGG
ARAPS
ARMRJ
ASPBG
AVWKF
AXYYD
AYJHY
AZFZN
B-.
BA0
BBWZM
BDATZ
BENPR
BGLVJ
BGNMA
C24
C6C
CAG
CCPQU
COF
CS3
CSCUP
DDRTE
DL5
DNIVK
DPUIP
DU5
EBLON
EBS
EIOEI
EJD
ESBYG
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~
I09
IHE
IJ-
IKXTQ
ITM
IWAJR
IXC
IXE
IZIGR
IZQ
I~X
I~Z
J-C
J0Z
JBSCW
JCJTX
JZLTJ
K7-
KDC
KOV
KOW
LAK
LLZTM
M4Y
MA-
N2Q
NB0
NDZJH
NPVJJ
NQJWS
NU0
O9-
O93
O9G
O9I
O9J
OAM
OVD
P19
P2P
P9O
PF0
PSYQQ
PT5
QOK
QOS
R4E
R89
R9I
RHV
RNI
RNS
ROL
RPX
RSV
RZC
RZE
RZK
S16
S1Z
S26
S27
S28
S3B
SAP
SCJ
SCLPG
SDH
SDM
SHX
SISQX
SNE
SNPRN
SNX
SOHCF
SOJ
SPH
SPISZ
SRMVM
SSLCW
STPWE
SZN
T13
T16
TEORI
TSG
TSK
TSV
TUC
U2A
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W23
W48
WK8
YLTOR
Z45
Z7R
Z7X
Z81
Z83
Z88
Z8M
Z8R
Z8U
Z8W
Z92
ZMTXR
~EX
77I
AASML
AAYXX
ABDBE
ABFSG
ACSTC
ADHKG
AEZWR
AFFHD
AFHIU
AGQPQ
AHPBZ
AHWEU
AIXLP
AYFIA
CITATION
PHGZM
PHGZT
PQGLB
8FE
8FG
AZQEC
DWQXO
GNUQQ
JQ2
P62
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c382t-c73f1330cfddc8a9bb115d6403c88da839e3bcf6801b5b1c5ea937c669d84d1c3
IEDL.DBID K7-
ISICitedReferencesCount 20
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000434268000014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1370-4621
IngestDate Sat Oct 18 22:46:40 EDT 2025
Sat Nov 29 02:27:47 EST 2025
Tue Nov 18 22:05:16 EST 2025
Fri Feb 21 02:36:42 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 3
Keywords Quaternion-valued neural networks
Resilient backpropagation
SuperSAB
Levenberg–Marquardt algorithm
Conjugate gradient algorithms
Quickprop
Scaled conjugate gradient algorithm
Time series prediction
Quasi-Newton algorithms
Delta-bar-delta
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c382t-c73f1330cfddc8a9bb115d6403c88da839e3bcf6801b5b1c5ea937c669d84d1c3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-4445-8091
PQID 2918341079
PQPubID 2043838
PageCount 25
ParticipantIDs proquest_journals_2918341079
crossref_primary_10_1007_s11063_017_9716_1
crossref_citationtrail_10_1007_s11063_017_9716_1
springer_journals_10_1007_s11063_017_9716_1
PublicationCentury 2000
PublicationDate 2018-06-01
PublicationDateYYYYMMDD 2018-06-01
PublicationDate_xml – month: 06
  year: 2018
  text: 2018-06-01
  day: 01
PublicationDecade 2010
PublicationPlace New York
PublicationPlace_xml – name: New York
– name: Dordrecht
PublicationTitle Neural processing letters
PublicationTitleAbbrev Neural Process Lett
PublicationYear 2018
Publisher Springer US
Springer Nature B.V
Publisher_xml – name: Springer US
– name: Springer Nature B.V
References Goh, Mandic (CR19) 2007; 20
Took, Mandic (CR51) 2010; 58
CR38
Charalambous (CR11) 1992; 139
CR36
CR34
Xia, Jahanchahi, Mandic (CR57) 2015; 26
Xu, Xia, Mandic (CR59) 2016; 27
Che Ujang, Took, Mandic (CR12) 2010; 23
Arena, Fortuna, Muscato, Xibilia (CR3) 1997; 10
Mandic, Chambers (CR29) 2001
CR2
Xia, Jelfs, Van Hulle, Principe, Mandic (CR58) 2011; 22
Goh, Mandic (CR18) 2005; 53
CR4
Bishop (CR8) 1995
Fletcher, Powell (CR16) 1963; 6
Tollenaere (CR48) 1990; 3
Reeves, Fletcher (CR44) 1964; 7
Goh, Mandic (CR20) 2007; 18
CR46
Hestenes, Stiefel (CR22) 1952; 49
CR42
CR40
Jacobs (CR24) 1988; 1
Battiti (CR6) 1992; 4
Hagan, Menhaj (CR21) 1994; 5
Popa (CR35) 2015; 2015
Amin, Amin, Al-Nuaimi, Murase, Lu, Zhang, Kwok (CR1) 2011
CR15
CR14
Marquardt (CR30) 1963; 11
Popa (CR41) 2017; 2017
CR56
CR55
CR10
CR53
CR52
Nocedal, Wright (CR32) 1999
Polak, Ribiere (CR33) 1969; 3
Barnard (CR5) 1992; 3
Shanno (CR47) 1970; 24
Took, Strbac, Aihara, Mandic (CR54) 2011; 36
Che Ujang, Took, Mandic (CR13) 2011; 22
Luenberger, Ye (CR28) 2008
Popa, Matoušek (CR37) 2015
Beale, Lootsma (CR7) 1972
Took, Mandic (CR49) 2009; 57
Goh, Mandic (CR17) 2004; 16
Zhang (CR60) 2005
Riedmiller (CR45) 1994; 16
CR27
Møller (CR31) 1993; 6
Took, Mandic (CR50) 2010; 58
CR25
Popa (CR39) 2016; 2016
Powell (CR43) 1977; 12
Johansson, Dowla, Goodman (CR26) 1991; 2
Buchholz, Le Bihan (CR9) 2008; 18
Isokawa, Kusakabe, Matsui, Peper, Palade, Howlett, Jai (CR23) 2003
(9716_CR60) 2005
9716_CR46
9716_CR42
D Xu (9716_CR59) 2016; 27
9716_CR40
S Goh (9716_CR18) 2005; 53
C Charalambous (9716_CR11) 1992; 139
M Møller (9716_CR31) 1993; 6
CA Popa (9716_CR37) 2015
B Che Ujang (9716_CR13) 2011; 22
M Powell (9716_CR43) 1977; 12
9716_CR36
E Johansson (9716_CR26) 1991; 2
9716_CR34
E Polak (9716_CR33) 1969; 3
T Isokawa (9716_CR23) 2003
Y Xia (9716_CR57) 2015; 26
S Goh (9716_CR20) 2007; 18
C Bishop (9716_CR8) 1995
R Jacobs (9716_CR24) 1988; 1
9716_CR38
J Nocedal (9716_CR32) 1999
M Riedmiller (9716_CR45) 1994; 16
C Took (9716_CR51) 2010; 58
9716_CR25
M Amin (9716_CR1) 2011
R Battiti (9716_CR6) 1992; 4
D Marquardt (9716_CR30) 1963; 11
M Hestenes (9716_CR22) 1952; 49
Y Xia (9716_CR58) 2011; 22
E Beale (9716_CR7) 1972
S Buchholz (9716_CR9) 2008; 18
CA Popa (9716_CR35) 2015; 2015
CA Popa (9716_CR41) 2017; 2017
P Arena (9716_CR3) 1997; 10
C Took (9716_CR50) 2010; 58
B Che Ujang (9716_CR12) 2010; 23
M Hagan (9716_CR21) 1994; 5
9716_CR27
9716_CR14
D Mandic (9716_CR29) 2001
9716_CR15
9716_CR56
9716_CR10
9716_CR55
9716_CR52
9716_CR53
CA Popa (9716_CR39) 2016; 2016
C Took (9716_CR49) 2009; 57
S Goh (9716_CR19) 2007; 20
E Barnard (9716_CR5) 1992; 3
D Luenberger (9716_CR28) 2008
9716_CR4
R Fletcher (9716_CR16) 1963; 6
T Tollenaere (9716_CR48) 1990; 3
9716_CR2
D Shanno (9716_CR47) 1970; 24
S Goh (9716_CR17) 2004; 16
C Reeves (9716_CR44) 1964; 7
C Took (9716_CR54) 2011; 36
References_xml – volume: 53
  start-page: 1827
  issue: 5
  year: 2005
  end-page: 1836
  ident: CR18
  article-title: Nonlinear adaptive prediction of complex-valued signals by complex-valued PRNN
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2005.845462
– volume: 6
  start-page: 525
  issue: 4
  year: 1993
  end-page: 533
  ident: CR31
  article-title: A scaled conjugate gradient algorithm for fast supervised learning
  publication-title: Neural Netw
  doi: 10.1016/S0893-6080(05)80056-5
– volume: 4
  start-page: 141
  issue: 2
  year: 1992
  end-page: 166
  ident: CR6
  article-title: First and second-order methods for learning between steepest descent and Newton’s method
  publication-title: Neural Comput
  doi: 10.1162/neco.1992.4.2.141
– volume: 5
  start-page: 989
  issue: 6
  year: 1994
  end-page: 993
  ident: CR21
  article-title: Training feedforward networks with the Marquardt algorithm
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.329697
– year: 2005
  ident: CR60
  publication-title: The Schur complement and its applications
– ident: CR4
– volume: 1
  start-page: 295
  issue: 4
  year: 1988
  end-page: 307
  ident: CR24
  article-title: Increased rates of convergence through learning rate adaptation
  publication-title: Neural Netw
  doi: 10.1016/0893-6080(88)90003-2
– volume: 18
  start-page: 75
  issue: 2
  year: 2008
  end-page: 85
  ident: CR9
  article-title: Polarized signal classification by complex and quaternionic multi-layer perceptrons
  publication-title: Int J Neural Syst
  doi: 10.1142/S0129065708001403
– volume: 12
  start-page: 241
  issue: 1
  year: 1977
  end-page: 254
  ident: CR43
  article-title: Restart procedures for the conjugate gradient method
  publication-title: Math Program
  doi: 10.1007/BF01593790
– volume: 57
  start-page: 1316
  issue: 4
  year: 2009
  end-page: 1327
  ident: CR49
  article-title: The quaternion LMS algorithm for adaptive filtering of hypercomplex processes
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2008.2010600
– volume: 2017
  start-page: 362
  year: 2017
  end-page: 374
  ident: CR41
  article-title: Quasi-newton learning methods for quaternion-valued neural networks
  publication-title: Adv Comput Intell IWANN
  doi: 10.1007/978-3-319-59153-7_32
– ident: CR25
– ident: CR42
– volume: 36
  start-page: 1754
  issue: 6
  year: 2011
  end-page: 1760
  ident: CR54
  article-title: Quaternion-valued short-term joint forecasting of three-dimensional wind and atmospheric parameters
  publication-title: Renew Energy
  doi: 10.1016/j.renene.2010.12.013
– ident: CR46
– volume: 11
  start-page: 431
  issue: 2
  year: 1963
  end-page: 441
  ident: CR30
  article-title: An algorithm for least-squares estimation of nonlinear parameters
  publication-title: J Soc Ind Appl Math
  doi: 10.1137/0111030
– start-page: 550
  year: 2011
  end-page: 559
  ident: CR1
  article-title: Wirtinger calculus based gradient descent and Levenberg–Marquardt learning algorithms in complex-valued neural networks
  publication-title: Neural information processing. Lecture notes in computer science
  doi: 10.1007/978-3-642-24955-6_66
– ident: CR15
– volume: 2
  start-page: 291
  issue: 4
  year: 1991
  end-page: 301
  ident: CR26
  article-title: Backpropagation learning for multilayer feed-forward neural networks using the conjugate gradient method
  publication-title: Int J Neural Syst
  doi: 10.1142/S0129065791000261
– volume: 24
  start-page: 647
  issue: 111
  year: 1970
  end-page: 656
  ident: CR47
  article-title: Conditioning of quasi-Newton methods for function minimization
  publication-title: Math Comput
  doi: 10.1090/S0025-5718-1970-0274029-X
– start-page: 318
  year: 2003
  end-page: 324
  ident: CR23
  article-title: Quaternion neural network and its application
  publication-title: Knowledge-based intelligent information and engineering systems. Lecture notes in computer science
  doi: 10.1007/978-3-540-45226-3_44
– ident: CR36
– volume: 7
  start-page: 149
  issue: 2
  year: 1964
  end-page: 154
  ident: CR44
  article-title: Function minimization by conjugate gradients
  publication-title: Comput J
  doi: 10.1093/comjnl/7.2.149
– year: 2001
  ident: CR29
  publication-title: Recurrent neural networks for prediction: learning algorithms, architectures and stability
  doi: 10.1002/047084535X
– year: 2008
  ident: CR28
  publication-title: Linear and nonlinear programming. International series in operations research & management science
– volume: 22
  start-page: 1193
  issue: 8
  year: 2011
  end-page: 1206
  ident: CR13
  article-title: Quaternion-valued nonlinear adaptive filtering
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/TNN.2011.2157358
– volume: 16
  start-page: 2699
  issue: 12
  year: 2004
  end-page: 2713
  ident: CR17
  article-title: A complex-valued RTRL algorithm for recurrent neural networks
  publication-title: Neural Comput
  doi: 10.1162/0899766042321779
– volume: 49
  start-page: 409
  issue: 6
  year: 1952
  end-page: 436
  ident: CR22
  article-title: Methods of conjugate gradients for solving linear systems
  publication-title: J Res Natl Bur Stand
  doi: 10.6028/jres.049.044
– ident: CR14
– ident: CR2
– ident: CR53
– volume: 23
  start-page: 426
  issue: 3
  year: 2010
  end-page: 434
  ident: CR12
  article-title: Split quaternion nonlinear adaptive filtering
  publication-title: Neural Netw
  doi: 10.1016/j.neunet.2009.10.006
– volume: 3
  start-page: 35
  issue: 16
  year: 1969
  end-page: 43
  ident: CR33
  article-title: Note sur la convergence de méthodes de directions conjuguées
  publication-title: Revue Française d’Informatique et de Recherche Opérationnelle
  doi: 10.1051/m2an/196903R100351
– ident: CR10
– volume: 3
  start-page: 561
  issue: 5
  year: 1990
  end-page: 573
  ident: CR48
  article-title: Supersab: fast adaptive back propagation with good scaling properties
  publication-title: Neural Netw
  doi: 10.1016/0893-6080(90)90006-7
– volume: 10
  start-page: 335
  issue: 2
  year: 1997
  end-page: 342
  ident: CR3
  article-title: Multilayer perceptrons to approximate quaternion valued functions
  publication-title: Neural Netw
  doi: 10.1016/S0893-6080(96)00048-2
– volume: 6
  start-page: 163
  issue: 2
  year: 1963
  end-page: 168
  ident: CR16
  article-title: A rapidly convergent descent method for minimization
  publication-title: Comput J
  doi: 10.1093/comjnl/6.2.163
– ident: CR56
– volume: 2016
  start-page: 243
  year: 2016
  end-page: 252
  ident: CR39
  article-title: Scaled conjugate gradient learning for quaternion-valued neural networks
  publication-title: Neural Inf Process ICONIP
– ident: CR40
– volume: 27
  start-page: 249
  issue: 2
  year: 2016
  end-page: 261
  ident: CR59
  article-title: Optimization in quaternion dynamic systems: gradient, Hessian, and learning algorithms
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2015.2440473
– ident: CR27
– volume: 139
  start-page: 301
  issue: 3
  year: 1992
  end-page: 310
  ident: CR11
  article-title: Conjugate gradient algorithm for efficient training of artificial neural networks
  publication-title: IEE Proc G Circuits Devices Syst
  doi: 10.1049/ip-g-2.1992.0050
– volume: 58
  start-page: 3895
  issue: 7
  year: 2010
  end-page: 3901
  ident: CR50
  article-title: Quaternion-valued stochastic gradient-based adaptive IIR filtering
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2010.2047719
– year: 1995
  ident: CR8
  publication-title: Neural networks for pattern recognition
– volume: 58
  start-page: 4427
  issue: 8
  year: 2010
  end-page: 4431
  ident: CR51
  article-title: A quaternion widely linear adaptive filter
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2010.2048323
– volume: 18
  start-page: 1511
  issue: 5
  year: 2007
  end-page: 1516
  ident: CR20
  article-title: Stochastic gradient-adaptive complex-valued nonlinear neural adaptive filters with a gradient-adaptive step size
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/TNN.2007.895828
– start-page: 39
  year: 1972
  end-page: 43
  ident: CR7
  article-title: A derivation of conjugate gradients
  publication-title: Numerical methods for nonlinear optimization
– start-page: 221
  year: 2015
  end-page: 233
  ident: CR37
  article-title: Scaled conjugate gradient learning for complex-valued neural networks
  publication-title: Mendel 2015. Advances in intelligent systems and computing
– ident: CR38
– ident: CR52
– volume: 20
  start-page: 1061
  issue: 10
  year: 2007
  end-page: 1066
  ident: CR19
  article-title: An augmented CRTRL for complex-valued recurrent neural networks
  publication-title: Neural Netw
  doi: 10.1016/j.neunet.2007.09.015
– volume: 26
  start-page: 663
  issue: 4
  year: 2015
  end-page: 673
  ident: CR57
  article-title: Quaternion-valued echo state networks
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2014.2320715
– volume: 22
  start-page: 74
  issue: 1
  year: 2011
  end-page: 83
  ident: CR58
  article-title: An augmented echo state network for nonlinear adaptive filtering of complex noncircular signals
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/TNN.2010.2085444
– volume: 3
  start-page: 232
  issue: 2
  year: 1992
  end-page: 240
  ident: CR5
  article-title: Optimization for training neural nets
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.125864
– ident: CR34
– volume: 16
  start-page: 265
  issue: 3
  year: 1994
  end-page: 278
  ident: CR45
  article-title: Advanced supervised learning in multi-layer perceptrons—from backpropagation to adaptive learning algorithms
  publication-title: Comput Stand Interfaces
  doi: 10.1016/0920-5489(94)90017-5
– ident: CR55
– year: 1999
  ident: CR32
  publication-title: Numerical optimization. Springer series in operations research
– volume: 2015
  start-page: 412
  year: 2015
  end-page: 422
  ident: CR35
  article-title: Conjugate gradient algorithms for complex-valued neural networks
  publication-title: Neural Inf Process ICONIP
– volume: 1
  start-page: 295
  issue: 4
  year: 1988
  ident: 9716_CR24
  publication-title: Neural Netw
  doi: 10.1016/0893-6080(88)90003-2
– volume: 10
  start-page: 335
  issue: 2
  year: 1997
  ident: 9716_CR3
  publication-title: Neural Netw
  doi: 10.1016/S0893-6080(96)00048-2
– ident: 9716_CR36
  doi: 10.1109/IJCNN.2015.7280450
– volume: 5
  start-page: 989
  issue: 6
  year: 1994
  ident: 9716_CR21
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.329697
– volume: 20
  start-page: 1061
  issue: 10
  year: 2007
  ident: 9716_CR19
  publication-title: Neural Netw
  doi: 10.1016/j.neunet.2007.09.015
– volume: 36
  start-page: 1754
  issue: 6
  year: 2011
  ident: 9716_CR54
  publication-title: Renew Energy
  doi: 10.1016/j.renene.2010.12.013
– volume-title: Linear and nonlinear programming. International series in operations research & management science
  year: 2008
  ident: 9716_CR28
  doi: 10.1007/978-0-387-74503-9
– start-page: 318
  volume-title: Knowledge-based intelligent information and engineering systems. Lecture notes in computer science
  year: 2003
  ident: 9716_CR23
  doi: 10.1007/978-3-540-45226-3_44
– ident: 9716_CR55
  doi: 10.1109/IJCNN.2011.6033585
– ident: 9716_CR25
  doi: 10.1109/IJCNN.2010.5596629
– volume: 27
  start-page: 249
  issue: 2
  year: 2016
  ident: 9716_CR59
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2015.2440473
– start-page: 550
  volume-title: Neural information processing. Lecture notes in computer science
  year: 2011
  ident: 9716_CR1
  doi: 10.1007/978-3-642-24955-6_66
– volume: 11
  start-page: 431
  issue: 2
  year: 1963
  ident: 9716_CR30
  publication-title: J Soc Ind Appl Math
  doi: 10.1137/0111030
– volume: 3
  start-page: 35
  issue: 16
  year: 1969
  ident: 9716_CR33
  publication-title: Revue Française d’Informatique et de Recherche Opérationnelle
  doi: 10.1051/m2an/196903R100351
– volume-title: The Schur complement and its applications
  year: 2005
  ident: 9716_CR60
  doi: 10.1007/b105056
– volume: 6
  start-page: 525
  issue: 4
  year: 1993
  ident: 9716_CR31
  publication-title: Neural Netw
  doi: 10.1016/S0893-6080(05)80056-5
– ident: 9716_CR42
  doi: 10.1007/978-3-319-62524-9_5
– ident: 9716_CR46
  doi: 10.1109/ICNN.1993.298623
– ident: 9716_CR2
  doi: 10.1109/ICSMC.1995.538035
– ident: 9716_CR14
  doi: 10.1109/ICASSP.2012.6288329
– volume: 3
  start-page: 232
  issue: 2
  year: 1992
  ident: 9716_CR5
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.125864
– volume: 139
  start-page: 301
  issue: 3
  year: 1992
  ident: 9716_CR11
  publication-title: IEE Proc G Circuits Devices Syst
  doi: 10.1049/ip-g-2.1992.0050
– volume: 18
  start-page: 75
  issue: 2
  year: 2008
  ident: 9716_CR9
  publication-title: Int J Neural Syst
  doi: 10.1142/S0129065708001403
– start-page: 221
  volume-title: Mendel 2015. Advances in intelligent systems and computing
  year: 2015
  ident: 9716_CR37
  doi: 10.1007/978-3-319-19824-8_18
– volume: 49
  start-page: 409
  issue: 6
  year: 1952
  ident: 9716_CR22
  publication-title: J Res Natl Bur Stand
  doi: 10.6028/jres.049.044
– volume: 4
  start-page: 141
  issue: 2
  year: 1992
  ident: 9716_CR6
  publication-title: Neural Comput
  doi: 10.1162/neco.1992.4.2.141
– volume: 57
  start-page: 1316
  issue: 4
  year: 2009
  ident: 9716_CR49
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2008.2010600
– ident: 9716_CR52
  doi: 10.1109/IJCNN.2010.5596690
– volume: 3
  start-page: 561
  issue: 5
  year: 1990
  ident: 9716_CR48
  publication-title: Neural Netw
  doi: 10.1016/0893-6080(90)90006-7
– volume: 53
  start-page: 1827
  issue: 5
  year: 2005
  ident: 9716_CR18
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2005.845462
– ident: 9716_CR4
  doi: 10.1007/BFb0047683
– volume: 18
  start-page: 1511
  issue: 5
  year: 2007
  ident: 9716_CR20
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/TNN.2007.895828
– volume: 26
  start-page: 663
  issue: 4
  year: 2015
  ident: 9716_CR57
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2014.2320715
– volume: 23
  start-page: 426
  issue: 3
  year: 2010
  ident: 9716_CR12
  publication-title: Neural Netw
  doi: 10.1016/j.neunet.2009.10.006
– volume: 2017
  start-page: 362
  year: 2017
  ident: 9716_CR41
  publication-title: Adv Comput Intell IWANN
  doi: 10.1007/978-3-319-59153-7_32
– volume: 16
  start-page: 265
  issue: 3
  year: 1994
  ident: 9716_CR45
  publication-title: Comput Stand Interfaces
  doi: 10.1016/0920-5489(94)90017-5
– volume: 24
  start-page: 647
  issue: 111
  year: 1970
  ident: 9716_CR47
  publication-title: Math Comput
  doi: 10.1090/S0025-5718-1970-0274029-X
– ident: 9716_CR27
– volume: 58
  start-page: 3895
  issue: 7
  year: 2010
  ident: 9716_CR50
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2010.2047719
– ident: 9716_CR10
– volume: 2016
  start-page: 243
  year: 2016
  ident: 9716_CR39
  publication-title: Neural Inf Process ICONIP
  doi: 10.1007/978-3-319-46675-0_27
– ident: 9716_CR38
  doi: 10.1109/SYNASC.2016.050
– volume-title: Recurrent neural networks for prediction: learning algorithms, architectures and stability
  year: 2001
  ident: 9716_CR29
  doi: 10.1002/047084535X
– volume: 2
  start-page: 291
  issue: 4
  year: 1991
  ident: 9716_CR26
  publication-title: Int J Neural Syst
  doi: 10.1142/S0129065791000261
– volume: 12
  start-page: 241
  issue: 1
  year: 1977
  ident: 9716_CR43
  publication-title: Math Program
  doi: 10.1007/BF01593790
– volume-title: Neural networks for pattern recognition
  year: 1995
  ident: 9716_CR8
  doi: 10.1093/oso/9780198538493.001.0001
– ident: 9716_CR56
– ident: 9716_CR34
  doi: 10.1109/SYNASC.2014.44
– volume: 7
  start-page: 149
  issue: 2
  year: 1964
  ident: 9716_CR44
  publication-title: Comput J
  doi: 10.1093/comjnl/7.2.149
– volume: 22
  start-page: 74
  issue: 1
  year: 2011
  ident: 9716_CR58
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/TNN.2010.2085444
– volume: 58
  start-page: 4427
  issue: 8
  year: 2010
  ident: 9716_CR51
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2010.2048323
– ident: 9716_CR53
  doi: 10.1109/ICASSP.2009.4960282
– volume: 16
  start-page: 2699
  issue: 12
  year: 2004
  ident: 9716_CR17
  publication-title: Neural Comput
  doi: 10.1162/0899766042321779
– volume-title: Numerical optimization. Springer series in operations research
  year: 1999
  ident: 9716_CR32
  doi: 10.1007/978-0-387-40065-5
– volume: 2015
  start-page: 412
  year: 2015
  ident: 9716_CR35
  publication-title: Neural Inf Process ICONIP
  doi: 10.1007/978-3-319-26535-3_47
– ident: 9716_CR40
  doi: 10.1007/978-3-319-58088-3_17
– ident: 9716_CR15
– volume: 6
  start-page: 163
  issue: 2
  year: 1963
  ident: 9716_CR16
  publication-title: Comput J
  doi: 10.1093/comjnl/6.2.163
– start-page: 39
  volume-title: Numerical methods for nonlinear optimization
  year: 1972
  ident: 9716_CR7
– volume: 22
  start-page: 1193
  issue: 8
  year: 2011
  ident: 9716_CR13
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/TNN.2011.2157358
SSID ssj0010020
Score 2.2553608
Snippet This paper presents the deduction of the enhanced gradient descent, conjugate gradient, scaled conjugate gradient, quasi-Newton, and Levenberg–Marquardt...
SourceID proquest
crossref
springer
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 949
SubjectTerms Algorithms
Approximation
Artificial Intelligence
Artificial neural networks
Back propagation
Calculus
Complex Systems
Computational Intelligence
Computer Science
Conjugate gradient method
Machine learning
Neural networks
Quaternions
Teaching methods
Time series
SummonAdditionalLinks – databaseName: SpringerLINK Contemporary 1997-Present
  dbid: RSV
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8MwDI7Q4MCF8RSDgXrgBIrUrGmbHCfExGniOe1WJU46Jo0NrR2_H6ePVSBAglulpm7lR_y5dmxCLiyLYmYMGhKAppy5K2M0hRCgF6BGM5YWwybi4VCMx_KuOsed1dXudUqy2Kmbw24Yvbjan5i6tkcUQ55N9HbCWePD42idOnAAqIiyYp_yqMfqVOZ3JD47owZhfkmKFr5m0P7XV-6SnQpaev1SF_bIhp3vk3Y9tsGrrPiAyKqn6sTrzyaL5TR_ec08xK7e_Uq534MoKTpSs5U1nmvdgSSHZa14dkieBzdP17e0mqBAIRC9nEIcpBiE-pAaA0JJrREAmoj7AQhhFIIjG2hII3RTOtQMQqsQrkAUSSO4YRAckdZ8MbfHxJNKcK5ZariMuGJWMhMaHvvKd0PMhOwQv2ZlAlV7cTflYpY0jZEdaxJkTeJYk7AOuVw_8lb21vhtcbeWT1KZWZb0JO5IHCNYfP1VLY_m9o_ETv60-pRsI0wSZYFYl7Ty5cqekS14z6fZ8rzQvg8zyNKH
  priority: 102
  providerName: Springer Nature
Title Learning Algorithms for Quaternion-Valued Neural Networks
URI https://link.springer.com/article/10.1007/s11063-017-9716-1
https://www.proquest.com/docview/2918341079
Volume 47
WOSCitedRecordID wos000434268000014&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: 1573-773X
  dateEnd: 20241207
  omitProxy: false
  ssIdentifier: ssj0010020
  issn: 1370-4621
  databaseCode: P5Z
  dateStart: 19970201
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 1573-773X
  dateEnd: 20241207
  omitProxy: false
  ssIdentifier: ssj0010020
  issn: 1370-4621
  databaseCode: K7-
  dateStart: 19970201
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1573-773X
  dateEnd: 20241207
  omitProxy: false
  ssIdentifier: ssj0010020
  issn: 1370-4621
  databaseCode: BENPR
  dateStart: 19970201
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 1573-773X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0010020
  issn: 1370-4621
  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/eLvHCXMwpV1LS8NAEB60evBifWJ9lBw8KYvZZJPsnkSlRRBKrQ_ES0hmkyrUVk3q73c23VgU9OJlCSQZws7s7jePzAdwmPEw4lrTQkJMmeDmSuuUYYDo-WTRnOcV2UTU68mHB9W3AbfCllXWe2K1UesJmhj5iafI-AQ5K-r09Y0Z1iiTXbUUGouwxD2PGzu_ithXFsFgocrhilwmQo_XWc3q1znyhUwlUcRMEyXGv59Lc7D5Iz9aHTvd5n8_eA1WLeB0zmYWsg4L2XgDmjWZg2PX9iYo22l16JyNhiSnfHopHEK0zvU0MUFD0h-7T0bTTDumoQeJ7M0qyIstuOt2bi8umeVVYOhLr2QY-Tm5pi7mWqNMVJoSLNShcH2UUicEmTI_xTykwysNUo5BlhCIwTBUWgrN0d-GxngyznbAUYkUIuW5FioUCc8U14EWkZu4htpMqha49azGaJuOG-6LUTxvl2wUEZMiYqOImLfg6OuV11nHjb8e3q8nP7aLr4jnM9-C41p989u_Ctv9W9gerBBakrM6sX1olO_T7ACW8aN8Lt7bsHTe6fUH7coCaewHjzQObu4_AfXE4JE
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LS8QwEB58gV58i-uzB70owabNtslBRHygrC4KKt5qO0lXYV0f3VX8U_5GJ324KOjNg7dC26HNfJnMZCbzAawZHoRca5pIiAkT3F5pnTCsI3o-IZrzNCebCJtNeX2tzgbgvToLY8sqK5uYG2r9gHaPfMtTBD5BwYraeXxiljXKZlcrCo0CFg3z9kohW7Z9vE_6Xfe8w4OLvSNWsgow9KXXZRj6KQVmLqZao4xVkpBTpAPh-iiljslhMH6CaUCmO6knHOsmpiUcg0BpKTRHn-QOwrDwZWh79TdC9pm1sL5XHuCFLhOBx6ssan5Uj2IvW7kUMtu0ifGv62Dfuf2Wj82XucOJ_zZAkzBeOtTObjEDpmDAdKZhoiKrcErbNQOq7CTbcnbbLfru7u195pDH7pz3YrspSvhkV3G7Z7RjG5aQyGZRIZ_NwuWf_MAcDHUeOmYeHBVLIRKeaqECEXOjuK5rEbqxa6nbpKqBW2kxwrKpuuX2aEf9dtBW8REpPrKKj3gNNj5feSw6ivz28FKl7Kg0LlnU13QNNiu49G__KGzhd2GrMHp0cXoSnRw3G4swRp6hLGrilmCo-9wzyzCCL9277HklR70DN3-Nog-UyTtH
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1dS8MwFA2iIr44P3E6tQ8-KWFNm7XJ41CHopSJOvYWmqSdg9mNtfP3e9OPFUUF8a3QNC03N825uTfnIHQeEc8nWsNEUkpiSsyV1hKrjlKOCx5NSJyLTfhBwIZD3i91TtOq2r1KSRZnGgxLU5K1Zzpu1wffIJIxdUA-NhRIGMKfNWo0g0y4_jRYphEMGMojLt_G1HNIldb8rovPC1ONNr8kSPN1p9f49xdvo60Sclrdwkd20EqU7KJGJedglbN7D_GSa3VkdSej6Xycvb6lFmBa63ERmm1DGEE8CCeLSFuG0gO6DIoa8nQfvfRunq9ucamsgJXLnAwr340hOLVVrLViIZcSgKH2qO0qxnQIoClypYo9WL5kRxLViUKAMcrzuGZUE-UeoNVkmkSHyOIho1SSWFPu0ZBEnOiOpr4d2kbcjPEmsiuzClXSjhv1i4moCZONaQSYRhjTCNJEF8tHZgXnxm-NW9VYiXL6pcLh8KcCh_Dh9ZfV2NS3f-zs6E-tz9BG_7onHu6C-2O0CUiKFTVkLbSazRfRCVpX79k4nZ_mTvkBhz7eTw
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=Learning+Algorithms+for+Quaternion-Valued+Neural+Networks&rft.jtitle=Neural+processing+letters&rft.date=2018-06-01&rft.pub=Springer+Nature+B.V&rft.issn=1370-4621&rft.eissn=1573-773X&rft.volume=47&rft.issue=3&rft.spage=949&rft.epage=973&rft_id=info:doi/10.1007%2Fs11063-017-9716-1
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1370-4621&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1370-4621&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1370-4621&client=summon