Complex-Valued Neural Networks: A Comprehensive Survey

Complex-valued neural networks (CVNNs) have shown their excellent efficiency compared to their real counter-parts in speech enhancement, image and signal processing. Researchers throughout the years have made many efforts to improve the learning algorithms and activation functions of CVNNs. Since CV...

Full description

Saved in:
Bibliographic Details
Published in:IEEE/CAA journal of automatica sinica Vol. 9; no. 8; pp. 1406 - 1426
Main Authors: Lee, ChiYan, Hasegawa, Hideyuki, Gao, Shangce
Format: Journal Article
Language:English
Published: Piscataway Chinese Association of Automation (CAA) 01.08.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Faculty of Engineering,University of Toyama,Toyama 930-8555,Japan
Subjects:
Algorithms
Complex activation function
complex backpropagation algorithm
complex-valued learning algorithm
complex-valued neural network
deep learning
Image enhancement
Image segmentation
Machine learning
Magnetic resonance imaging
Neural networks
Pattern classification
Recurrent neural networks
Signal processing
Signal processing algorithms
Speech enhancement
Speech processing
Wind forecasting
Complex activation function
complex-valued neural network
deep learning
complex backpro-pagation algorithm
complex-valued learning algorithm
ISSN:2329-9266, 2329-9274
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Complex-valued neural networks (CVNNs) have shown their excellent efficiency compared to their real counter-parts in speech enhancement, image and signal processing. Researchers throughout the years have made many efforts to improve the learning algorithms and activation functions of CVNNs. Since CVNNs have proven to have better performance in handling the naturally complex-valued data and signals, this area of study will grow and expect the arrival of some effective improvements in the future. Therefore, there exists an obvious reason to provide a comprehensive survey paper that systematically collects and categorizes the advancement of CVNNs. In this paper, we discuss and summarize the recent advances based on their learning algorithms, activation functions, which is the most challenging part of building a CVNN, and applications. Besides, we outline the structure and applications of complex-valued convolutional, residual and recurrent neural networks. Finally, we also present some challenges and future research directions to facilitate the exploration of the ability of CVNNs.
AbstractList Complex-valued neural networks(CVNNs)have shown their excellent efficiency compared to their real counter-parts in speech enhancement,image and signal processing.Researchers throughout the years have made many efforts to improve the learning algorithms and activation functions of CVNNs.Since CVNNs have proven to have better performance in handling the naturally complex-valued data and signals,this area of study will grow and expect the arrival of some effective improvements in the future.Therefore,there exists an obvious reason to provide a comprehensive survey paper that systemati-cally collects and categorizes the advancement of CVNNs.In this paper,we discuss and summarize the recent advances based on their learning algorithms,activation functions,which is the most challenging part of building a CVNN,and applications.Besides,we outline the structure and applications of complex-valued convolutional,residual and recurrent neural networks.Finally,we also present some challenges and future research directions to facilitate the exploration of the ability of CVNNs.
Complex-valued neural networks (CVNNs) have shown their excellent efficiency compared to their real counter-parts in speech enhancement, image and signal processing. Researchers throughout the years have made many efforts to improve the learning algorithms and activation functions of CVNNs. Since CVNNs have proven to have better performance in handling the naturally complex-valued data and signals, this area of study will grow and expect the arrival of some effective improvements in the future. Therefore, there exists an obvious reason to provide a comprehensive survey paper that systematically collects and categorizes the advancement of CVNNs. In this paper, we discuss and summarize the recent advances based on their learning algorithms, activation functions, which is the most challenging part of building a CVNN, and applications. Besides, we outline the structure and applications of complex-valued convolutional, residual and recurrent neural networks. Finally, we also present some challenges and future research directions to facilitate the exploration of the ability of CVNNs.
Author Hasegawa, Hideyuki
Lee, ChiYan
Gao, Shangce
AuthorAffiliation Faculty of Engineering,University of Toyama,Toyama 930-8555,Japan
AuthorAffiliation_xml – name: Faculty of Engineering,University of Toyama,Toyama 930-8555,Japan
Author_xml – sequence: 1
  givenname: ChiYan
  surname: Lee
  fullname: Lee, ChiYan
  email: leechiyan1610@gmail.com
  organization: Faculty of Engineering, University of Toyama,Toyama,Japan,930-8555
– sequence: 2
  givenname: Hideyuki
  surname: Hasegawa
  fullname: Hasegawa, Hideyuki
  email: hasegawa@eng.u-toyama.ac.jp
  organization: Faculty of Engineering, University of Toyama,Toyama,Japan,930-8555
– sequence: 3
  givenname: Shangce
  surname: Gao
  fullname: Gao, Shangce
  email: gaosc@eng.u-toyama.ac.jp
  organization: Faculty of Engineering, University of Toyama,Toyama,Japan,930-8555
BookMark eNp9kEtLw0AUhQepYK1du3ATcCeknWfScVeKT4ouqm6HyfTGpqZJnUn68Nc7IVLBhatzuXznHu45RZ2iLAChc4IHhGA5fBzPBhRTOiBYxJwdoS5lVIaSxrxzmKPoBPWdW2KMCRVxJHkXRZNytc5hF77pvIZ58AS11bmXalvaD3cdjIOGsLCAwmUbCGa13cD-DB2nOnfQ_9Eeer29eZnch9Pnu4fJeBoaRnkVak0klkLyNI6xYYKIKMGplqPUb82IcQ4MGDPEjwkQ4HOKDQgwRDKuk5T10FV7d6uLVBfvalnWtvCJ6mu-2CVqv02at_EIY-7hyxZe2_KzBlf90jSSsYgYI9RTw5YytnTOQqrWNltpu1cEq6ZM5ctUzVXVlukd4o_DZJWusrKorM7yf3wXrS8DgEOKHHFJIsq-AaRcgIQ
CODEN IJASJC
CitedBy_id crossref_primary_10_1109_JAS_2023_123387
crossref_primary_10_3390_app15031603
crossref_primary_10_1109_TCE_2024_3515877
crossref_primary_10_1007_s00365_025_09713_8
crossref_primary_10_1038_s41467_024_55321_8
crossref_primary_10_1109_TAES_2024_3443020
crossref_primary_10_1142_S0129183126500294
crossref_primary_10_3390_s25144393
crossref_primary_10_1109_LWC_2023_3309479
crossref_primary_10_1587_nolta_14_175
crossref_primary_10_1016_j_engappai_2024_108352
crossref_primary_10_1109_TSMC_2024_3371164
crossref_primary_10_1109_TNNLS_2024_3384314
crossref_primary_10_1038_s41598_023_40080_1
crossref_primary_10_1109_JLT_2024_3461734
crossref_primary_10_14529_mmp250108
crossref_primary_10_3389_fenvs_2025_1640840
crossref_primary_10_3390_photonics11050431
crossref_primary_10_1016_j_optlaseng_2024_108685
crossref_primary_10_1103_PhysRevResearch_7_013164
crossref_primary_10_1109_JAS_2023_123474
crossref_primary_10_1109_LWC_2024_3476137
crossref_primary_10_1109_TCSII_2024_3486746
crossref_primary_10_1016_j_compbiomed_2025_110691
crossref_primary_10_1016_j_chaos_2023_114432
crossref_primary_10_1016_j_ecosta_2024_06_003
crossref_primary_10_1109_ACCESS_2024_3461572
crossref_primary_10_1109_TCSI_2024_3462806
crossref_primary_10_1109_TNNLS_2023_3282231
crossref_primary_10_3788_COL202523_090501
crossref_primary_10_3390_rs15215085
crossref_primary_10_1109_TMTT_2023_3319835
crossref_primary_10_1121_10_0036384
crossref_primary_10_1002_mp_17909
crossref_primary_10_1016_j_neucom_2023_126358
crossref_primary_10_1109_TAES_2024_3353725
crossref_primary_10_3389_frai_2024_1353873
crossref_primary_10_1016_j_neunet_2025_107375
crossref_primary_10_1016_j_cma_2024_117406
crossref_primary_10_1016_j_engappai_2025_111601
crossref_primary_10_1016_j_neunet_2024_106664
crossref_primary_10_3390_app15126599
crossref_primary_10_1109_JIOT_2022_3228748
crossref_primary_10_1109_TAES_2024_3382222
crossref_primary_10_1109_JAS_2024_124335
crossref_primary_10_3390_s25082489
crossref_primary_10_1007_s10462_025_11123_y
crossref_primary_10_1109_ACCESS_2024_3514781
crossref_primary_10_1109_JSTQE_2024_3493857
crossref_primary_10_1002_asjc_3631
crossref_primary_10_1109_TASLP_2024_3444492
crossref_primary_10_3390_electronics14101959
crossref_primary_10_1109_LCSYS_2025_3604015
crossref_primary_10_3390_stats8010020
crossref_primary_10_1109_LGRS_2024_3411554
crossref_primary_10_1364_AO_545152
crossref_primary_10_1016_j_asoc_2024_112682
crossref_primary_10_3390_app15169179
crossref_primary_10_3390_s25020353
crossref_primary_10_1016_j_neucom_2025_129412
crossref_primary_10_1109_JSEN_2025_3525674
crossref_primary_10_1098_rsta_2024_0169
crossref_primary_10_1186_s13636_024_00337_7
crossref_primary_10_1007_s11280_023_01210_x
crossref_primary_10_1007_s44439_025_00002_7
crossref_primary_10_1109_ACCESS_2023_3280454
crossref_primary_10_1109_JAS_2023_124026
crossref_primary_10_3390_electronics12204380
crossref_primary_10_1007_s12204_024_2778_0
crossref_primary_10_1038_s41598_025_14872_6
crossref_primary_10_1109_ACCESS_2025_3535472
crossref_primary_10_1109_TSMC_2024_3490183
crossref_primary_10_1121_10_0028230
crossref_primary_10_1016_j_knosys_2023_110788
crossref_primary_10_1002_ett_70148
crossref_primary_10_1117_1_JRS_19_026504
crossref_primary_10_1109_TIM_2025_3608349
crossref_primary_10_1007_s11571_024_10129_6
crossref_primary_10_1109_TSMC_2024_3387408
crossref_primary_10_1140_epjs_s11734_024_01372_3
crossref_primary_10_1364_AO_545150
crossref_primary_10_1088_1361_6560_ad0997
crossref_primary_10_1093_gji_ggaf348
crossref_primary_10_1007_s11063_024_11472_9
crossref_primary_10_1109_JSTARS_2025_3593845
crossref_primary_10_1016_j_asoc_2023_110306
crossref_primary_10_1007_s00521_024_10368_y
crossref_primary_10_1109_TCSS_2023_3335485
crossref_primary_10_3390_jimaging11080286
crossref_primary_10_3390_math11071701
crossref_primary_10_1109_JSTARS_2023_3292315
crossref_primary_10_1016_j_eswa_2025_128893
crossref_primary_10_1109_JAS_2023_123489
crossref_primary_10_1109_MSP_2024_3389496
Cites_doi 10.1109/JAS.2021.1004018
10.1049/el:19921186
10.1109/JAS.2019.1911732
10.1109/ICASSP.2018.8462556
10.21437/Interspeech.2017-584
10.1109/JAS.2021.1004174
10.1016/j.neucom.2012.08.010
10.1109/ICSMC.2010.5642294
10.1587/transinf.E96.D.2257
10.1109/IJCNN.2012.6252535
10.1109/RadarConf2147009.2021.9455169
10.1117/12.145076
10.1109/TNN.2002.1000133
10.1109/JAS.2021.1003817
10.1109/IGARSS.2019.8898217
10.1016/j.neucom.2008.04.006
10.1109/ACCESS.2015.2506601
10.1109/ACCESS.2019.2924548
10.1016/S0893-6080(03)00138-2
10.1007/978-3-319-25393-0_49
10.1109/ICSMC.2006.384789
10.3906/elk-1408-157
10.1109/TNNLS.2020.2977614
10.1109/JAS.2021.1004027
10.1109/FSKD.2017.8393327
10.1109/ICACI.2016.7449840
10.1109/JAS.2020.1003048
10.1016/j.cmpb.2016.01.001
10.3390/rs11050522
10.1109/TNSE.2020.3048902
10.1109/TSP.2013.6614053
10.1109/CVPR.2016.90
10.1260/2040-2295.6.3.281
10.1109/JAS.2021.1004084
10.1109/JAS.2020.1003114
10.1016/j.neunet.2019.09.036
10.23919/APSIPA.2018.8659610
10.1109/78.127967
10.1109/ICSMC.1998.727520
10.1109/LGRS.2019.2953892
10.1162/NECO_a_00729
10.1109/TNNLS.2017.2770172
10.3906/elk-0908-137
10.1109/NNSP.2000.889414
10.1109/TNNLS.2013.2294638
10.1007/978-3-319-92537-0_8
10.1109/72.728394
10.1109/GlobalSIP.2016.7905999
10.1109/IJCNN.1992.227274
10.1016/j.neucom.2014.04.075
10.1007/978-3-642-24955-6_65
10.1109/WNYIPW.2019.8923089
10.3390/electronics10060752
10.1109/ICoAC.2013.6921958
10.1016/j.neunet.2013.01.008
10.1016/j.neucom.2005.03.002
10.1109/TBME.2018.2883085
10.1504/IJBET.2014.064651
10.1109/JAS.2020.1003539
10.1109/JAS.2021.1003871
10.1016/j.patrec.2019.08.021
10.1007/s00521-018-3920-4
10.1109/SEST.2018.8495637
10.4018/978-1-60566-214-5
10.1109/tnnls.2021.3105901
10.1109/TNNLS.2019.2955567
10.1109/IJCNN.2009.5178754
10.23919/SICE.2018.8492660
10.1109/SSCI.2018.8628865
10.1186/s12859-016-1209-0
10.1109/JAS.2020.1003390
10.1109/TNN.2007.894038
10.1109/JAS.2019.1911825
10.1016/j.neunet.2016.11.001
10.1007/s11071-018-4053-0
10.1007/s11063-014-9379-0
10.1109/tgrs.2020.3047112
10.1109/JAS.2021.1003982
10.1162/isal_a_00406
10.1109/TNN.2011.2144618
10.1109/PROC.1975.9807
10.1109/ITSC45102.2020.9294335
10.1007/s11517-017-1721-z
10.1109/IJCNN.2011.6033400
10.1109/IGARSS47720.2021.9554116
10.1007/s00500-018-3216-8
10.1007/s11071-015-2147-5
10.1007/s11063-017-9621-7
10.1016/j.neucom.2019.06.112
10.1109/JAS.2020.1003090
10.1007/978-3-642-24955-6_66
10.1109/ICIP.2017.8297024
10.1016/j.neucom.2019.10.064
10.1016/j.mri.2020.02.002
10.1109/IJCNN.2015.7280450
10.1007/978-3-319-92537-0_9
10.5772/13295
10.1007/s11063-016-9537-7
10.1109/JAS.2020.1003462
10.1142/S0129065795000299
10.1109/ICoICT.2015.7231422
10.1038/s41467-020-20719-7
10.1016/j.neunet.2020.01.011
10.1109/IJCNN48605.2020.9207122
10.1016/j.neucom.2009.06.004
10.3103/S1060992X1201002X
10.1016/j.neunet.2018.01.016
10.1016/j.cmpb.2018.07.015
10.1109/IMFEDK48381.2019.8950700
10.1109/TSMC.2019.2901277
10.1109/SYNASC.2014.44
10.1109/TGRS.2019.2917214
10.1016/j.neucom.2020.04.114
10.1007/978-3-642-20353-4
10.1016/j.neucom.2009.05.017
10.1162/neco_a_00990
10.1109/SIPROCESS.2019.8868708
10.1007/978-3-319-24574-4_28
10.1109/TSMC.2021.3055501
10.1109/TNNLS.2012.2195028
10.1109/IJCNN.2011.6033384
10.1016/j.renene.2017.01.019
10.1162/NECO_a_00254
10.1007/978-3-642-27632-3
10.1109/JAS.2021.1004045
10.1109/78.134446
10.1016/S0893-6080(97)00036-1
10.1109/TNN.2004.839354
10.1016/j.amc.2013.12.027
10.1007/978-3-030-00129-2_4
10.1162/089976603321891846
10.21437/Interspeech.2016-300
10.1109/ICoAC.2012.6416850
10.1109/JAS.2020.1003402
10.1109/ACCESS.2020.3004591
10.1007/978-3-642-13232-2_6
10.1016/j.neunet.2019.02.006
10.1109/ICASSP.1991.150526
10.1016/j.isprsjprs.2019.09.002
10.1109/TCYB.2018.2838573
10.1142/s0129065700000090
10.1109/ECCE.2012.6342351
10.1016/j.patcog.2017.10.013
10.1038/nature14539
10.1109/SIU.2010.5650970
10.1109/TGRS.2017.2743222
10.1109/JAS.2020.1003393
10.1109/TGRS.2020.2976694
10.1109/ISCAS45731.2020.9181225
10.1109/82.142037
10.1016/j.neunet.2019.09.032
10.1109/JAS.2021.1004141
10.3115/v1/d14-1179
10.1016/j.ins.2011.11.003
10.1109/WNYIPW.2017.8356260
10.1109/LGRS.2018.2866567
10.1109/ASET.2018.8379880
10.1175/1520-0477(1996)077<0437:TNYRP>2.0.CO;2
10.4103/2228-7477.112144
10.1109/TMI.2016.2548501
10.1142/9789812791184_0010
10.1109/JAS.2021.1004051
10.1109/TAC.2017.2669580
10.1016/S0893-6080(97)00118-4
10.1007/s10916-008-9205-1
10.1109/JAS.2020.1003465
10.1109/TNNLS.2020.3030565
10.1109/ISCAS.2010.5537907
10.1109/TNNLS.2015.2494361
10.1016/j.neucom.2007.07.037
10.1109/TNNLS.2013.2288943
10.1016/j.neucom.2020.01.020
10.1109/ACCESS.2019.2938896
10.1109/JBHI.2014.2387795
10.1007/s11460-011-0125-3
10.1016/j.neucom.2007.07.025
10.1016/j.neucom.2019.06.051
10.1016/j.jfranklin.2015.11.014
10.1109/IJCNN.2017.7965936
10.1155/2009/329173
10.1016/0031-3203(92)90101-N
10.1162/08997660460734001
10.1007/s00521-015-2142-2
10.21609/jiki.v11i2.617
10.1109/TETCI.2018.2872600
10.1016/S0893-6080(03)00168-0
10.1109/ICII.2001.983106
10.1016/j.neunet.2021.01.014
10.1016/j.renene.2005.07.006
10.1109/DSMP.2018.8478463
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
– notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
7TB
8FD
FR3
JQ2
L7M
L~C
L~D
2B.
4A8
92I
93N
PSX
TCJ
DOI 10.1109/JAS.2022.105743
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Mechanical & Transportation Engineering Abstracts
Technology Research Database
Engineering Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList

Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2329-9274
EndPage 1426
ExternalDocumentID zdhxb_ywb202208004
10_1109_JAS_2022_105743
9849162
Genre orig-research
GroupedDBID -0I
-0Y
-SI
-S~
0R~
4.4
5VR
6IK
92M
97E
9D9
9DI
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
AFUIB
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CAJEI
EBS
EJD
IFIPE
IPLJI
JAVBF
M43
O9-
OCL
PQQKQ
Q--
RIA
RIE
RT9
T8Y
TCJ
TGT
U1F
U1G
U5I
U5S
AAYXX
CITATION
7SC
7SP
7TB
8FD
FR3
JQ2
L7M
L~C
L~D
2B.
4A8
92I
93N
PSX
R-I
RIG
ID FETCH-LOGICAL-c324t-aa1909594f770c35156b0fa98f095c8344e3e33c1834be1e4d20ce5ec1934abf3
IEDL.DBID RIE
ISICitedReferencesCount 138
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000838825000008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2329-9266
IngestDate Thu May 29 04:10:31 EDT 2025
Sun Sep 07 03:46:31 EDT 2025
Tue Nov 18 21:46:26 EST 2025
Sat Nov 29 03:31:06 EST 2025
Wed Aug 27 02:23:52 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 8
Keywords Complex activation function
complex-valued neural network
deep learning
complex backpro-pagation algorithm
complex-valued learning algorithm
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c324t-aa1909594f770c35156b0fa98f095c8344e3e33c1834be1e4d20ce5ec1934abf3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
PQID 2697563312
PQPubID 2040495
PageCount 21
ParticipantIDs proquest_journals_2697563312
wanfang_journals_zdhxb_ywb202208004
ieee_primary_9849162
crossref_citationtrail_10_1109_JAS_2022_105743
crossref_primary_10_1109_JAS_2022_105743
PublicationCentury 2000
PublicationDate 2022-08-01
PublicationDateYYYYMMDD 2022-08-01
PublicationDate_xml – month: 08
  year: 2022
  text: 2022-08-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE/CAA journal of automatica sinica
PublicationTitleAbbrev JAS
PublicationTitle_FL IEEE/CAA Journal of Automatica Sinica
PublicationYear 2022
Publisher Chinese Association of Automation (CAA)
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Faculty of Engineering,University of Toyama,Toyama 930-8555,Japan
Publisher_xml – name: Chinese Association of Automation (CAA)
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
– name: Faculty of Engineering,University of Toyama,Toyama 930-8555,Japan
References ref57
ref207
ref56
ref208
ref59
ref205
ref58
ref206
ref53
Olanrewaju (ref193) 2011; 5
ref203
ref52
ref204
ref55
ref201
ref54
ref202
ref209
Diamond (ref159) 2017
ref210
ref211
ref51
ref50
ref46
ref218
ref45
ref219
ref48
ref216
ref217
ref42
ref214
ref41
ref215
ref212
ref43
ref213
Zimmermann (ref44) 2011
ref49
Kumar (ref139) 2020; 7
ref8
ref7
Reichert (ref19) 2014
ref9
ref4
ref3
ref6
ref5
ref100
ref221
ref220
ref35
ref34
ref37
ref31
ref30
ref32
Mochida (ref68) 2017; 117
ref39
ref38
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
ref200
Wang (ref119)
ref128
ref129
Arjovsky (ref36) 2016; 48
ref97
ref126
ref96
ref127
ref99
ref124
ref98
Bassey (ref14) 2021; abs/2101.12249
ref93
ref133
ref92
ref95
ref131
ref132
ref130
ref91
Yeats (ref47) 2021
ref137
ref85
ref138
ref88
ref87
ref136
Kiziltas (ref142) 2019; 3
ref82
ref144
ref145
ref83
ref143
ref140
ref141
ref79
ref108
Wisdom (ref118); 29
ref78
ref109
Kitajima (ref173) 2010
ref106
ref107
ref75
ref104
ref74
ref105
ref77
ref102
ref76
ref103
Choi (ref101) 2019
Virtue (ref94) 2019
ref71
Trabelsi (ref81) 2018
ref70
ref112
ref73
ref72
ref110
Ji (ref188) 2017
ref67
Inturrisi (ref196) 2021
ref117
ref64
ref115
ref63
ref116
ref66
ref113
ref65
ref114
Cole (ref89)
ref60
ref122
ref123
ref62
ref120
ref61
ref121
ref168
ref169
Guberman (ref33) 2016
LeCun (ref86) 1995
ref170
Jing (ref134) 2017; 70
Jalab (ref40) 2011; 6
ref177
ref178
ref175
ref176
ref174
ref171
ref172
ref179
Wolter (ref135); 31
ref180
ref181
ref189
ref186
ref187
ref184
ref185
ref182
ref183
ref148
ref149
ref146
ref147
Isaacson (ref69) 2006
Agostinelli (ref195) 2015
ref155
ref156
ref153
ref154
ref151
ref152
ref150
ref157
ref158
ref166
ref164
ref165
ref162
ref163
ref160
ref161
ref13
ref12
ref15
ref11
ref10
ref17
ref16
ref18
Vasudeva (ref125) 2020
Sarroff (ref111) 2015
Mönning (ref80) 2018
ref2
ref1
Aizenberg (ref167) 2011; 353
ref191
ref192
ref190
ref199
ref197
ref198
ref194
LeCun (ref84); 2
Danihelka (ref90) 2016; 48
References_xml – ident: ref211
  doi: 10.1109/JAS.2021.1004018
– ident: ref37
  doi: 10.1049/el:19921186
– ident: ref63
  doi: 10.1109/JAS.2019.1911732
– ident: ref115
  doi: 10.1109/ICASSP.2018.8462556
– ident: ref123
  doi: 10.21437/Interspeech.2017-584
– ident: ref201
  doi: 10.1109/JAS.2021.1004174
– ident: ref62
  doi: 10.1016/j.neucom.2012.08.010
– ident: ref67
  doi: 10.1109/ICSMC.2010.5642294
– ident: ref5
  doi: 10.1587/transinf.E96.D.2257
– ident: ref191
  doi: 10.1109/IJCNN.2012.6252535
– ident: ref103
  doi: 10.1109/RadarConf2147009.2021.9455169
– ident: ref56
  doi: 10.1117/12.145076
– ident: ref24
  doi: 10.1109/TNN.2002.1000133
– ident: ref198
  doi: 10.1109/JAS.2021.1003817
– ident: ref124
  doi: 10.1109/IGARSS.2019.8898217
– ident: ref25
  doi: 10.1016/j.neucom.2008.04.006
– ident: ref61
  doi: 10.1109/ACCESS.2015.2506601
– ident: ref128
  doi: 10.1109/ACCESS.2019.2924548
– year: 2017
  ident: ref159
  article-title: Unrolled optimization with deep priors
  publication-title: arXiv preprint
– ident: ref52
  doi: 10.1016/S0893-6080(03)00138-2
– year: 2018
  ident: ref80
  article-title: Evaluation of complex-valued neural networks on real-valued classification tasks
  publication-title: arXiv preprint
– ident: ref194
  doi: 10.1007/978-3-319-25393-0_49
– volume: 2
  start-page: 396
  volume-title: Advances in Neural Information Processing Systems
  ident: ref84
  article-title: Handwritten digit recognition with a back-propagation network
– ident: ref65
  doi: 10.1109/ICSMC.2006.384789
– ident: ref145
  doi: 10.3906/elk-1408-157
– ident: ref153
  doi: 10.1109/TNNLS.2020.2977614
– ident: ref202
  doi: 10.1109/JAS.2021.1004027
– ident: ref190
  doi: 10.1109/FSKD.2017.8393327
– ident: ref185
  doi: 10.1109/ICACI.2016.7449840
– ident: ref205
  doi: 10.1109/JAS.2020.1003048
– ident: ref146
  doi: 10.1016/j.cmpb.2016.01.001
– ident: ref151
  doi: 10.3390/rs11050522
– ident: ref210
  doi: 10.1109/TNSE.2020.3048902
– ident: ref155
  doi: 10.1109/TSP.2013.6614053
– ident: ref138
  doi: 10.1109/CVPR.2016.90
– ident: ref26
  doi: 10.1260/2040-2295.6.3.281
– ident: ref219
  doi: 10.1109/JAS.2021.1004084
– ident: ref218
  doi: 10.1109/JAS.2020.1003114
– ident: ref206
  doi: 10.1016/j.neunet.2019.09.036
– start-page: 1231
  volume-title: Proc. IEEE 29th Chinese Control And Decision Conf.
  year: 2017
  ident: ref188
  article-title: Prediction of soil moisture with complex-valued neural network
– ident: ref169
  doi: 10.23919/APSIPA.2018.8659610
– ident: ref1
  doi: 10.1109/78.127967
– ident: ref113
  doi: 10.1109/ICSMC.1998.727520
– ident: ref102
  doi: 10.1109/LGRS.2019.2953892
– ident: ref49
  doi: 10.1162/NECO_a_00729
– ident: ref220
  doi: 10.1109/TNNLS.2017.2770172
– ident: ref154
  doi: 10.3906/elk-0908-137
– volume-title: Proc. 2nd Int. Conf. Learning Representations
  year: 2014
  ident: ref19
  article-title: Neuronal synchrony in complex-valued deep networks
– ident: ref32
  doi: 10.1109/NNSP.2000.889414
– volume-title: Proc. Int. Conf. Learning Representations
  year: 2019
  ident: ref101
  article-title: Phase-aware speech enhancement with deep complex U-Net
– ident: ref110
  doi: 10.1109/TNNLS.2013.2294638
– ident: ref127
  doi: 10.1007/978-3-319-92537-0_8
– year: 2016
  ident: ref33
  article-title: On complex valued convolutional neural networks
  publication-title: arXiv preprint
– ident: ref38
  doi: 10.1109/72.728394
– ident: ref96
  doi: 10.1109/GlobalSIP.2016.7905999
– ident: ref27
  doi: 10.1109/IJCNN.1992.227274
– ident: ref60
  doi: 10.1016/j.neucom.2014.04.075
– ident: ref149
  doi: 10.1007/978-3-642-24955-6_65
– ident: ref164
  doi: 10.1109/WNYIPW.2019.8923089
– ident: ref140
  doi: 10.3390/electronics10060752
– ident: ref171
  doi: 10.1109/ICoAC.2013.6921958
– ident: ref161
  doi: 10.1016/j.neunet.2013.01.008
– volume: 48
  start-page: 1986
  volume-title: Proc. 33rd Int. Conf. Machine Learning
  year: 2016
  ident: ref90
  article-title: Associative long short-term memory
– ident: ref30
  doi: 10.1016/j.neucom.2005.03.002
– ident: ref168
  doi: 10.1109/TBME.2018.2883085
– ident: ref156
  doi: 10.1504/IJBET.2014.064651
– ident: ref203
  doi: 10.1109/JAS.2020.1003539
– ident: ref217
  doi: 10.1109/JAS.2021.1003871
– ident: ref137
  doi: 10.1016/j.patrec.2019.08.021
– start-page: 39
  year: 2006
  ident: ref69
  article-title: Metacognitive knowledge monitoring and self-regulated learning
  publication-title: Journal of the Scholarship of Teaching and Learning
– ident: ref162
  doi: 10.1007/s00521-018-3920-4
– ident: ref174
  doi: 10.1109/SEST.2018.8495637
– ident: ref43
  doi: 10.4018/978-1-60566-214-5
– ident: ref144
  doi: 10.1109/tnnls.2021.3105901
– ident: ref215
  doi: 10.1109/TNNLS.2019.2955567
– ident: ref9
  doi: 10.1109/IJCNN.2009.5178754
– ident: ref34
  doi: 10.23919/SICE.2018.8492660
– ident: ref132
  doi: 10.1109/SSCI.2018.8628865
– volume-title: Complex-valued deep learning with applications to magnetic resonance image synthesis
  year: 2019
  ident: ref94
– ident: ref189
  doi: 10.1186/s12859-016-1209-0
– ident: ref208
  doi: 10.1109/JAS.2020.1003390
– ident: ref21
  doi: 10.1109/TNN.2007.894038
– ident: ref87
  doi: 10.1109/JAS.2019.1911825
– ident: ref186
  doi: 10.1016/j.neunet.2016.11.001
– ident: ref187
  doi: 10.1007/s11071-018-4053-0
– ident: ref8
  doi: 10.1007/s11063-014-9379-0
– ident: ref105
  doi: 10.1109/tgrs.2020.3047112
– ident: ref204
  doi: 10.1109/JAS.2021.1003982
– ident: ref207
  doi: 10.1162/isal_a_00406
– ident: ref71
  doi: 10.1109/TNN.2011.2144618
– ident: ref35
  doi: 10.1109/PROC.1975.9807
– ident: ref152
  doi: 10.1109/ITSC45102.2020.9294335
– ident: ref157
  doi: 10.1007/s11517-017-1721-z
– ident: ref17
  doi: 10.1109/IJCNN.2011.6033400
– ident: ref104
  doi: 10.1109/IGARSS47720.2021.9554116
– ident: ref45
  doi: 10.1007/s00500-018-3216-8
– volume-title: Proc. ESANN
  year: 2011
  ident: ref44
  article-title: Comparison of the complex valued and real valued neural networks trained with gradient descent and random search algorithms
– ident: ref181
  doi: 10.1007/s11071-015-2147-5
– ident: ref55
  doi: 10.1007/s11063-017-9621-7
– ident: ref199
  doi: 10.1016/j.neucom.2019.06.112
– ident: ref209
  doi: 10.1109/JAS.2020.1003090
– year: 2021
  ident: ref196
  article-title: Piecewise linear units improve deep neural networks
  publication-title: arXiv preprint
– ident: ref57
  doi: 10.1007/978-3-642-24955-6_66
– ident: ref4
  doi: 10.1109/ICIP.2017.8297024
– ident: ref136
  doi: 10.1016/j.neucom.2019.10.064
– ident: ref93
  doi: 10.1016/j.mri.2020.02.002
– ident: ref54
  doi: 10.1109/IJCNN.2015.7280450
– ident: ref122
  doi: 10.1007/978-3-319-92537-0_9
– ident: ref66
  doi: 10.5772/13295
– ident: ref163
  doi: 10.1007/s11063-016-9537-7
– ident: ref200
  doi: 10.1109/JAS.2020.1003462
– ident: ref16
  doi: 10.1142/S0129065795000299
– ident: ref148
  doi: 10.1109/ICoICT.2015.7231422
– ident: ref143
  doi: 10.1038/s41467-020-20719-7
– ident: ref74
  doi: 10.1016/j.neunet.2020.01.011
– ident: ref106
  doi: 10.1109/IJCNN48605.2020.9207122
– ident: ref20
  doi: 10.1016/j.neucom.2009.06.004
– ident: ref192
  doi: 10.3103/S1060992X1201002X
– start-page: 3610
  volume-title: Proc. IEEE SICE Annu. Conf.
  year: 2010
  ident: ref173
  article-title: Output prediction of wind power generation system using complex-valued neural network
– ident: ref76
  doi: 10.1016/j.neunet.2018.01.016
– ident: ref95
  doi: 10.1016/j.cmpb.2018.07.015
– volume: 70
  start-page: 1733
  volume-title: Proc. 34th Int. Conf. Machine Learning
  year: 2017
  ident: ref134
  article-title: Tunable efficient unitary neural networks (EUNN) and their application to RNN
– year: 2015
  ident: ref111
  article-title: Learning representations using complex-valued nets
  publication-title: arXiv preprint
– volume-title: Proc. Int. Conf. Learning Representations
  year: 2015
  ident: ref195
  article-title: Learning activation functions to improve deep neural networks
– ident: ref160
  doi: 10.1109/IMFEDK48381.2019.8950700
– ident: ref178
  doi: 10.1109/TSMC.2019.2901277
– volume: 48
  start-page: 1120
  volume-title: Proc. 33rd Int. Conf. Machine Learning, ser. Proc. Machine Learning Research
  year: 2016
  ident: ref36
  article-title: Unitary evolution recurrent neural networks
– ident: ref50
  doi: 10.1109/SYNASC.2014.44
– ident: ref15
  doi: 10.1109/TGRS.2019.2917214
– ident: ref53
  doi: 10.1016/j.neucom.2020.04.114
– volume: 117
  start-page: 1
  issue: 112
  year: 2017
  ident: ref68
  article-title: A complex-valued reinforcement learning method using complex-valued neural networks
  publication-title: IEICE Technical Report
– volume: 353
  volume-title: Complex-Valued Neural Networks With Multi-Valued Neurons
  year: 2011
  ident: ref167
  doi: 10.1007/978-3-642-20353-4
– ident: ref51
  doi: 10.1016/j.neucom.2009.05.017
– ident: ref91
  doi: 10.1162/neco_a_00990
– ident: ref100
  doi: 10.1109/SIPROCESS.2019.8868708
– ident: ref158
  doi: 10.1007/978-3-319-24574-4_28
– ident: ref48
  doi: 10.1109/TSMC.2021.3055501
– ident: ref107
  doi: 10.1109/TNNLS.2012.2195028
– volume-title: Proc. 26th Annu. Meeting of ISMRM
  ident: ref119
  article-title: Complex-valued residual network learning for parallel MR imaging
– ident: ref72
  doi: 10.1109/IJCNN.2011.6033384
– ident: ref6
  doi: 10.1016/j.renene.2017.01.019
– ident: ref70
  doi: 10.1162/NECO_a_00254
– start-page: 11953
  volume-title: Proc. Int. Conf. Machine Learning
  year: 2021
  ident: ref47
  article-title: Improving gradient regularization using complex-valued neural networks
– ident: ref10
  doi: 10.1007/978-3-642-27632-3
– ident: ref213
  doi: 10.1109/JAS.2021.1004045
– ident: ref3
  doi: 10.1109/78.134446
– ident: ref42
  doi: 10.1016/S0893-6080(97)00036-1
– ident: ref176
  doi: 10.1109/TNN.2004.839354
– ident: ref109
  doi: 10.1016/j.amc.2013.12.027
– ident: ref28
  doi: 10.1007/978-3-030-00129-2_4
– ident: ref79
  doi: 10.1162/089976603321891846
– ident: ref170
  doi: 10.21437/Interspeech.2016-300
– ident: ref175
  doi: 10.1109/ICoAC.2012.6416850
– volume: 3
  start-page: 1
  issue: 1
  year: 2019
  ident: ref142
  article-title: Skin segmentation by using complex valued neural network with HSV color spaces
  publication-title: Int. Journal of Multidisciplinary Studies and Innovative Technologies
– ident: ref214
  doi: 10.1109/JAS.2020.1003402
– ident: ref126
  doi: 10.1109/ACCESS.2020.3004591
– ident: ref13
  doi: 10.1007/978-3-642-13232-2_6
– ident: ref182
  doi: 10.1016/j.neunet.2019.02.006
– ident: ref41
  doi: 10.1109/ICASSP.1991.150526
– ident: ref46
  doi: 10.1016/j.isprsjprs.2019.09.002
– volume: 31
  start-page: 10536
  volume-title: Advances in Neural Information Processing Systems
  ident: ref135
  article-title: Complex gated recurrent neural networks
– ident: ref177
  doi: 10.1109/TCYB.2018.2838573
– ident: ref23
  doi: 10.1142/s0129065700000090
– ident: ref112
  doi: 10.1109/ECCE.2012.6342351
– ident: ref129
  doi: 10.1016/j.patcog.2017.10.013
– ident: ref92
  doi: 10.1038/nature14539
– ident: ref150
  doi: 10.1109/SIU.2010.5650970
– ident: ref29
  doi: 10.1109/TGRS.2017.2743222
– ident: ref212
  doi: 10.1109/JAS.2020.1003393
– ident: ref221
  doi: 10.1109/TGRS.2020.2976694
– volume: abs/2101.12249
  year: 2021
  ident: ref14
  article-title: A survey of complex-valued neural networks
  publication-title: ArXiv
– ident: ref120
  doi: 10.1109/ISCAS45731.2020.9181225
– volume: 5
  start-page: 1251
  issue: 7
  year: 2011
  ident: ref193
  article-title: Forgery detection in medical images using complex valued neural network (CVNN)
  publication-title: Australian Journal of Basic and Applied Sciences
– ident: ref2
  doi: 10.1109/82.142037
– ident: ref184
  doi: 10.1016/j.neunet.2019.09.032
– ident: ref64
  doi: 10.1109/JAS.2021.1004141
– ident: ref133
  doi: 10.3115/v1/d14-1179
– ident: ref59
  doi: 10.1016/j.ins.2011.11.003
– ident: ref97
  doi: 10.1109/WNYIPW.2017.8356260
– ident: ref98
  doi: 10.1109/LGRS.2018.2866567
– volume: 6
  start-page: 1766
  issue: 7
  year: 2011
  ident: ref40
  article-title: New activation functions for complex-valued neural network
  publication-title: Int. Journal of Physical Sciences
– year: 2020
  ident: ref125
  article-title: CoVeGAN: Complex-valued generative adversarial network for compressive sensing MR image reconstruction
  publication-title: arXiv preprint
– start-page: 4714
  volume-title: Proc. 27th Annu. Meeting of ISMRM
  ident: ref89
  article-title: Complex-valued convolutional neural networks for MRI reconstruction
– ident: ref179
  doi: 10.1109/ASET.2018.8379880
– ident: ref83
  doi: 10.1175/1520-0477(1996)077<0437:TNYRP>2.0.CO;2
– ident: ref7
  doi: 10.4103/2228-7477.112144
– volume: 29
  start-page: 4880
  volume-title: Advances in Neural Information Processing Systems
  ident: ref118
  article-title: Full-capacity unitary recurrent neural networks
– ident: ref88
  doi: 10.1109/TMI.2016.2548501
– ident: ref114
  doi: 10.1142/9789812791184_0010
– ident: ref131
  doi: 10.1109/JAS.2021.1004051
– ident: ref180
  doi: 10.1109/TAC.2017.2669580
– ident: ref77
  doi: 10.1016/S0893-6080(97)00118-4
– ident: ref39
  doi: 10.1007/s10916-008-9205-1
– ident: ref216
  doi: 10.1109/JAS.2020.1003465
– ident: ref121
  doi: 10.1109/TNNLS.2020.3030565
– ident: ref85
  doi: 10.1109/ISCAS.2010.5537907
– ident: ref197
  doi: 10.1109/TNNLS.2015.2494361
– ident: ref78
  doi: 10.1016/j.neucom.2007.07.037
– ident: ref108
  doi: 10.1109/TNNLS.2013.2288943
– ident: ref141
  doi: 10.1016/j.neucom.2020.01.020
– ident: ref99
  doi: 10.1109/ACCESS.2019.2938896
– ident: ref165
  doi: 10.1109/JBHI.2014.2387795
– ident: ref12
  doi: 10.1007/s11460-011-0125-3
– ident: ref58
  doi: 10.1016/j.neucom.2007.07.025
– ident: ref117
  doi: 10.1016/j.neucom.2019.06.051
– ident: ref183
  doi: 10.1016/j.jfranklin.2015.11.014
– volume: 7
  start-page: 251
  issue: 2
  year: 2020
  ident: ref139
  article-title: Detection of microcalcifications in digital mammogram using curvelet fractal texture features
  publication-title: European Journal of Molecular & Clinical Medicine
– ident: ref130
  doi: 10.1109/IJCNN.2017.7965936
– ident: ref22
  doi: 10.1155/2009/329173
– ident: ref73
  doi: 10.1016/0031-3203(92)90101-N
– ident: ref18
  doi: 10.1162/08997660460734001
– ident: ref172
  doi: 10.1007/s00521-015-2142-2
– ident: ref147
  doi: 10.21609/jiki.v11i2.617
– ident: ref31
  doi: 10.1109/TETCI.2018.2872600
– start-page: 255
  volume-title: The Handbook of Brain Theory and Neural Networks
  year: 1995
  ident: ref86
  article-title: Convolutional networks for images, speech, and time series
– ident: ref11
  doi: 10.1016/S0893-6080(03)00168-0
– volume-title: Proc. Int. Conf. Learning Representations
  year: 2018
  ident: ref81
  article-title: Deep complex networks
– ident: ref116
  doi: 10.1109/ICII.2001.983106
– ident: ref75
  doi: 10.1016/j.neunet.2021.01.014
– ident: ref82
  doi: 10.1016/j.renene.2005.07.006
– ident: ref166
  doi: 10.1109/DSMP.2018.8478463
SSID ssj0001257694
Score 2.6176636
Snippet Complex-valued neural networks (CVNNs) have shown their excellent efficiency compared to their real counter-parts in speech enhancement, image and signal...
Complex-valued neural networks(CVNNs)have shown their excellent efficiency compared to their real counter-parts in speech enhancement,image and signal...
SourceID wanfang
proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1406
SubjectTerms Algorithms
Complex activation function
complex backpropagation algorithm
complex-valued learning algorithm
complex-valued neural network
deep learning
Image enhancement
Image segmentation
Machine learning
Magnetic resonance imaging
Neural networks
Pattern classification
Recurrent neural networks
Signal processing
Signal processing algorithms
Speech enhancement
Speech processing
Wind forecasting
Title Complex-Valued Neural Networks: A Comprehensive Survey
URI https://ieeexplore.ieee.org/document/9849162
https://www.proquest.com/docview/2697563312
https://d.wanfangdata.com.cn/periodical/zdhxb-ywb202208004
Volume 9
WOSCitedRecordID wos000838825000008&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: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 2329-9274
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001257694
  issn: 2329-9266
  databaseCode: RIE
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61KOjBVxWrVRb04MHodpN9xFsRRUSKUJXeljxmrVC20nf99U52t7WCHrwtm0lYJpnMN9nJN4ScRToAT_OIykhzih6CUekpoEYwI0wCvs4Y-F4fw2YzarfFU4lcLO7CAECWfAaX9jH7l296emSPyq5ExBHN4Ia7EoZhfldr6TwFkXNW9xAxgqACHU_B5FN3xdVDo4WxoOdlZW05--GEsqoqPwDm2kSmiUzfljzN3db_vnGbbBaI0mnkS2CHlCDdJRtLPIMVElir78KUvsruCIxjGTmwSzNPAR9cOw3HSvShk6ezO61RfwyzPfJyd_t8c0-LgglUIy4aUinRvQtf8CQMXc0QqgTKTaSIEnyrbUUNYMCYRjPmCurAjedq8EEjiuNSJWyflNNeCgfEsRuoChRXBuMp3zciMpbXRYNnQhlJUyWXcw3GumATt0UtunEWVbgiRpXHVuVxrvIqOV90-MiJNP4WrVi9LsQKlVZJbT5FcWFog9gLROgHjNWx-bSYtu_WT9OZqng2UXZ0i4354e9jH5F1K5Jn9tVIedgfwTFZ1ePh-6B_kq20L4Kgzw4
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB4hoGo50BaoupTSSHDgUC_Z2HmY26oq4rGskHiIm-XHBJBWodoHu_DrO07Cskhw4BbFYysaezzfOONvALYzm2BkRcZ0ZgUjD8GZjgwyJ7mTLsfYlgx8l520282uruTpHPye3oVBxDL5DJv-sfyX7-7syB-V7cpMEJqhDXchFiJqVbe1Zk5UCDuXlQ8JJUgmyfXUXD6tUO4etc8oGoyisrCt4C_cUFlX5QXE_DDWRa6L6xlfs__5fV_5BZZrTBm0q0XwFeawWIGlGabBVUi83fdwwi51b4Qu8Jwc1KVbJYEP9oJ24CX6eFMltAdno_49PqzBxf7f8z8HrC6ZwCwhoyHTmhy8jKXI0zS0nMBKYsJcyyynt9bX1ECOnFsyZGGwhcJFocUYLeE4oU3Ov8F8cVfgdwj8FmoSI4yjiCqOncycZ3axGLlUZ9o1oPmkQWVrPnFf1qKnyrgilIpUrrzKVaXyBuxMO_yrqDTeFl31ep2K1SptwMbTFKna1AYqSmQaJ5y3qHmrnrbn1kd3MzHqYWz86B4di_XXx_4FHw_OTzqqc9g9_gGfvHiV57cB88P-CH_Cor0f3g76m-Wq-w9zedJV
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=Complex-Valued+Neural+Networks%3A+A+Comprehensive+Survey&rft.jtitle=IEEE%2FCAA+journal+of+automatica+sinica&rft.au=Lee%2C+ChiYan&rft.au=Hasegawa%2C+Hideyuki&rft.au=Gao%2C+Shangce&rft.date=2022-08-01&rft.issn=2329-9266&rft.eissn=2329-9274&rft.volume=9&rft.issue=8&rft.spage=1406&rft.epage=1426&rft_id=info:doi/10.1109%2FJAS.2022.105743&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JAS_2022_105743
thumbnail_s http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fzdhxb-ywb%2Fzdhxb-ywb.jpg