A Survey on Evolutionary Neural Architecture Search

Deep neural networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labor-intensive because of the trial-and-error process and also...

Full description

Saved in:
Bibliographic Details
Published inIEEE transaction on neural networks and learning systems Vol. 34; no. 2; pp. 550 - 570
Main Authors Liu, Yuqiao, Sun, Yanan, Xue, Bing, Zhang, Mengjie, Yen, Gary G., Tan, Kay Chen
Format Journal Article
LanguageEnglish
Published United States IEEE 01.02.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Algorithms
Artificial neural networks
Computer architecture
Convolutional neural networks
Deep learning
Design
Evolutionary computation
evolutionary computation (EC)
evolutionary neural architecture search (NAS)
image classification
Neural networks
Optimization
Search problems
Statistics
Online AccessGet full text

Cover

Abstract Deep neural networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labor-intensive because of the trial-and-error process and also not easy to realize due to the rare expertise in practice. Neural architecture search (NAS) is a type of technology that can design the architectures automatically. Among different methods to realize NAS, the evolutionary computation (EC) methods have recently gained much attention and success. Unfortunately, there has not yet been a comprehensive summary of the EC-based NAS algorithms. This article reviews over 200 articles of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles and justifications on the design. Furthermore, current challenges and issues are also discussed to identify future research in this emerging field.
AbstractList Deep neural networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labor-intensive because of the trial-and-error process and also not easy to realize due to the rare expertise in practice. Neural architecture search (NAS) is a type of technology that can design the architectures automatically. Among different methods to realize NAS, the evolutionary computation (EC) methods have recently gained much attention and success. Unfortunately, there has not yet been a comprehensive summary of the EC-based NAS algorithms. This article reviews over 200 articles of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles and justifications on the design. Furthermore, current challenges and issues are also discussed to identify future research in this emerging field.
Deep neural networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labor-intensive because of the trial-and-error process and also not easy to realize due to the rare expertise in practice. Neural architecture search (NAS) is a type of technology that can design the architectures automatically. Among different methods to realize NAS, the evolutionary computation (EC) methods have recently gained much attention and success. Unfortunately, there has not yet been a comprehensive summary of the EC-based NAS algorithms. This article reviews over 200 articles of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles and justifications on the design. Furthermore, current challenges and issues are also discussed to identify future research in this emerging field.Deep neural networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labor-intensive because of the trial-and-error process and also not easy to realize due to the rare expertise in practice. Neural architecture search (NAS) is a type of technology that can design the architectures automatically. Among different methods to realize NAS, the evolutionary computation (EC) methods have recently gained much attention and success. Unfortunately, there has not yet been a comprehensive summary of the EC-based NAS algorithms. This article reviews over 200 articles of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles and justifications on the design. Furthermore, current challenges and issues are also discussed to identify future research in this emerging field.
Author Xue, Bing
Zhang, Mengjie
Tan, Kay Chen
Yen, Gary G.
Sun, Yanan
Liu, Yuqiao
Author_xml – sequence: 1
  givenname: Yuqiao
  orcidid: 0000-0001-6255-2714
  surname: Liu
  fullname: Liu, Yuqiao
  email: lyqguitar@gmail.com
  organization: College of Computer Science, Sichuan University, Chengdu, China
– sequence: 2
  givenname: Yanan
  orcidid: 0000-0001-6374-1429
  surname: Sun
  fullname: Sun, Yanan
  email: ysun@scu.edu.cn
  organization: College of Computer Science, Sichuan University, Chengdu, China
– sequence: 3
  givenname: Bing
  orcidid: 0000-0002-4865-8026
  surname: Xue
  fullname: Xue, Bing
  email: bing.xue@ecs.vuw.ac.nz
  organization: School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand
– sequence: 4
  givenname: Mengjie
  orcidid: 0000-0003-4463-9538
  surname: Zhang
  fullname: Zhang, Mengjie
  email: mengjie.zhang@ecs.vuw.ac.nz
  organization: School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand
– sequence: 5
  givenname: Gary G.
  orcidid: 0000-0001-8851-5348
  surname: Yen
  fullname: Yen, Gary G.
  email: gyen@okstate.edu
  organization: School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, OK, USA
– sequence: 6
  givenname: Kay Chen
  orcidid: 0000-0002-6802-2463
  surname: Tan
  fullname: Tan, Kay Chen
  email: kaychen.tan@polyu.edu.hk
  organization: Department of Computing, Hong Kong Polytechnic University, Hong Kong
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34357870$$D View this record in MEDLINE/PubMed
BookMark eNp9kE1LwzAYgIMoTqd_QEEKXrxsvvlq0uMYfsGYhyl4C0n6Bitdq2kr7N_buY-DB3NJAs_zkjyn5LCqKyTkgsKYUshuX-bz2WLMgNExpwBSigNywmjKRoxrfbg_q7cBOW-aD-hXCjIV2TEZcMGl0gpOCJ8kiy5-4yqpq-Tuuy67tqgrG1fJHLtoy2QS_XvRom-7iMkCbX89I0fBlg2eb_cheb2_e5k-jmbPD0_TyWzkBVXtyLo0hFTbzElhHQgnrE6pE3nwIbfofA4ZKg-UBZeDU8C5Vl4HLVGCCxkfkpvN3M9Yf3XYtGZZNB7L0lZYd41hUmaCCwVr9PoP-lF3sepfZ5hSXEjJFe-pqy3VuSXm5jMWy_6rZpejB_QG8LFumojB-KK16yJttEVpKJh1fPMb36zjm238XmV_1N30f6XLjVQg4l7IJGilBP8BRt6OhA
CODEN ITNNAL
CitedBy_id crossref_primary_10_1007_s13042_024_02300_6
crossref_primary_10_1109_TETCI_2024_3377683
crossref_primary_10_1109_TFUZZ_2024_3373792
crossref_primary_10_1109_TNNLS_2024_3382724
crossref_primary_10_1109_TII_2023_3305682
crossref_primary_10_1109_MCI_2023_3277769
crossref_primary_10_1109_TEVC_2023_3255263
crossref_primary_10_1016_j_asoc_2023_110671
crossref_primary_10_1109_ACCESS_2022_3212767
crossref_primary_10_1109_JSEN_2023_3325545
crossref_primary_10_1016_j_swevo_2025_101879
crossref_primary_10_1109_TEVC_2023_3346969
crossref_primary_10_1016_j_neucom_2024_129111
crossref_primary_10_1016_j_ins_2024_120644
crossref_primary_10_1109_TEVC_2023_3338371
crossref_primary_10_1109_TNNLS_2023_3347542
crossref_primary_10_1109_TPAMI_2024_3498035
crossref_primary_10_1007_s00138_024_01611_6
crossref_primary_10_1007_s10586_024_04828_2
crossref_primary_10_1109_TPAMI_2024_3395423
crossref_primary_10_1002_rob_22247
crossref_primary_10_1109_TII_2024_3393553
crossref_primary_10_1109_TIP_2024_3512381
crossref_primary_10_1007_s00521_022_07035_5
crossref_primary_10_1016_j_dsp_2024_104559
crossref_primary_10_1142_S179396232541003X
crossref_primary_10_1109_TNNLS_2021_3123105
crossref_primary_10_1007_s13042_022_01578_8
crossref_primary_10_1109_ACCESS_2024_3441469
crossref_primary_10_1007_s11547_024_01770_6
crossref_primary_10_1016_j_swevo_2024_101629
crossref_primary_10_1109_TNNLS_2023_3283239
crossref_primary_10_1016_j_neunet_2024_106427
crossref_primary_10_1016_j_aej_2023_12_028
crossref_primary_10_1109_TEVC_2023_3319566
crossref_primary_10_1109_JSTARS_2022_3217047
crossref_primary_10_3390_ai4030039
crossref_primary_10_1016_j_eswa_2023_121202
crossref_primary_10_1109_TCCN_2022_3169740
crossref_primary_10_1016_j_ins_2024_121347
crossref_primary_10_1145_3715851
crossref_primary_10_1109_TCBB_2023_3272333
crossref_primary_10_1016_j_indcrop_2024_118635
crossref_primary_10_1016_j_knosys_2025_113122
crossref_primary_10_1016_j_jksuci_2024_102226
crossref_primary_10_1016_j_swevo_2024_101741
crossref_primary_10_3389_fpls_2022_897883
crossref_primary_10_1016_j_cja_2024_11_005
crossref_primary_10_1109_TETCI_2023_3301395
crossref_primary_10_1109_TCASAI_2024_3493036
crossref_primary_10_1109_TEVC_2023_3290172
crossref_primary_10_1109_MCI_2022_3155332
crossref_primary_10_1109_LSENS_2023_3273733
crossref_primary_10_1016_j_asoc_2025_112832
crossref_primary_10_3934_era_2024013
crossref_primary_10_1007_s11227_022_04960_z
crossref_primary_10_1016_j_asoc_2023_110216
crossref_primary_10_1021_acsami_4c06740
crossref_primary_10_1007_s11227_023_05790_3
crossref_primary_10_1016_j_swevo_2025_101856
crossref_primary_10_1109_TETCI_2023_3251400
crossref_primary_10_1007_s41095_024_0447_8
crossref_primary_10_1109_TAI_2021_3128502
crossref_primary_10_1109_TIV_2023_3319689
crossref_primary_10_1016_j_neunet_2025_107368
crossref_primary_10_1109_TIM_2024_3400360
crossref_primary_10_1007_s00521_024_09903_8
crossref_primary_10_1109_TVT_2024_3369748
crossref_primary_10_1109_TCYB_2024_3455760
crossref_primary_10_1109_ACCESS_2023_3295330
crossref_primary_10_1007_s11633_022_1357_9
crossref_primary_10_1016_j_pnucene_2024_105294
crossref_primary_10_1016_j_bspc_2024_106325
crossref_primary_10_1109_TNNLS_2023_3269816
crossref_primary_10_1016_j_eswa_2024_125806
crossref_primary_10_3934_era_2024092
crossref_primary_10_3390_app14146143
crossref_primary_10_1007_s10115_024_02179_3
crossref_primary_10_1007_s40747_023_01166_5
crossref_primary_10_1007_s40747_025_01845_5
crossref_primary_10_1080_09524622_2024_2329193
crossref_primary_10_1109_TAI_2024_3407033
crossref_primary_10_3390_biomimetics8070525
crossref_primary_10_1109_JIOT_2024_3386965
crossref_primary_10_3389_fnume_2022_1083245
crossref_primary_10_1049_csy2_12085
crossref_primary_10_1007_s10462_022_10303_4
crossref_primary_10_1109_TAI_2024_3477457
crossref_primary_10_1109_ACCESS_2023_3320133
crossref_primary_10_1088_1361_6501_ad8f4c
crossref_primary_10_1109_TPAMI_2023_3334614
crossref_primary_10_1109_TNNLS_2023_3326648
crossref_primary_10_1109_TAI_2021_3134600
crossref_primary_10_1109_TAI_2023_3322394
crossref_primary_10_1109_TITS_2023_3321384
crossref_primary_10_1016_j_asoc_2023_111176
crossref_primary_10_7717_peerj_cs_1903
crossref_primary_10_1007_s11517_024_03025_y
crossref_primary_10_1109_ACCESS_2024_3365349
crossref_primary_10_1016_j_asoc_2024_111442
crossref_primary_10_1109_TEVC_2023_3324852
crossref_primary_10_1109_TEVC_2022_3220747
crossref_primary_10_1016_j_aei_2024_102395
crossref_primary_10_1016_j_swevo_2024_101837
crossref_primary_10_1109_MCOM_001_2300587
crossref_primary_10_1016_j_patcog_2023_110052
crossref_primary_10_1109_ACCESS_2024_3355804
crossref_primary_10_1016_j_autcon_2024_105593
crossref_primary_10_1109_TEVC_2024_3353182
crossref_primary_10_1093_nsr_nwae282
crossref_primary_10_3390_math12101563
crossref_primary_10_1109_ACCESS_2023_3312217
crossref_primary_10_32604_cmc_2024_051757
crossref_primary_10_1016_j_bspc_2024_107479
crossref_primary_10_3390_math11194115
crossref_primary_10_1038_s41467_023_36961_8
crossref_primary_10_1109_TEVC_2022_3147526
crossref_primary_10_1145_3603704
crossref_primary_10_1007_s10115_024_02090_x
crossref_primary_10_3934_mbe_2023671
crossref_primary_10_1007_s12626_023_00151_1
crossref_primary_10_1016_j_neucom_2024_127664
crossref_primary_10_1109_TNNLS_2023_3339614
crossref_primary_10_1016_j_knosys_2024_112810
crossref_primary_10_3390_ai5040142
crossref_primary_10_34133_research_0442
crossref_primary_10_1016_j_swevo_2024_101663
crossref_primary_10_1109_TCYB_2023_3267109
crossref_primary_10_1016_j_neunet_2024_106104
crossref_primary_10_4018_IJCINI_371401
crossref_primary_10_1007_s10115_024_02329_7
crossref_primary_10_1109_TEVC_2021_3088631
crossref_primary_10_1016_j_eswa_2025_127237
crossref_primary_10_1515_nanoph_2023_0527
crossref_primary_10_1109_TAI_2022_3207112
crossref_primary_10_1109_TCSVT_2024_3407138
crossref_primary_10_1016_j_icte_2025_02_008
crossref_primary_10_1109_JIOT_2024_3428554
crossref_primary_10_3389_fphys_2022_1097204
crossref_primary_10_1007_s00521_024_10759_1
crossref_primary_10_1007_s11063_024_11659_0
crossref_primary_10_1016_j_iot_2023_101047
crossref_primary_10_14778_3705829_3705835
crossref_primary_10_1016_j_asoc_2023_110412
crossref_primary_10_1109_MNANO_2025_3533937
crossref_primary_10_3390_math13040631
crossref_primary_10_3389_fncom_2023_1092185
crossref_primary_10_1109_TCASAI_2024_3523858
crossref_primary_10_1109_ACCESS_2023_3253818
crossref_primary_10_1109_TEVC_2023_3307245
crossref_primary_10_1109_TCAD_2023_3262201
crossref_primary_10_1007_s00034_024_02919_4
crossref_primary_10_3934_era_2024050
crossref_primary_10_1007_s00500_023_08316_4
crossref_primary_10_1186_s13634_022_00868_1
crossref_primary_10_1038_s41598_022_12509_6
crossref_primary_10_1109_TETCI_2023_3289974
crossref_primary_10_1109_TGRS_2025_3537085
crossref_primary_10_1016_j_patcog_2023_109790
crossref_primary_10_1007_s40747_023_01168_3
crossref_primary_10_1007_s40747_022_00919_y
crossref_primary_10_3390_drones7050287
crossref_primary_10_1007_s10710_024_09483_5
crossref_primary_10_1007_s10586_024_04765_0
crossref_primary_10_1007_s10462_024_10726_1
crossref_primary_10_1109_TNNLS_2023_3346169
crossref_primary_10_1016_j_procs_2025_02_177
crossref_primary_10_1038_s42256_024_00928_1
crossref_primary_10_1109_TIM_2022_3219476
crossref_primary_10_1007_s12065_023_00874_8
crossref_primary_10_1016_j_compmedimag_2023_102307
Cites_doi 10.1007/978-3-030-30484-3_32
10.1007/978-981-15-1398-5_1
10.1109/TEVC.2007.892759
10.1109/TCYB.2020.2983860
10.1145/3321707.3321729
10.1109/TEVC.2004.826067
10.1109/TNN.2010.2064176
10.1007/978-3-030-03991-2_24
10.1109/AFGR.1996.557260
10.1109/MCSoC2018.2018.00049
10.1162/neco.1997.9.8.1735
10.1609/aaai.v33i01.33014780
10.1109/CEC.2018.8477921
10.1016/j.swevo.2019.05.010
10.1109/CEC.2018.8477735
10.1016/j.swevo.2020.100650
10.1109/ICMLA.2011.73
10.1109/ICCV.2019.00188
10.1109/HPEC.2019.8916533
10.1162/neco.2006.18.7.1527
10.1007/s10710-018-9339-y
10.1109/CVPR.2016.90
10.1109/CVPR.2019.00927
10.1371/journal.pone.0188746
10.1038/s42256-018-0006-z
10.1007/s00500-008-0347-3
10.1109/TEVC.2018.2791283
10.1145/3205455.3205489
10.1109/ICIP.2018.8451394
10.1109/MMAR.2019.8864624
10.1155/2019/2537689
10.1002/cpe.4128
10.1109/CVPR.2017.243
10.1007/s11633-016-1006-2
10.1109/TNNLS.2018.2881143
10.1109/ACCESS.2019.2933947
10.1109/IFSA-SCIS.2017.8023302
10.1109/GCCE46687.2019.9015558
10.1145/3377930.3389834
10.1007/s10772-019-09652-3
10.1109/ACCESS.2018.2880416
10.1145/3319619.3322003
10.1109/72.265960
10.1109/CEC.2018.8477790
10.1145/2834892.2834896
10.1109/TNNLS.2016.2582798
10.1007/978-3-319-10590-1_53
10.1145/3205455.3205637
10.1109/BESC48373.2019.8962993
10.1109/SLT.2016.7846334
10.1007/978-3-030-16692-2_33
10.1109/IJCNN.2019.8852417
10.1007/978-3-642-04277-5_76
10.1109/TPAMI.1987.4767897
10.1038/nature14539
10.1007/s10710-019-09354-4
10.1613/jair.301
10.1109/ICNN.1995.488968
10.1007/978-3-030-01252-6_32
10.1109/IRI.2019.00052
10.1007/s10462-019-09719-2
10.1109/ICASSP.2017.7953077
10.1109/CCWC47524.2020.9031239
10.1007/978-3-030-44094-7_3
10.1109/CEC.2018.8477933
10.1109/HPBDIS.2019.8735458
10.1109/JSYST.2014.2300201
10.1109/ICCVW.2019.00238
10.1109/ICCV.2017.154
10.1109/SMC.2019.8914267
10.1145/3321707.3321721
10.1109/ICASSP.2015.7178918
10.1109/ECACE.2019.8679206
10.1016/j.inffus.2019.12.007
10.1109/ACCESS.2018.2887023
10.1007/978-3-030-36296-6_76
10.17533/udea.redin.20190736
10.1016/j.asoc.2019.105510
10.1016/j.jpdc.2017.09.006
10.1145/3341105.3373856
10.1109/ICRA.2019.8793613
10.1016/j.energy.2018.05.052
10.1109/TEVC.2018.2808689
10.1109/TEVC.2019.2924461
10.1162/evco_a_00253
10.1109/ICMLA.2019.00018
10.1201/9780367802486
10.1109/TEVC.2013.2281535
10.1109/CEC.2019.8790093
10.1109/ICCVW.2019.00256
10.1109/CVPR.2018.00907
10.1007/978-3-540-31880-4_35
10.1109/CEC.2019.8790151
10.1016/j.asoc.2018.09.013
10.1016/j.future.2019.01.049
10.1080/01691864.2018.1529620
10.1109/5.726791
10.1145/3240765.3243494
10.1109/4235.996017
10.1109/ACCESS.2020.2964424
10.1089/big.2020.0051
10.1109/TNNLS.2019.2919608
10.1016/j.media.2019.03.004
10.1007/978-3-319-77538-8_27
10.1007/978-981-15-0306-1_5
10.1109/TNNLS.2017.2695223
10.1007/978-3-642-35289-8_26
10.1109/TEVC.2021.3079985
10.1016/j.biortech.2019.121971
10.1007/s00521-020-04749-2
10.1007/978-1-4614-6940-7_15
10.1007/978-3-319-99259-4_34
10.1016/j.neucom.2019.10.053
10.1145/3321707.3321735
10.1007/978-3-030-30642-7_20
10.1109/TCYB.2015.2409837
10.1007/978-3-030-55789-8_61
10.1145/3205455.3205631
10.1145/3071178.3071229
10.1109/ICDAR.1995.598994
10.1109/CEC.2019.8790145
10.1016/j.neucom.2019.10.096
10.1007/978-3-030-32248-9_83
10.1016/B978-0-12-815480-9.00015-3
10.1016/j.neucom.2019.01.110
10.1109/3477.484436
10.7551/mitpress/3927.001.0001
10.1145/3129416.3129429
10.1007/BFb0055923
10.1007/978-3-319-16468-7_8
10.1007/s12065-007-0002-4
10.1109/BigData.2015.7364099
10.1145/3071178.3071208
10.1016/j.micpro.2020.102989
10.1016/j.neunet.2019.12.005
10.1016/j.knosys.2019.01.015
10.1007/978-3-030-29894-4_52
10.1109/TEVC.2019.2916183
10.1088/1361-6501/aae5b2
10.1109/CVPR.2015.7298594
10.1145/3378184.3378187
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7QF
7QO
7QP
7QQ
7QR
7SC
7SE
7SP
7SR
7TA
7TB
7TK
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
P64
7X8
DOI 10.1109/TNNLS.2021.3100554
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
PubMed
Aluminium Industry Abstracts
Biotechnology Research Abstracts
Calcium & Calcified Tissue Abstracts
Ceramic Abstracts
Chemoreception Abstracts
Computer and Information Systems Abstracts
Corrosion Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
Materials Business File
Mechanical & Transportation Engineering Abstracts
Neurosciences Abstracts
Solid State and Superconductivity Abstracts
METADEX
Technology Research Database
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Aerospace Database
Materials Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
Materials Research Database
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Materials Business File
Aerospace Database
Engineered Materials Abstracts
Biotechnology Research Abstracts
Chemoreception Abstracts
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
Civil Engineering Abstracts
Aluminium Industry Abstracts
Electronics & Communications Abstracts
Ceramic Abstracts
Neurosciences Abstracts
METADEX
Biotechnology and BioEngineering Abstracts
Computer and Information Systems Abstracts Professional
Solid State and Superconductivity Abstracts
Engineering Research Database
Calcium & Calcified Tissue Abstracts
Corrosion Abstracts
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
Materials Research Database
PubMed
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Statistics
Computer Science
EISSN 2162-2388
EndPage 570
ExternalDocumentID 34357870
10_1109_TNNLS_2021_3100554
9508774
Genre orig-research
Journal Article
GrantInformation_xml – fundername: Science and Technology Innovation Talent Project of Sichuan Province
  grantid: 2021JDRC0001
– fundername: Research Grants Council of the Hong Kong SAR
  grantid: PolyU11202418; PolyU11209219
  funderid: 10.13039/501100002920
– fundername: National Natural Science Foundation of China
  grantid: 61803277
  funderid: 10.13039/501100001809
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
ACPRK
AENEX
AFRAH
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
IFIPE
IPLJI
JAVBF
M43
MS~
O9-
OCL
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
RIG
NPM
7QF
7QO
7QP
7QQ
7QR
7SC
7SE
7SP
7SR
7TA
7TB
7TK
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
P64
7X8
ID FETCH-LOGICAL-c417t-ab6ff68a9b54ab04b4a861b4dfcfdaebcd09e7c012fbd0b703387c8f85e50bf93
IEDL.DBID RIE
ISSN 2162-237X
2162-2388
IngestDate Fri Jul 11 04:10:53 EDT 2025
Sun Jun 29 16:57:28 EDT 2025
Thu Jan 02 22:52:03 EST 2025
Tue Jul 01 00:27:40 EDT 2025
Thu Apr 24 23:11:47 EDT 2025
Wed Aug 27 02:48:03 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 2
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c417t-ab6ff68a9b54ab04b4a861b4dfcfdaebcd09e7c012fbd0b703387c8f85e50bf93
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0001-6374-1429
0000-0003-4463-9538
0000-0001-6255-2714
0000-0001-8851-5348
0000-0002-6802-2463
0000-0002-4865-8026
PMID 34357870
PQID 2773455373
PQPubID 85436
PageCount 21
ParticipantIDs proquest_journals_2773455373
proquest_miscellaneous_2559434709
pubmed_primary_34357870
crossref_citationtrail_10_1109_TNNLS_2021_3100554
crossref_primary_10_1109_TNNLS_2021_3100554
ieee_primary_9508774
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2023-02-01
PublicationDateYYYYMMDD 2023-02-01
PublicationDate_xml – month: 02
  year: 2023
  text: 2023-02-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Piscataway
PublicationTitle IEEE transaction on neural networks and learning systems
PublicationTitleAbbrev TNNLS
PublicationTitleAlternate IEEE Trans Neural Netw Learn Syst
PublicationYear 2023
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref56
ref208
ref59
ref58
ref206
ref203
ref52
ref204
ref55
ref201
ref54
ahmed (ref66) 2019
singh (ref48) 2019
ref210
ref211
ref51
zhu (ref171) 2020
ref219
ref47
ref214
ref215
devlin (ref4) 2018
ref44
ref212
ref43
ref49
ref7
ref9
ref3
ref6
ref5
ref221
liu (ref145) 2018
ref40
ref220
ho (ref149) 2020
ref35
ref34
ref37
ref36
ref33
ref38
frachon (ref76) 2019
colangelo (ref202) 2019
calisto (ref73) 2020; 11313
goodfellow (ref41) 2016; 1
fujino (ref213) 2017
elsken (ref26) 2018
shu (ref50) 2020
ref24
ref25
ref20
wei (ref182) 2016
ref22
ref21
assunção (ref99) 2019
collins (ref229) 2016
ref28
ref29
chen (ref125) 2020
deb (ref179) 2001; 16
ho (ref205) 1995; 1
ref128
deng (ref195) 2009
ref97
ref126
ref96
wistuba (ref27) 2019
assunção (ref207) 2019
wang (ref98) 2019
chen (ref130) 2018
ref93
ref133
zhang (ref65) 2019
ref92
ref95
ref94
ref132
chen (ref123) 2019
ref91
ref90
ref89
ref86
ref85
ref138
yang (ref137) 2019
ref88
ref135
ref87
ref136
elsaid (ref163) 2019
yang (ref31) 2009
hu (ref134) 2018
ref82
ref144
kang (ref53) 2019
ref84
ref140
ref141
ref80
ref79
ref108
ref78
ref109
ref107
ref228
ref75
ref225
ref226
tanaka (ref160) 2016; 130
ref77
ref102
ref223
ref103
laredo (ref83) 2019
koza (ref224) 1992; 1
ref71
ref70
ref112
ref72
ref110
ref68
wang (ref131) 2019
ref67
ref117
ref69
ref118
ref64
ref115
ref63
ref116
ref113
simonyan (ref8) 2014
maziarz (ref180) 2018; abs 1811 9828
deb (ref184) 1995; 9
ref60
chen (ref122) 2018
ref62
ref120
ref61
so (ref194) 2019
real (ref23) 2017; 70
kotyan (ref185) 2019
song (ref114) 2019
krizhevsky (ref13) 2009
ref168
ref169
dong (ref172) 2018
wei (ref209) 2020
rawal (ref157) 2018
guo (ref139) 2019
ref170
chu (ref129) 2019
ref175
chrabaszcz (ref222) 2017
ref176
ref173
ref174
miahi (ref119) 2019
camero (ref45) 2018
ref188
elsken (ref32) 2017
ref189
ref186
ref187
ref183
elsken (ref105) 2018
kitano (ref147) 1990; 4
yen (ref74) 2019; 49
jones (ref148) 2019
ref146
chen (ref181) 2015
suganuma (ref42) 2018
liashchynskyi (ref218) 2019
ref155
ref156
ref153
byla (ref106) 2019
ref154
ref151
bender (ref199) 2018
lu (ref101) 2019
ref152
ref158
price (ref30) 2006
qiang (ref39) 2019
ying (ref142) 2019
ref164
ref165
loshchilov (ref162) 2016
ref161
fan (ref124) 2020
ref12
ref15
yu (ref217) 2019
ref11
chung (ref227) 2014
ref17
ref16
zoph (ref10) 2016
ref19
ref18
devries (ref216) 2017
chu (ref200) 2019
goldberg (ref14) 2006
fujino (ref57) 2018
dong (ref143) 2020
cetto (ref111) 2019
liu (ref100) 2017
an (ref177) 2019
ref2
wistuba (ref127) 2018
chu (ref121) 2019
ref191
ref192
ref190
zhang (ref166) 2000; 4
assunção (ref196) 2018
schorn (ref81) 2019
ref197
ref198
ref193
lecun (ref1) 2015; 521
evans (ref167) 2019
neshat (ref159) 2020
lamos-sweeney (ref150) 2012
javaheripi (ref178) 2020
zhang (ref104) 2020
camero (ref46) 2019
References_xml – ident: ref86
  doi: 10.1007/978-3-030-30484-3_32
– ident: ref89
  doi: 10.1007/978-981-15-1398-5_1
– ident: ref188
  doi: 10.1109/TEVC.2007.892759
– volume: 16
  year: 2001
  ident: ref179
  publication-title: Multi-Objective Optimization Using Evolutionary Algorithms
– ident: ref24
  doi: 10.1109/TCYB.2020.2983860
– ident: ref170
  doi: 10.1145/3321707.3321729
– ident: ref190
  doi: 10.1109/TEVC.2004.826067
– year: 2014
  ident: ref227
  article-title: Empirical evaluation of gated recurrent neural networks on sequence modeling
  publication-title: arXiv 1412 3555
– ident: ref225
  doi: 10.1109/TNN.2010.2064176
– ident: ref75
  doi: 10.1007/978-3-030-03991-2_24
– ident: ref226
  doi: 10.1109/AFGR.1996.557260
– start-page: 1
  year: 2018
  ident: ref172
  article-title: PPP-Net: Platform-aware progressive search for pareto-optimal neural architectures
  publication-title: Proc 6th Int Conf Learn Represent (ICLR)
– start-page: 197
  year: 2019
  ident: ref99
  article-title: Fast denser: Efficient deep neuroevolution
  publication-title: Proc Eur Conf Genetic Program
– ident: ref113
  doi: 10.1109/MCSoC2018.2018.00049
– year: 2020
  ident: ref171
  article-title: Real-time federated evolutionary neural architecture search
  publication-title: arXiv 2003 02793
– ident: ref204
  doi: 10.1162/neco.1997.9.8.1735
– ident: ref36
  doi: 10.1609/aaai.v33i01.33014780
– start-page: 119
  year: 2019
  ident: ref106
  article-title: Deepswarm: Optimising convolutional neural networks using swarm intelligence
  publication-title: Proc UK Workshop Comput Intell
– year: 2019
  ident: ref46
  article-title: Random error sampling-based recurrent neural network architecture optimization
  publication-title: arXiv 1909 02425
– ident: ref47
  doi: 10.1109/CEC.2018.8477921
– volume: 49
  start-page: 62
  year: 2019
  ident: ref74
  article-title: Particle swarm optimization of deep neural networks architectures for image classification
  publication-title: Swarm Evol Comput
  doi: 10.1016/j.swevo.2019.05.010
– ident: ref97
  doi: 10.1109/CEC.2018.8477735
– ident: ref69
  doi: 10.1016/j.swevo.2020.100650
– ident: ref54
  doi: 10.1109/ICMLA.2011.73
– ident: ref70
  doi: 10.1109/ICCV.2019.00188
– year: 2019
  ident: ref101
  article-title: Multi-objective evolutionary design of deep convolutional neural networks for image classification
  publication-title: arXiv 1912 01369 [cs]
– ident: ref201
  doi: 10.1109/HPEC.2019.8916533
– ident: ref37
  doi: 10.1162/neco.2006.18.7.1527
– ident: ref197
  doi: 10.1007/s10710-018-9339-y
– ident: ref2
  doi: 10.1109/CVPR.2016.90
– ident: ref93
  doi: 10.1109/CVPR.2019.00927
– year: 2018
  ident: ref157
  article-title: From nodes to networks: Evolving recurrent neural networks
  publication-title: arXiv 1803 04439
– ident: ref56
  doi: 10.1371/journal.pone.0188746
– ident: ref28
  doi: 10.1038/s42256-018-0006-z
– year: 2016
  ident: ref162
  article-title: CMA-ES for hyperparameter optimization of deep neural networks
  publication-title: arXiv 1604 07269
– ident: ref33
  doi: 10.1007/s00500-008-0347-3
– volume: 70
  start-page: 2902
  year: 2017
  ident: ref23
  article-title: Large-scale evolution of image classifiers
  publication-title: Proc 34th Int Conf Mach Learn (ICML)
– ident: ref17
  doi: 10.1109/TEVC.2018.2791283
– ident: ref212
  doi: 10.1145/3205455.3205489
– ident: ref120
  doi: 10.1109/ICIP.2018.8451394
– ident: ref59
  doi: 10.1109/MMAR.2019.8864624
– ident: ref49
  doi: 10.1155/2019/2537689
– start-page: 169
  year: 2009
  ident: ref31
  article-title: Firefly algorithms for multimodal optimization
  publication-title: Proc Int Symp Stochastic Algorithms
– ident: ref38
  doi: 10.1002/cpe.4128
– ident: ref3
  doi: 10.1109/CVPR.2017.243
– volume: 4
  start-page: 2487
  year: 2000
  ident: ref166
  article-title: Particle swarm optimisation for evolving artificial neural network
  publication-title: Proc Conf IEEE Int Conf Syst Man Cybern Cybern Evolving Syst Hum Org Complex Interact (SMC)
– start-page: 497
  year: 2019
  ident: ref123
  article-title: Efficient evolutionary deep neural architecture search (NAS) by noisy network morphism mutation
  publication-title: Proc Int Conf Bio-Inspired Comput Theories Appl
– volume: 130
  start-page: 1
  year: 2016
  ident: ref160
  article-title: Evolution strategy based neural network optimization and LSTM language model for robust speech recognition
  publication-title: CIT
– year: 2018
  ident: ref26
  article-title: Neural architecture search: A survey
  publication-title: arXiv 1808 05377
– year: 2019
  ident: ref202
  article-title: Evolutionary cell aided design for neural network architectures
  publication-title: arXiv 1903 02130
– ident: ref228
  doi: 10.1007/s11633-016-1006-2
– year: 2019
  ident: ref177
  article-title: StyleNAS: An empirical study of neural architecture search to uncover surprisingly fast end-to-end universal style transfer networks
  publication-title: arXiv 1906 02470
– ident: ref25
  doi: 10.1109/TNNLS.2018.2881143
– year: 2019
  ident: ref137
  article-title: CARS: Continuous evolution for efficient neural architecture search
  publication-title: arXiv 1909 04977
– ident: ref82
  doi: 10.1109/ACCESS.2019.2933947
– start-page: 638
  year: 2019
  ident: ref53
  article-title: Efficient neural network space with genetic search
  publication-title: Proc Int Conf Bio-Inspired Comput Theories Appl
– ident: ref34
  doi: 10.1109/IFSA-SCIS.2017.8023302
– ident: ref94
  doi: 10.1109/GCCE46687.2019.9015558
– ident: ref79
  doi: 10.1145/3377930.3389834
– volume: 1
  year: 2016
  ident: ref41
  publication-title: Deep Learning
– year: 2006
  ident: ref30
  publication-title: Differential Evolution A Practical Approach to Global Optimization
– ident: ref103
  doi: 10.1007/s10772-019-09652-3
– year: 2020
  ident: ref209
  article-title: NPENAS: Neural predictor guided evolution for neural architecture search
  publication-title: arXiv 2003 12857
– ident: ref110
  doi: 10.1109/ACCESS.2018.2880416
– ident: ref158
  doi: 10.1145/3319619.3322003
– ident: ref156
  doi: 10.1109/72.265960
– year: 2020
  ident: ref125
  article-title: ImmuNetNAS: An immune-network approach for searching convolutional neural network architectures
  publication-title: arXiv 2002 12704
– year: 2017
  ident: ref222
  article-title: A downsampled variant of ImageNet as an alternative to the CIFAR datasets
  publication-title: arXiv 1707 08819
– ident: ref64
  doi: 10.1109/CEC.2018.8477790
– year: 2020
  ident: ref159
  article-title: An evolutionary deep learning method for short-term wind speed prediction: A case study of the lillgrund offshore wind farm
  publication-title: arXiv 2002 09106
– year: 2016
  ident: ref10
  article-title: Neural architecture search with reinforcement learning
  publication-title: arXiv 1611 01578
– ident: ref72
  doi: 10.1145/2834892.2834896
– volume: abs 1811 9828
  start-page: 1
  year: 2018
  ident: ref180
  article-title: Evolutionary-neural hybrid agents for architecture search
  publication-title: CoRR
– ident: ref55
  doi: 10.1109/TNNLS.2016.2582798
– ident: ref223
  doi: 10.1007/978-3-319-10590-1_53
– start-page: 26
  year: 2019
  ident: ref39
  article-title: Neural architecture search for optimizing deep belief network models of fMRI data
  publication-title: Proc Int Workshop Multiscale Multimodal Med Imag
– ident: ref164
  doi: 10.1145/3205455.3205637
– start-page: 473
  year: 2019
  ident: ref66
  article-title: A novel automatic CNN architecture design approach based on genetic algorithm
  publication-title: Proc Int Conf Adv Intell Syst Inform
– ident: ref210
  doi: 10.1109/BESC48373.2019.8962993
– ident: ref58
  doi: 10.1109/SLT.2016.7846334
– year: 2019
  ident: ref81
  article-title: Automated design of error-resilient and hardware-efficient deep neural networks
  publication-title: arXiv 1909 13844
– year: 2019
  ident: ref163
  article-title: The ant swarm neuro-evolution procedure for optimizing recurrent networks
  publication-title: arXiv 1909 11849
– ident: ref151
  doi: 10.1007/978-3-030-16692-2_33
– ident: ref96
  doi: 10.1109/IJCNN.2019.8852417
– ident: ref174
  doi: 10.1007/978-3-642-04277-5_76
– year: 2019
  ident: ref27
  article-title: A survey on neural architecture search
  publication-title: arXiv 1905 01392
– start-page: 248
  year: 2009
  ident: ref195
  article-title: ImageNet: A large-scale hierarchical image database
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit
– year: 2012
  ident: ref150
  article-title: Deep learning using genetic algorithms
– ident: ref7
  doi: 10.1109/TPAMI.1987.4767897
– year: 2019
  ident: ref121
  article-title: Multi-objective reinforced evolution in mobile neural architecture search
  publication-title: arXiv 1901 01074
– volume: 521
  start-page: 436
  year: 2015
  ident: ref1
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– ident: ref44
  doi: 10.1007/s10710-019-09354-4
– year: 2020
  ident: ref178
  article-title: GeneCAI: Genetic evolution for acquiring compact AI
  publication-title: arXiv 2004 04249
– ident: ref11
  doi: 10.1613/jair.301
– year: 2019
  ident: ref185
  article-title: Evolving robust neural architectures to defend from adversarial attacks
  publication-title: arXiv 1906 11667
– ident: ref16
  doi: 10.1109/ICNN.1995.488968
– ident: ref214
  doi: 10.1007/978-3-030-01252-6_32
– ident: ref67
  doi: 10.1109/IRI.2019.00052
– ident: ref18
  doi: 10.1007/s10462-019-09719-2
– ident: ref5
  doi: 10.1109/ICASSP.2017.7953077
– ident: ref43
  doi: 10.1109/CCWC47524.2020.9031239
– ident: ref208
  doi: 10.1007/978-3-030-44094-7_3
– year: 2019
  ident: ref48
  article-title: A genetic algorithm based kernel-size selection approach for a multi-column convolutional neural network
  publication-title: arXiv 1912 12405
– year: 2018
  ident: ref130
  article-title: Joint neural architecture search and quantization
  publication-title: arXiv 1811 09426
– ident: ref154
  doi: 10.1109/CEC.2018.8477933
– start-page: 549
  year: 2018
  ident: ref199
  article-title: Understanding and simplifying one-shot architecture search
  publication-title: Proc 35th Int Conf Mach Learn (ICML)
– ident: ref68
  doi: 10.1109/HPBDIS.2019.8735458
– year: 2019
  ident: ref65
  article-title: A new compensatory genetic algorithm-based method for effective compressed multi-function convolutional neural network model selection with multi-objective optimization
  publication-title: arXiv 1906 11912
– year: 2019
  ident: ref131
  article-title: Particle swarm optimisation for evolving deep neural networks for image classification by evolving and stacking transferable blocks
  publication-title: arXiv 1907 12659
– ident: ref220
  doi: 10.1109/JSYST.2014.2300201
– ident: ref60
  doi: 10.1109/ICCVW.2019.00238
– ident: ref35
  doi: 10.1109/ICCV.2017.154
– ident: ref108
  doi: 10.1109/SMC.2019.8914267
– ident: ref176
  doi: 10.1145/3321707.3321721
– year: 2019
  ident: ref148
  article-title: Evolutionary deep learning to identify galaxies in the zone of avoidance
  publication-title: arXiv 1903 07461
– ident: ref140
  doi: 10.1109/ICASSP.2015.7178918
– ident: ref84
  doi: 10.1109/ECACE.2019.8679206
– ident: ref155
  doi: 10.1016/j.inffus.2019.12.007
– ident: ref95
  doi: 10.1109/ACCESS.2018.2887023
– start-page: 1
  year: 2020
  ident: ref143
  article-title: Nas-bench-201: Extending the scope of reproducible neural architecture search
  publication-title: Proc Int Conf Learn Represent (ICLR)
– ident: ref175
  doi: 10.1007/978-3-030-36296-6_76
– ident: ref161
  doi: 10.17533/udea.redin.20190736
– year: 2019
  ident: ref207
  article-title: Fast-DENSER++: Evolving fully-trained deep artificial neural networks
  publication-title: arXiv 1905 02969
– year: 2019
  ident: ref167
  article-title: Genetic programming and gradient descent: A memetic approach to binary image classification
  publication-title: arXiv 1909 13030
– volume: 9
  start-page: 115
  year: 1995
  ident: ref184
  article-title: Simulated binary crossover for continuous search space
  publication-title: Complex Syst
– ident: ref78
  doi: 10.1016/j.asoc.2019.105510
– year: 2019
  ident: ref200
  article-title: FairNAS: Rethinking evaluation fairness of weight sharing neural architecture search
  publication-title: arXiv 1907 01845
– year: 2016
  ident: ref229
  article-title: Capacity and trainability in recurrent neural networks
  publication-title: arXiv 1611 09913
– ident: ref22
  doi: 10.1016/j.jpdc.2017.09.006
– ident: ref118
  doi: 10.1145/3341105.3373856
– ident: ref153
  doi: 10.1109/ICRA.2019.8793613
– year: 2019
  ident: ref139
  article-title: Single path one-shot neural architecture search with uniform sampling
  publication-title: arXiv 1904 00420
– ident: ref90
  doi: 10.1016/j.energy.2018.05.052
– ident: ref152
  doi: 10.1109/TEVC.2018.2808689
– ident: ref203
  doi: 10.1109/TEVC.2019.2924461
– ident: ref116
  doi: 10.1162/evco_a_00253
– ident: ref61
  doi: 10.1109/ICMLA.2019.00018
– volume: 4
  start-page: 461
  year: 1990
  ident: ref147
  article-title: Designing neural networks using genetic algorithms with graph generation system
  publication-title: Complex Syst
– year: 2018
  ident: ref105
  article-title: Efficient multi-objective neural architecture search via Lamarckian evolution
  publication-title: arXiv 1804 09081
– ident: ref12
  doi: 10.1201/9780367802486
– year: 2020
  ident: ref50
  article-title: Automatically searching for U-Net image translator architecture
  publication-title: arXiv 2002 11581
– volume: 11313
  year: 2020
  ident: ref73
  article-title: Self-adaptive 2D-3D ensemble of fully convolutional networks for medical image segmentation
  publication-title: Proc Med Imag Image Process Int Soc Opt Photon
– ident: ref189
  doi: 10.1109/TEVC.2013.2281535
– ident: ref146
  doi: 10.1109/CEC.2019.8790093
– ident: ref62
  doi: 10.1109/ICCVW.2019.00256
– ident: ref144
  doi: 10.1109/CVPR.2018.00907
– year: 2019
  ident: ref76
  article-title: ImmuNeCS: Neural committee search by an artificial immune system
  publication-title: arXiv 1911 07729
– ident: ref191
  doi: 10.1007/978-3-540-31880-4_35
– ident: ref63
  doi: 10.1109/CEC.2019.8790151
– ident: ref136
  doi: 10.1016/j.asoc.2018.09.013
– ident: ref168
  doi: 10.1016/j.future.2019.01.049
– year: 2018
  ident: ref134
  article-title: A novel channel pruning method for deep neural network compression
  publication-title: arXiv 1805 11394
– year: 2014
  ident: ref8
  article-title: Very deep convolutional networks for large-scale image recognition
  publication-title: arXiv 1409 1556
– ident: ref173
  doi: 10.1080/01691864.2018.1529620
– ident: ref221
  doi: 10.1109/5.726791
– ident: ref215
  doi: 10.1145/3240765.3243494
– ident: ref187
  doi: 10.1109/4235.996017
– start-page: 12
  year: 2009
  ident: ref13
  article-title: Learning multiple layers of features from tiny images
– ident: ref80
  doi: 10.1109/ACCESS.2020.2964424
– ident: ref88
  doi: 10.1089/big.2020.0051
– year: 2018
  ident: ref122
  article-title: Reinforced evolutionary neural architecture search
  publication-title: arXiv 1808 00193
– year: 2020
  ident: ref104
  article-title: Sampled training and node inheritance for fast evolutionary neural architecture search
  publication-title: arXiv 2003 11613
– year: 2019
  ident: ref129
  article-title: Fast, accurate and lightweight super-resolution with neural architecture search
  publication-title: arXiv 1901 07261
– ident: ref9
  doi: 10.1109/TNNLS.2019.2919608
– start-page: 243
  year: 2018
  ident: ref127
  article-title: Deep learning architecture search by neuro-cell-based evolution with function-preserving mutations
  publication-title: Proc Eur Conf Mach Learn Knowl Discovery Databases
– ident: ref126
  doi: 10.1016/j.media.2019.03.004
– ident: ref128
  doi: 10.1007/978-3-319-77538-8_27
– start-page: 17
  year: 2019
  ident: ref111
  article-title: Size/accuracy trade-off in convolutional neural networks: An evolutionary approach
  publication-title: Proc INNS Big Data Deep Learn Conf
– ident: ref77
  doi: 10.1007/978-981-15-0306-1_5
– ident: ref198
  doi: 10.1109/TNNLS.2017.2695223
– ident: ref6
  doi: 10.1007/978-3-642-35289-8_26
– start-page: 564
  year: 2016
  ident: ref182
  article-title: Network morphism
  publication-title: Proc Int Conf Mach Learn
– year: 2015
  ident: ref181
  article-title: Net2Net: Accelerating learning via knowledge transfer
  publication-title: arXiv 1511 05641
– ident: ref193
  doi: 10.1109/TEVC.2021.3079985
– ident: ref85
  doi: 10.1016/j.biortech.2019.121971
– year: 2019
  ident: ref114
  article-title: Efficient residual dense block search for image super-resolution
  publication-title: arXiv 1909 11409
– ident: ref206
  doi: 10.1007/s00521-020-04749-2
– ident: ref186
  doi: 10.1007/978-1-4614-6940-7_15
– ident: ref71
  doi: 10.1007/978-3-319-99259-4_34
– ident: ref169
  doi: 10.1016/j.neucom.2019.10.053
– ident: ref109
  doi: 10.1145/3321707.3321735
– year: 2020
  ident: ref124
  article-title: Evolutionary neural architecture search for retinal vessel segmentation
  publication-title: arXiv 2001 06678
– ident: ref132
  doi: 10.1007/978-3-030-30642-7_20
– ident: ref219
  doi: 10.1109/TCYB.2015.2409837
– ident: ref87
  doi: 10.1007/978-3-030-55789-8_61
– ident: ref135
  doi: 10.1145/3205455.3205631
– ident: ref112
  doi: 10.1145/3071178.3071229
– year: 2018
  ident: ref4
  article-title: BERT: Pre-training of deep bidirectional transformers for language understanding
  publication-title: arXiv 1810 04805
– volume: 1
  start-page: 278
  year: 1995
  ident: ref205
  article-title: Random decision forests
  publication-title: Proc 3rd Int Conf Document Anal Recognition
  doi: 10.1109/ICDAR.1995.598994
– year: 2019
  ident: ref119
  article-title: Genetic neural architecture search for automatic assessment of human sperm images
  publication-title: arXiv 1909 09432
– start-page: 19
  year: 2018
  ident: ref196
  article-title: Evolving the topology of large scale deep neural networks
  publication-title: Proc Eur Conf Genetic Program
– ident: ref133
  doi: 10.1109/CEC.2019.8790145
– ident: ref165
  doi: 10.1016/j.neucom.2019.10.096
– ident: ref40
  doi: 10.1007/978-3-030-32248-9_83
– year: 2019
  ident: ref98
  article-title: Evolving knowledge and structure through evolution-based neural architecture search
– ident: ref117
  doi: 10.1016/B978-0-12-815480-9.00015-3
– start-page: 386
  year: 2018
  ident: ref45
  article-title: Evolutionary deep learning for car park occupancy prediction in smart cities
  publication-title: Proc Int Conf Learn Intell Optim
– year: 2017
  ident: ref216
  article-title: Improved regularization of convolutional neural networks with cutout
  publication-title: arXiv 1708 04552
– start-page: 7105
  year: 2019
  ident: ref142
  article-title: NAS-bench-101: Towards reproducible neural architecture search
  publication-title: Proc Int Conf Mach Learn
– ident: ref107
  doi: 10.1016/j.neucom.2019.01.110
– ident: ref29
  doi: 10.1109/3477.484436
– ident: ref183
  doi: 10.7551/mitpress/3927.001.0001
– ident: ref20
  doi: 10.1145/3129416.3129429
– year: 2018
  ident: ref145
  article-title: DARTS: Differentiable architecture search
  publication-title: Arxiv 1806 09055
– ident: ref15
  doi: 10.1007/BFb0055923
– ident: ref138
  doi: 10.1007/978-3-319-16468-7_8
– year: 2017
  ident: ref32
  article-title: Simple and efficient architecture search for convolutional neural networks
  publication-title: Arxiv 1711 04528
– year: 2006
  ident: ref14
  publication-title: Genetic Algorithms
– start-page: 278
  year: 2017
  ident: ref213
  article-title: The evolutionary deep learning based on deep convolutional neural network for the anime storyboard recognition
  publication-title: Proc Int Symp Distrib Comput Artif Intell
– year: 2017
  ident: ref100
  article-title: Hierarchical representations for efficient architecture search
  publication-title: arXiv 1711 00436
– ident: ref19
  doi: 10.1007/s12065-007-0002-4
– ident: ref211
  doi: 10.1109/BigData.2015.7364099
– ident: ref102
  doi: 10.1145/3071178.3071208
– year: 2020
  ident: ref149
  article-title: Neural architecture search for deep image prior
  publication-title: arXiv 2001 04776
– ident: ref115
  doi: 10.1016/j.micpro.2020.102989
– year: 2019
  ident: ref83
  article-title: Automatic model selection for neural networks
  publication-title: arXiv 1905 06010
– ident: ref92
  doi: 10.1016/j.neunet.2019.12.005
– ident: ref51
  doi: 10.1016/j.knosys.2019.01.015
– ident: ref192
  doi: 10.1007/978-3-030-29894-4_52
– ident: ref21
  doi: 10.1109/TEVC.2019.2916183
– year: 2019
  ident: ref217
  article-title: Evaluating the search phase of neural architecture search
  publication-title: arXiv 1902 08142
– year: 2019
  ident: ref194
  article-title: The evolved transformer
  publication-title: arXiv 1901 11117
– year: 2018
  ident: ref42
  article-title: Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search
  publication-title: arXiv 1803 00370
– start-page: 136
  year: 2018
  ident: ref57
  article-title: Recognizing the order of four-scene comics by evolutionary deep learning
  publication-title: Proc Int Symp Distrib Comput Artif Intell
– volume: 1
  year: 1992
  ident: ref224
  publication-title: Genetic Programming On the Programming of Computers by Means of Natural Selection
– ident: ref52
  doi: 10.1088/1361-6501/aae5b2
– ident: ref141
  doi: 10.1109/CVPR.2015.7298594
– ident: ref91
  doi: 10.1145/3378184.3378187
– year: 2019
  ident: ref218
  article-title: Grid search, random search, genetic algorithm: A big comparison for NAS
  publication-title: arXiv 1912 06059
SSID ssj0000605649
Score 2.7213867
Snippet Deep neural networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 550
SubjectTerms Algorithms
Artificial neural networks
Computer architecture
Convolutional neural networks
Deep learning
Design
Evolutionary computation
evolutionary computation (EC)
evolutionary neural architecture search (NAS)
image classification
Neural networks
Optimization
Search problems
Statistics
Title A Survey on Evolutionary Neural Architecture Search
URI https://ieeexplore.ieee.org/document/9508774
https://www.ncbi.nlm.nih.gov/pubmed/34357870
https://www.proquest.com/docview/2773455373
https://www.proquest.com/docview/2559434709
Volume 34
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8QwEB7Ug-zF96O-qOBNu6Z5tkcRRUT3osLeSpImF6Ur61bQX2-SPkRR8VZokraZmc43k3kAHBlGWK5xmTjlhBIqeZ4ogtOEI60IwSZTNkT5jvjVA70es_EcnPS5MMaYEHxmhv4ynOWXE117V9mp71jq4Mo8zDvDrcnV6v0pyOFyHtAuTjlOMBHjLkcG5af3o9HNnbMGcTr0Hm2nQwewSCgJ_PpFJYUeK7_DzaB2LpfhtnvhJtrkcVjP1FC_f6vl-N8vWoGlFn_GZw3DrMKcqdZguevtELeivgYDj0KbIs7rQM7iu3r6at7iSRVfvLbcKqdvsa_tEZb7PI6ImwjmDXi4vLg_v0rabguJpqmYJVJxa3kmc8WoVIgqKjOeKlpabUtplC5RboR2Cs2qEin3pyCZ0JnNmGFI2ZxswkI1qcw2xAwzzI106E44664sM04M10hhaZGbgiNIuw0vdFuK3HfEeCqCSYLyItCr8PQqWnpFcNzPeW4Kcfw5et1vdj-y3ecI9jq6Fq2svhRYCEIZI4JEcNjfdlLmj05kZSa1G-MML0qoQHkEWw0_9Gt3bLTz8zN3YeBb1DeR3nuwMJvWZt8BmZk6CBz8AQuB6rE
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT9wwEB4BlWAvpQUKaWkbJG6QxfEzOSIE2sKyFxZpb5Ht2BeqLFo2SPTX13YeCFRQb5FiO4nnc-ab8XgG4NAwwnKNy8QpJ5RQyfNEEZwmHGlFCDaZsiHKd8JHt_RyxmYrcNyfhTHGhOAzM_SXYS-_nOvau8pOfMVSR1dW4YPT-yxtTmv1HhXkmDkPfBenHCeYiFl3SgblJ9PJZHzj7EGcDr1P22nRAawTSgJiXyilUGXlbcIZFM_FJlx3r9zEm9wN66Ua6j-vsjn-7zd9go8tA41PG8h8hhVTbcFmV90hbhf7Fgw8D23SOG8DOY1v6sWjeYrnVXz-2OJVLp5in90jDPe8IRE3Mcw7cHtxPj0bJW29hUTTVCwTqbi1PJO5YlQqRBWVGU8VLa22pTRKlyg3QjuVZlWJlPtXkEzozGbMMKRsTr7AWjWvzB7EDDPMjXT8Tjj7riwzTgzXSGFpkeuCI0i7CS90m4zc18T4XQSjBOVFkFfh5VW08orgqO9z36TieLf1tp_svmU7zxHsd3It2tX6UGAhiAMUESSCg_62W2d-80RWZl67Ns70ooQKlEew2-ChH7uD0dd_P_MnbIym1-Ni_Gty9Q0GvmB9E_e9D2vLRW2-O1qzVD8Cmv8Cc0Ht-g
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+on+Evolutionary+Neural+Architecture+Search&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Liu%2C+Yuqiao&rft.au=Sun%2C+Yanan&rft.au=Xue%2C+Bing&rft.au=Zhang%2C+Mengjie&rft.date=2023-02-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=2162-237X&rft.eissn=2162-2388&rft.volume=34&rft.issue=2&rft.spage=550&rft_id=info:doi/10.1109%2FTNNLS.2021.3100554&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon