Research Review for Broad Learning System: Algorithms, Theory, and Applications

In recent years, the appearance of the broad learning system (BLS) is poised to revolutionize conventional artificial intelligence methods. It represents a step toward building more efficient and effective machine-learning methods that can be extended to a broader range of necessary research fields....

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on cybernetics Ročník 52; číslo 9; s. 8922 - 8950
Hlavní autoři:	Gong, Xinrong, Zhang, Tong, Chen, C. L. Philip, Liu, Zhulin
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.09.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Artificial intelligence Biomedical engineering Broad learning system (BLS) classification Computer architecture Computer science Computer vision Data mining feature learning Knowledge engineering Learning systems Machine learning Natural language processing Neural networks regression research review semisupervised learning (SSL) Task analysis Training Unsupervised learning
ISSN:	2168-2267, 2168-2275, 2168-2275
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	In recent years, the appearance of the broad learning system (BLS) is poised to revolutionize conventional artificial intelligence methods. It represents a step toward building more efficient and effective machine-learning methods that can be extended to a broader range of necessary research fields. In this survey, we provide a comprehensive overview of the BLS in data mining and neural networks for the first time, focusing on summarizing various BLS methods from the aspects of its algorithms, theories, applications, and future open research questions. First, we introduce the basic pattern of BLS manifestation, the universal approximation capability, and essence from the theoretical perspective. Furthermore, we focus on BLS's various improvements based on the current state of the theoretical research, which further improves its flexibility, stability, and accuracy under general or specific conditions, including classification, regression, semisupervised, and unsupervised tasks. Due to its remarkable efficiency, impressive generalization performance, and easy extendibility, BLS has been applied in different domains. Next, we illustrate BLS's practical advances, such as computer vision, biomedical engineering, control, and natural language processing. Finally, the future open research problems and promising directions for BLSs are pointed out.
AbstractList	In recent years, the appearance of the broad learning system (BLS) is poised to revolutionize conventional artificial intelligence methods. It represents a step toward building more efficient and effective machine-learning methods that can be extended to a broader range of necessary research fields. In this survey, we provide a comprehensive overview of the BLS in data mining and neural networks for the first time, focusing on summarizing various BLS methods from the aspects of its algorithms, theories, applications, and future open research questions. First, we introduce the basic pattern of BLS manifestation, the universal approximation capability, and essence from the theoretical perspective. Furthermore, we focus on BLS’s various improvements based on the current state of the theoretical research, which further improves its flexibility, stability, and accuracy under general or specific conditions, including classification, regression, semisupervised, and unsupervised tasks. Due to its remarkable efficiency, impressive generalization performance, and easy extendibility, BLS has been applied in different domains. Next, we illustrate BLS’s practical advances, such as computer vision, biomedical engineering, control, and natural language processing. Finally, the future open research problems and promising directions for BLSs are pointed out. In recent years, the appearance of the broad learning system (BLS) is poised to revolutionize conventional artificial intelligence methods. It represents a step toward building more efficient and effective machine-learning methods that can be extended to a broader range of necessary research fields. In this survey, we provide a comprehensive overview of the BLS in data mining and neural networks for the first time, focusing on summarizing various BLS methods from the aspects of its algorithms, theories, applications, and future open research questions. First, we introduce the basic pattern of BLS manifestation, the universal approximation capability, and essence from the theoretical perspective. Furthermore, we focus on BLS's various improvements based on the current state of the theoretical research, which further improves its flexibility, stability, and accuracy under general or specific conditions, including classification, regression, semisupervised, and unsupervised tasks. Due to its remarkable efficiency, impressive generalization performance, and easy extendibility, BLS has been applied in different domains. Next, we illustrate BLS's practical advances, such as computer vision, biomedical engineering, control, and natural language processing. Finally, the future open research problems and promising directions for BLSs are pointed out.In recent years, the appearance of the broad learning system (BLS) is poised to revolutionize conventional artificial intelligence methods. It represents a step toward building more efficient and effective machine-learning methods that can be extended to a broader range of necessary research fields. In this survey, we provide a comprehensive overview of the BLS in data mining and neural networks for the first time, focusing on summarizing various BLS methods from the aspects of its algorithms, theories, applications, and future open research questions. First, we introduce the basic pattern of BLS manifestation, the universal approximation capability, and essence from the theoretical perspective. Furthermore, we focus on BLS's various improvements based on the current state of the theoretical research, which further improves its flexibility, stability, and accuracy under general or specific conditions, including classification, regression, semisupervised, and unsupervised tasks. Due to its remarkable efficiency, impressive generalization performance, and easy extendibility, BLS has been applied in different domains. Next, we illustrate BLS's practical advances, such as computer vision, biomedical engineering, control, and natural language processing. Finally, the future open research problems and promising directions for BLSs are pointed out.
Author	Chen, C. L. Philip Gong, Xinrong Zhang, Tong Liu, Zhulin
Author_xml	– sequence: 1 givenname: Xinrong orcidid: 0000-0001-5821-6283 surname: Gong fullname: Gong, Xinrong organization: School of Computer Science and Engineering, South China University of Technology, Guangzhou, China – sequence: 2 givenname: Tong orcidid: 0000-0002-7025-6365 surname: Zhang fullname: Zhang, Tong email: tony@scut.edu.cn organization: School of Computer Science and Engineering, South China University of Technology, Guangzhou, China – sequence: 3 givenname: C. L. Philip orcidid: 0000-0001-5451-7230 surname: Chen fullname: Chen, C. L. Philip organization: School of Computer Science and Engineering, South China University of Technology, Guangzhou, China – sequence: 4 givenname: Zhulin orcidid: 0000-0003-4145-823X surname: Liu fullname: Liu, Zhulin organization: School of Computer Science and Engineering, South China University of Technology, Guangzhou, China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/33729975$$D View this record in MEDLINE/PubMed
BookMark	eNp9kUtLAzEUhYMovn-ACBJw48LWvGYycdcWX1AQtC5chZi5YyMzk5pMlf57U1tduDCbGw7fudx7zx7abH0LCB1R0qeUqIvJ6HnYZ4TRPid5EsQG2mU0L3qMyWzz95_LHXQY4xtJr0iSKrbRDueSKSWzXXT_ABFMsFP8AB8OPnHlAx4Gb0o8Tnrr2lf8uIgdNJd4UL_64LppE8_xZAo-LM6xaUs8mM1qZ03nfBsP0FZl6giH67qPnq6vJqPb3vj-5m40GPesoFnXE8qYzMoyk5xKK4wolQVFVClAqbzKKsg5UJEDVxWTUKmc5QXJlACgklDC99HZqu8s-Pc5xE43Llqoa9OCn0fNMsIKIiXjCT39g775eWjTdJpJIohSjNNEnayp-UsDpZ4F15iw0D-nSoBcATb4GANU2rrue-kuGFdrSvQyF73MRS9z0etckpP-cf40_89zvPI4APjlFV_uRPgXckeVXQ
CODEN	ITCEB8
CitedBy_id	crossref_primary_10_1109_ACCESS_2021_3084610 crossref_primary_10_1016_j_ejrh_2025_102708 crossref_primary_10_1016_j_ifacol_2024_08_320 crossref_primary_10_1190_geo2024_0393_1 crossref_primary_10_1016_j_engappai_2024_107856 crossref_primary_10_1016_j_ins_2023_02_048 crossref_primary_10_1109_TFUZZ_2023_3330883 crossref_primary_10_3390_photonics12070737 crossref_primary_10_1109_TCSS_2021_3135425 crossref_primary_10_1109_TCYB_2021_3113709 crossref_primary_10_1109_TCSS_2022_3202249 crossref_primary_10_1049_esi2_12178 crossref_primary_10_1016_j_engappai_2024_108433 crossref_primary_10_1016_j_microc_2025_112840 crossref_primary_10_1029_2022JB025505 crossref_primary_10_1016_j_asoc_2025_113789 crossref_primary_10_1109_TCSS_2022_3188891 crossref_primary_10_1016_j_eswa_2023_121159 crossref_primary_10_1109_ACCESS_2021_3077764 crossref_primary_10_1109_JAS_2024_124821 crossref_primary_10_1109_TASE_2025_3579737 crossref_primary_10_1109_TVT_2024_3497582 crossref_primary_10_1007_s10489_024_05637_1 crossref_primary_10_1016_j_engappai_2023_107508 crossref_primary_10_1002_ett_70242 crossref_primary_10_3390_coatings13030513 crossref_primary_10_1109_TPAMI_2023_3262853 crossref_primary_10_1061_JCEMD4_COENG_13170 crossref_primary_10_1109_JSEN_2024_3492041 crossref_primary_10_1109_TFUZZ_2025_3543369 crossref_primary_10_1109_TCSS_2024_3386621 crossref_primary_10_1109_TNNLS_2024_3491101 crossref_primary_10_1016_j_knosys_2025_113765 crossref_primary_10_1016_j_asoc_2025_113679 crossref_primary_10_1088_1361_6501_ad7e46 crossref_primary_10_1109_TAFFC_2024_3392791 crossref_primary_10_1109_TCYB_2023_3267947 crossref_primary_10_3390_su16093621 crossref_primary_10_1109_TCCN_2024_3522143 crossref_primary_10_1109_TFUZZ_2025_3530458 crossref_primary_10_1109_TAI_2022_3162570 crossref_primary_10_1016_j_imavis_2024_104919 crossref_primary_10_1016_j_patcog_2025_111886 crossref_primary_10_1109_TAI_2021_3105621 crossref_primary_10_1088_1742_6596_2861_1_012010 crossref_primary_10_1109_TNNLS_2023_3291793 crossref_primary_10_1093_tse_tdac065 crossref_primary_10_1109_JSEN_2025_3574436 crossref_primary_10_1016_j_conengprac_2024_105850 crossref_primary_10_1038_s41598_025_92178_3 crossref_primary_10_1016_j_dsp_2024_104869 crossref_primary_10_1109_TIM_2022_3144232 crossref_primary_10_1109_TCYB_2023_3235496 crossref_primary_10_1109_TKDE_2021_3137792 crossref_primary_10_1111_mice_13305 crossref_primary_10_3390_math13142274 crossref_primary_10_1016_j_isprsjprs_2025_08_020 crossref_primary_10_1109_TAFFC_2022_3170369 crossref_primary_10_1109_TNNLS_2023_3256999 crossref_primary_10_1109_TSMC_2024_3487776 crossref_primary_10_1007_s40747_023_01154_9 crossref_primary_10_1142_S0218126625502755 crossref_primary_10_1109_LSP_2023_3263433 crossref_primary_10_3390_e25020338 crossref_primary_10_1016_j_conengprac_2025_106278 crossref_primary_10_1109_TKDE_2024_3390135 crossref_primary_10_1109_TNNLS_2022_3222265 crossref_primary_10_3390_math12132147 crossref_primary_10_1007_s40815_024_01804_1 crossref_primary_10_1088_1361_6501_adb2b2 crossref_primary_10_1016_j_asoc_2025_113543 crossref_primary_10_1016_j_asoc_2024_112552 crossref_primary_10_1016_j_medengphy_2024_104267 crossref_primary_10_1109_TCSS_2021_3130401 crossref_primary_10_1109_TII_2023_3345449 crossref_primary_10_1007_s11760_025_04713_4 crossref_primary_10_1088_1361_6501_ad3d00 crossref_primary_10_1109_TCSS_2022_3223516 crossref_primary_10_1109_TFUZZ_2024_3400898 crossref_primary_10_1016_j_jprocont_2024_103235 crossref_primary_10_1016_j_neucom_2025_130544 crossref_primary_10_1016_j_swevo_2025_102038 crossref_primary_10_1016_j_ins_2024_120876 crossref_primary_10_1109_JAS_2024_124557 crossref_primary_10_1109_TNNLS_2023_3294788 crossref_primary_10_1016_j_bspc_2024_106010 crossref_primary_10_1109_TCYB_2024_3393020 crossref_primary_10_1155_int_1649220 crossref_primary_10_1016_j_knosys_2023_110853 crossref_primary_10_1016_j_measurement_2024_114785 crossref_primary_10_1109_TCYB_2024_3401014 crossref_primary_10_1007_s13042_023_01964_w crossref_primary_10_3389_fnins_2023_1137567 crossref_primary_10_1109_TITS_2023_3321384 crossref_primary_10_1109_TVT_2024_3390571 crossref_primary_10_3390_electronics12143118 crossref_primary_10_1109_TNNLS_2025_3529219 crossref_primary_10_3390_math11041014 crossref_primary_10_1109_ACCESS_2024_3509923 crossref_primary_10_1080_00207179_2024_2373802 crossref_primary_10_1109_TCSS_2023_3298324 crossref_primary_10_1145_3639063 crossref_primary_10_1109_TITS_2021_3140112 crossref_primary_10_1016_j_conengprac_2025_106284 crossref_primary_10_1109_TIM_2023_3259022 crossref_primary_10_1016_j_knosys_2024_111397 crossref_primary_10_1016_j_lwt_2024_116570 crossref_primary_10_1007_s00521_024_09449_9 crossref_primary_10_1016_j_knosys_2025_113297 crossref_primary_10_1109_TCSI_2022_3189221 crossref_primary_10_3389_fnins_2022_1046268 crossref_primary_10_1016_j_isatra_2025_02_027 crossref_primary_10_1109_TCYB_2023_3271314 crossref_primary_10_1016_j_measurement_2024_116437 crossref_primary_10_1155_2022_7094539 crossref_primary_10_1109_TCYB_2023_3269773 crossref_primary_10_1016_j_knosys_2024_112923 crossref_primary_10_1109_TCSS_2022_3169132 crossref_primary_10_1088_1361_6501_ad26c8 crossref_primary_10_3389_fnins_2023_1137557 crossref_primary_10_1016_j_engappai_2024_108617 crossref_primary_10_1109_TIM_2022_3227995 crossref_primary_10_1088_1361_6501_acc47b crossref_primary_10_3390_math11194087 crossref_primary_10_1016_j_engappai_2024_109155 crossref_primary_10_1007_s10489_023_04931_8 crossref_primary_10_1109_TNNLS_2023_3264617 crossref_primary_10_1109_TNNLS_2025_3548941 crossref_primary_10_1007_s11432_022_3560_8 crossref_primary_10_1109_TNNLS_2024_3396659 crossref_primary_10_3390_electronics13153014 crossref_primary_10_1016_j_neucom_2025_129421 crossref_primary_10_1109_TNNLS_2024_3416191 crossref_primary_10_1002_rnc_5693 crossref_primary_10_1080_10589759_2025_2521359 crossref_primary_10_1109_TNNLS_2023_3265662 crossref_primary_10_1109_TFUZZ_2022_3215566 crossref_primary_10_1109_TSMC_2022_3211519 crossref_primary_10_1109_TIE_2024_3454429 crossref_primary_10_1109_TIFS_2024_3524157 crossref_primary_10_1109_JIOT_2023_3257479 crossref_primary_10_3233_JIFS_235725 crossref_primary_10_1109_TKDE_2023_3271120 crossref_primary_10_1016_j_foodchem_2025_143831 crossref_primary_10_1007_s10845_022_02054_4 crossref_primary_10_1016_j_aei_2023_102255 crossref_primary_10_1016_j_eswa_2023_121857 crossref_primary_10_1016_j_neucom_2024_127833 crossref_primary_10_1016_j_neucom_2024_127277 crossref_primary_10_1109_JAS_2024_124929 crossref_primary_10_1016_j_ins_2025_122485 crossref_primary_10_1109_TSTE_2025_3549225 crossref_primary_10_1109_TCYB_2024_3403927 crossref_primary_10_1109_TITS_2023_3266256 crossref_primary_10_1007_s11036_024_02325_9 crossref_primary_10_1109_TETCI_2022_3146983 crossref_primary_10_1109_TETCI_2024_3378599 crossref_primary_10_1007_s10462_025_11324_5 crossref_primary_10_1007_s10489_022_04082_2 crossref_primary_10_1016_j_conengprac_2024_106174 crossref_primary_10_1109_TBDATA_2024_3423677 crossref_primary_10_1109_TITS_2023_3274256 crossref_primary_10_1109_TAI_2024_3403953 crossref_primary_10_3390_math13050797 crossref_primary_10_3390_su15010380 crossref_primary_10_1109_TCYB_2025_3549479 crossref_primary_10_1016_j_knosys_2025_113346 crossref_primary_10_3390_a18030130 crossref_primary_10_1109_TII_2024_3361017 crossref_primary_10_1007_s11517_024_03246_1 crossref_primary_10_1016_j_asoc_2025_113577 crossref_primary_10_1109_TCYB_2023_3341804 crossref_primary_10_1016_j_knosys_2025_113184 crossref_primary_10_1109_TMECH_2023_3277102 crossref_primary_10_3390_app15126454 crossref_primary_10_3390_s24113621 crossref_primary_10_1109_TII_2024_3438234 crossref_primary_10_1109_TETCI_2024_3370005
Cites_doi	10.1109/SBCCI.2003.1232813 10.1109/ICARM49381.2020.9195332 10.1109/ACCESS.2020.3032515 10.1109/CVPR.2019.00521 10.1109/72.536316 10.1016/j.molcel.2011.08.018 10.1177/1550147720907830 10.1007/11893295_122 10.1109/5.58326 10.1109/CAC48633.2019.8997269 10.3389/fnins.2016.00508 10.1109/21.97471 10.1109/CVPR.2009.5206848 10.1109/EMBC.2018.8512990 10.1109/ACCESS.2019.2908015 10.1109/TCYB.2020.2978500 10.1162/089976603321780317 10.1016/j.neunet.2019.05.009 10.3390/rs10050685 10.1038/s41586-019-1424-8 10.1007/978-981-13-7403-6_31 10.1155/2020/7463291 10.1109/SMC.2018.00596 10.1103/RevModPhys.34.123 10.1109/21.260667 10.1146/annurev-neuro-062111-150525 10.1109/TCSVT.2020.2974811 10.1109/TNN.2007.903150 10.1109/SURV.2009.090205 10.1109/SMC.2018.00383 10.1016/B978-0-12-741252-8.50010-8 10.1007/978-94-009-1740-8 10.1016/j.neucom.2019.08.084 10.1109/ACCESS.2019.2895909 10.1109/ACCESS.2019.2905528 10.1109/TSMC.2020.3006124 10.1109/SMC42975.2020.9282871 10.1145/2939672.2939785 10.1109/ISCAS.2019.8702583 10.1080/02533839.2019.1694442 10.1038/nn.2276 10.1109/ICCT46805.2019.8947271 10.1007/978-3-319-95933-7_60 10.1109/CYBER46603.2019.9066676 10.1109/34.990138 10.1109/TPAMI.2007.250598 10.1109/TIE.2019.2931255 10.1109/ACCESS.2020.3040340 10.1109/ICICIP47338.2019.9012200 10.1007/978-981-13-3549-5_2 10.1109/SIPROCESS.2019.8868769 10.1109/SMC.2018.00328 10.1016/j.neunet.2020.05.031 10.1007/978-3-030-22971-9_20 10.1109/TCYB.2020.2969705 10.1142/S0219691319500012 10.1109/ACCESS.2020.3006584 10.1038/323533a0 10.1007/978-3-030-26766-7_36 10.1613/jair.301 10.1109/JAS.2017.7510820 10.1016/j.engappai.2020.104139 10.1109/ICPICS50287.2020.9202108 10.1109/TNNLS.2020.3009417 10.1145/3383972.3384054 10.1109/3477.979966 10.1109/CCDC.2019.8832716 10.1109/TNNLS.2017.2648880 10.1109/EI247390.2019.9062263 10.1016/j.neucom.2019.04.017 10.1109/BIBM.2018.8621147 10.1007/s12559-019-09698-0 10.1016/0893-6080(89)90044-0 10.1186/s12864-016-2931-8 10.1109/3477.740166 10.1109/SPAC46244.2018.8965520 10.1109/TSMC.2019.2956022 10.1016/j.robot.2020.103441 10.1109/TAFFC.2019.2937768 10.1109/ISCAS45731.2020.9180445 10.1109/TSMC.2020.2995205 10.1109/JSTSP.2016.2520912 10.1109/TGRS.2009.2037898 10.1016/j.ins.2015.11.039 10.1007/s11263-007-0075-7 10.1016/s0893-6080(05)80131-5 10.1016/j.asoc.2019.01.015 10.1109/TGRS.2014.2381602 10.1061/AJRUA6.0001066 10.7763/IJCTE.2013.V5.795 10.1016/S0031-3203(01)00203-5 10.1016/j.snb.2007.09.060 10.1109/LGRS.2019.2913999 10.1109/MCOM.2017.1600400 10.1109/CYBER46603.2019.9066761 10.1109/SPAC46244.2018.8965603 10.1145/3093337.3037698 10.1109/2.144401 10.1109/TCYB.2014.2307349 10.1109/TSP.2013.2254478 10.1162/neco.1995.7.2.219 10.1109/IROS.2003.1249705 10.1109/TCYB.2021.3050508 10.1007/springerreference_5816 10.1109/TNNLS.2017.2716952 10.1109/72.143378 10.1109/ICCSS.2017.8091501 10.1109/ACCESS.2020.3003916 10.1109/TAMD.2015.2431497 10.1109/ACCESS.2019.2943188 10.1109/ACCESS.2019.2929094 10.1109/TSMCB.2009.2013721 10.1109/BIBM47256.2019.8983025 10.1109/TKDE.2020.3047857 10.1038/nature10887 10.1037/h0042519 10.1016/j.inffus.2017.02.007 10.1126/science.aaf2654 10.5555/2969033.2969153 10.1038/s41563-019-0291-x 10.1109/TEC.2005.847955 10.1109/CAC48633.2019.8996625 10.1109/TITS.2019.2897583 10.1109/COMST.2017.2682318 10.1109/TNNLS.2017.2712793 10.1007/s40815-020-00913-x 10.1109/SEC.2018.00040 10.1126/science.1127647 10.1109/ROBIO49542.2019.8961680 10.4324/9781410605337-29 10.1109/YAC.2017.7967609 10.1134/s1054661816010065 10.1109/LSP.2006.882107 10.1007/s11042-020-09303-9 10.1109/SMC42975.2020.9283159 10.1109/SPAC.2017.8304274 10.1109/TSMC.1985.6313399 10.1109/TSMC.2020.2969686 10.1109/CVPRW.2010.5543262 10.1109/CAC48633.2019.8997252 10.1109/JPROC.2019.2918951 10.1109/JBHI.2017.2688239 10.5555/2999134.2999257 10.1162/neco.1997.9.8.1735 10.1109/ICECCE49384.2020.9179272 10.1109/LGRS.2019.2907598 10.1109/JSEE.2012.00015 10.1109/TNN.2006.889496 10.1109/TCYB.2019.2934823 10.3390/en12244750 10.1109/TNNLS.2020.3004634 10.1109/ICCChina.2019.8855958 10.1016/j.neucom.2017.08.043 10.1109/ICDM.2001.989589 10.3390/s17061356 10.1109/CCDC.2019.8833310 10.1109/TIE.2019.2950853 10.1016/j.jpowsour.2020.228581 10.1109/TIP.2017.2756450 10.1146/annurev.ne.13.030190.000325 10.1109/TSMC.2020.2964684 10.1016/j.knosys.2019.105295 10.1109/SMC.2019.8914249 10.1088/1361-6501/ab8fee 10.1109/TCYB.2018.2863020 10.1016/j.maturitas.2009.07.014 10.1109/ICCSS48103.2019.9115436 10.1016/0925-2312(94)90053-1 10.1007/978-3-540-45167-9_12 10.1109/TIT.2015.2472522 10.1049/iet-com.2012.0222 10.1109/TFUZZ.2020.3009757 10.1109/ACCESS.2019.2950240 10.1109/EMBC.2019.8856666 10.1109/SMC.2019.8914328 10.1109/ACCESS.2018.2886202 10.1007/s40747-020-00139-2 10.1109/TGRS.2016.2524557 10.1145/3364836.3364890 10.1109/ACCESS.2020.2978109 10.1109/SMC.2018.00162 10.1109/TNNLS.2019.2935033 10.23919/CCC50068.2020.9188835 10.1109/72.392253 10.1145/3395245.3395252 10.1007/s11069-009-9392-1 10.1109/CompComm.2018.8780984 10.1109/ICARM.2019.8833648 10.1109/MCOM.2007.4378332 10.1145/3319921.3319955 10.1109/TNNLS.2020.3004253 10.1111/mice.12494 10.1109/5.726791 10.1109/CAC.2018.8623741 10.1109/ICIEA49774.2020.9102007 10.1109/CVPR.2016.90 10.1561/2000000039 10.1016/j.asoc.2020.106698 10.1109/JSTARS.2020.3001198 10.1126/science.1211095 10.1109/TIP.2012.2235849 10.1038/nrn2148 10.1109/CCDC.2019.8832560 10.1109/SPAC49953.2019.237871 10.1109/72.80202 10.1109/SMC.2018.00716 10.1016/j.comnet.2010.05.010 10.1109/72.471375 10.1109/TCYB.2018.2857815 10.1109/ICARCV.2018.8581232 10.1109/TSMC.2019.2958382 10.1016/j.adhoc.2012.02.016 10.1109/ICPR.1992.201708 10.1109/ACCESS.2019.2938349 10.3390/electronics8111273 10.1109/TCYB.2018.2875983 10.1016/j.neucom.2019.01.073 10.1007/bf00058655 10.1109/JIOT.2020.2980198 10.1162/153244303322753616 10.1109/ACCESS.2018.2885164 10.1109/IWCMC48107.2020.9148092 10.1155/2007/12725 10.2200/S00196ED1V01Y200906AIM006 10.1016/j.neucom.2019.10.059 10.1007/s00221-001-0932-5 10.1016/j.ymssp.2020.106738 10.1016/j.neunet.2014.10.001 10.1109/TKDE.2018.2866149 10.1109/TNNLS.2018.2866622 10.1016/j.neunet.2005.04.006 10.1109/SMC.2018.00719 10.1109/CVPR.2017.243 10.1109/TSMC.2020.3043147 10.1109/TCSI.2019.2959886 10.1007/s11263-015-0816-y 10.1109/TCYB.2020.2998984 10.1109/TMI.2015.2458702 10.1109/IJCNN.2019.8852226 10.1109/TSMC.2018.2884996 10.1016/j.neucom.2020.05.025 10.1109/TCYB.2020.3015749 10.1109/TNNLS.2015.2508926 10.1145/1361684.1361686 10.1109/TGRS.2017.2689805 10.1007/BFb0080116 10.1038/nature14236 10.1023/A:1018628609742 10.1109/TMM.2020.2987703 10.1016/j.measurement.2016.04.007 10.1534/genetics.112.146704 10.1109/TNSRE.2020.3003342 10.1016/j.neucom.2007.07.025 10.1007/978-3-319-70139-4 10.1002/stc.2571 10.1016/j.neuron.2016.10.050 10.1109/TBME.2010.2082539 10.1109/TCYB.2016.2588526 10.1109/MNET.001.1900078 10.1088/1741-2560/12/3/036009 10.1007/s40815-019-00739-2 10.1080/00207179208934315 10.1109/59.589648 10.1109/iThings/GreenCom/CPSCom/SmartData.2019.00091 10.1038/s41592-019-0330-1 10.1007/978-1-4419-9326-7_1 10.1016/j.knosys.2020.106319 10.1007/978-3-030-04224-0_6 10.1016/0020-0190(87)90114-1 10.1016/j.ins.2015.09.025 10.1016/j.neucom.2014.08.098 10.1109/SPAC46244.2018.8965623 10.1109/ICACTE.2010.5579543 10.1109/DASC/PiCom/CBDCom/CyberSciTech.2019.00053 10.1145/3318299.3318318 10.1109/CCNC.2017.7983103 10.1038/nature14539 10.1109/LCOMM.2019.2952072 10.1177/1475921720916923 10.3390/app9061111 10.1109/TCSII.2012.2204112 10.1016/S0925-2312(99)00127-7 10.1109/SPAC46244.2018.8965489 10.1109/TSMCC.2012.2189204 10.1007/978-3-319-46487-9_6 10.1109/TSMC.2019.2957818 10.1016/j.neucom.2005.12.126 10.1162/neco.2006.18.7.1527 10.1109/TKDE.2008.239 10.1007/s11432-017-9421-3 10.1212/01.wnl.0000243257.85592.9a 10.1002/adma.201505898 10.1007/s11042-019-07979-2 10.1109/TCYB.2020.2988792 10.1109/SSCI44817.2019.9002711 10.1109/TITS.2020.3011937 10.1093/nar/28.1.235 10.1109/SMC.2019.8914437 10.1007/978-3-030-01313-4_1 10.1016/j.neucom.2018.09.028
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION NPM 7SC 7SP 7TB 8FD F28 FR3 H8D JQ2 L7M L~C L~D 7X8
DOI	10.1109/TCYB.2021.3061094
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitle	CrossRef PubMed Aerospace Database 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 ANTE: Abstracts in New Technology & Engineering Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitleList	Aerospace Database MEDLINE - Academic PubMed
Database_xml	– sequence: 1 dbid: NPM name: PubMed 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://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Sciences (General) Computer Science
EISSN	2168-2275
EndPage	8950
ExternalDocumentID	33729975 10_1109_TCYB_2021_3061094 9380770
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 62076102; U1813203; U1801262 funderid: 10.13039/501100001809 – fundername: National Key Research and Development Program of China grantid: 2019YFA0706200; 2019YFB1703600 funderid: 10.13039/501100012166 – fundername: National Natural Science Foundation of Guangdong for Distinguished Young Scholar grantid: 2020B1515020041 funderid: 10.13039/501100003453 – fundername: Science and Technology Major Project of Guangzhou grantid: 202007030006 – fundername: Science and Technology Program of Guangzhou grantid: 202002030250 – fundername: Guangdong–Hong Kong–Macao Greater Bay Area Center for Brain Science and Brain-Inspired Intelligence Fund grantid: 2019016
GroupedDBID	0R~ 4.4 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK AENEX AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD HZ~ IFIPE IPLJI JAVBF M43 O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION NPM 7SC 7SP 7TB 8FD F28 FR3 H8D JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c415t-49aa5c7d57317c4a4d9ce909d4e996f5fe63e146e39f27ef962680594ee170103
IEDL.DBID	RIE
ISICitedReferencesCount	249
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000732872900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2168-2267 2168-2275
IngestDate	Sun Nov 09 13:51:06 EST 2025 Sun Nov 09 08:53:36 EST 2025 Mon Jul 21 06:03:28 EDT 2025 Tue Nov 18 22:16:48 EST 2025 Sat Nov 29 08:02:48 EST 2025 Wed Aug 27 02:03:47 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	9
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-c415t-49aa5c7d57317c4a4d9ce909d4e996f5fe63e146e39f27ef962680594ee170103
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 ObjectType-Review-3 content type line 23
ORCID	0000-0002-7025-6365 0000-0001-5451-7230 0000-0001-5821-6283 0000-0003-4145-823X
PMID	33729975
PQID	2704099231
PQPubID	85422
PageCount	29
ParticipantIDs	crossref_citationtrail_10_1109_TCYB_2021_3061094 ieee_primary_9380770 pubmed_primary_33729975 proquest_journals_2704099231 proquest_miscellaneous_2502807723 crossref_primary_10_1109_TCYB_2021_3061094
PublicationCentury	2000
PublicationDate	2022-09-01
PublicationDateYYYYMMDD	2022-09-01
PublicationDate_xml	– month: 09 year: 2022 text: 2022-09-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: Piscataway
PublicationTitle	IEEE transactions on cybernetics
PublicationTitleAbbrev	TCYB
PublicationTitleAlternate	IEEE Trans Cybern
PublicationYear	2022
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	ref57 ref207 ref208 ref59 ref205 ref58 ref206 ref53 ref203 ref52 ref204 ref55 ref201 ref54 ref202 Luo (ref181) ref209 Belkin (ref113) 2006; 7 Lan (ref291) ref210 ref211 ref51 ref50 ref46 ref218 ref45 ref219 ref48 ref216 ref47 ref217 ref42 ref214 ref41 ref215 ref44 ref212 ref213 Simonyan (ref7) 2014 Lu (ref282) 2017 ref49 ref8 ref9 ref4 ref3 ref6 ref100 ref221 ref101 ref222 ref40 ref220 ref35 ref306 ref34 ref307 ref37 ref304 ref36 ref305 ref31 Dy (ref121) 2004; 5 ref302 ref30 ref303 ref33 ref300 ref32 ref301 ref39 ref38 ref308 ref309 ref310 ref24 Cui (ref191) ref317 ref23 ref26 ref315 ref25 ref316 ref20 ref313 ref314 ref22 ref311 ref21 ref312 ref29 ref200 ref128 ref249 ref129 ref97 ref126 ref247 ref96 ref127 ref248 ref99 ref124 ref245 ref98 ref125 Snell (ref131) 2017 ref246 ref93 ref133 ref254 ref92 ref134 ref255 ref95 ref252 ref94 ref132 ref253 ref250 ref130 ref251 ref91 ref90 ref89 ref139 ref86 ref137 ref258 ref85 ref138 ref259 ref88 ref135 ref256 ref87 ref136 ref257 ref82 ref144 ref265 ref145 ref266 ref84 ref142 ref263 ref83 ref143 ref264 ref140 ref261 ref141 ref262 ref80 ref260 ref79 ref108 ref229 ref78 ref106 ref227 ref107 ref228 ref75 ref104 ref225 ref74 ref105 ref226 ref77 ref102 ref223 Fernández-Redondo (ref287) ref76 ref103 ref224 ref71 ref111 ref232 ref70 ref112 ref233 ref73 ref230 ref72 ref110 ref231 ref68 ref119 ref67 ref117 ref238 ref69 ref118 ref239 ref64 ref115 ref236 ref63 ref116 ref237 ref66 ref234 ref65 ref114 ref235 ref60 ref122 ref243 ref123 ref244 ref62 ref120 ref241 ref61 ref242 ref240 ref168 ref289 ref169 Muthuramalingam (ref276) 2008; 4 ref290 ref170 ref177 ref298 ref178 ref175 ref296 ref176 ref297 ref173 ref294 ref174 ref295 ref171 ref292 ref172 ref293 Zhu (ref109) 2005 ref179 ref180 Salakhutdinov (ref5) ref188 ref189 ref186 ref187 ref184 ref185 ref182 ref183 ref148 ref269 ref149 ref146 ref267 ref147 ref268 Tong (ref28) 2002; 2 Zhang (ref43) 2015 ref155 ref156 ref277 ref153 ref274 ref154 ref275 ref151 ref272 ref152 ref273 ref270 ref150 ref271 ref159 ref157 ref278 ref158 ref279 ref280 ref166 ref167 ref288 ref164 ref285 ref165 ref286 ref162 ref283 ref163 ref160 ref281 ref161 ref13 ref12 ref15 ref14 ref11 ref10 ref17 ref16 ref19 ref18 Suykens (ref27) 1999; 9 Feng (ref81) 2018; 75 Hinton (ref299); 656 ref2 ref1 ref192 ref190 ref199 ref197 ref198 ref195 ref196 Lin (ref56) 2010 ref193 ref194 Rahimi (ref284) 2008
References_xml	– ident: ref127 doi: 10.1109/SBCCI.2003.1232813 – ident: ref148 doi: 10.1109/ICARM49381.2020.9195332 – ident: ref174 doi: 10.1109/ACCESS.2020.3032515 – ident: ref110 doi: 10.1109/CVPR.2019.00521 – ident: ref26 doi: 10.1109/72.536316 – ident: ref239 doi: 10.1016/j.molcel.2011.08.018 – volume: 75 start-page: 25 volume-title: Diabetes year: 2018 ident: ref81 article-title: Performance analysis of fuzzy BLS using different cluster methods for classification – ident: ref154 doi: 10.1177/1550147720907830 – ident: ref275 doi: 10.1007/11893295_122 – ident: ref59 doi: 10.1109/5.58326 – ident: ref190 doi: 10.1109/CAC48633.2019.8997269 – ident: ref301 doi: 10.3389/fnins.2016.00508 – ident: ref292 doi: 10.1109/21.97471 – ident: ref67 doi: 10.1109/CVPR.2009.5206848 – ident: ref182 doi: 10.1109/EMBC.2018.8512990 – ident: ref206 doi: 10.1109/ACCESS.2019.2908015 – ident: ref106 doi: 10.1109/TCYB.2020.2978500 – ident: ref91 doi: 10.1162/089976603321780317 – ident: ref96 doi: 10.1016/j.neunet.2019.05.009 – ident: ref114 doi: 10.3390/rs10050685 – ident: ref281 doi: 10.1038/s41586-019-1424-8 – ident: ref170 doi: 10.1007/978-981-13-7403-6_31 – ident: ref227 doi: 10.1155/2020/7463291 – ident: ref54 doi: 10.1109/SMC.2018.00596 – ident: ref47 doi: 10.1103/RevModPhys.34.123 – ident: ref269 doi: 10.1109/21.260667 – ident: ref296 doi: 10.1146/annurev-neuro-062111-150525 – ident: ref212 doi: 10.1109/TCSVT.2020.2974811 – ident: ref11 doi: 10.1109/TNN.2007.903150 – ident: ref253 doi: 10.1109/SURV.2009.090205 – volume: 2 start-page: 45 year: 2002 ident: ref28 article-title: Support vector machine active learning with applications to text classification publication-title: J. Mach. Learn. Res. – ident: ref80 doi: 10.1109/SMC.2018.00383 – ident: ref298 doi: 10.1016/B978-0-12-741252-8.50010-8 – ident: ref49 doi: 10.1007/978-94-009-1740-8 – ident: ref101 doi: 10.1016/j.neucom.2019.08.084 – ident: ref223 doi: 10.1109/ACCESS.2019.2895909 – ident: ref142 doi: 10.1109/ACCESS.2019.2905528 – ident: ref244 doi: 10.1109/TSMC.2020.3006124 – ident: ref29 doi: 10.1109/SMC42975.2020.9282871 – ident: ref98 doi: 10.1145/2939672.2939785 – ident: ref204 doi: 10.1109/ISCAS.2019.8702583 – ident: ref216 doi: 10.1080/02533839.2019.1694442 – ident: ref300 doi: 10.1038/nn.2276 – ident: ref207 doi: 10.1109/ICCT46805.2019.8947271 – ident: ref184 doi: 10.1007/978-3-319-95933-7_60 – ident: ref147 doi: 10.1109/CYBER46603.2019.9066676 – ident: ref120 doi: 10.1109/34.990138 – ident: ref92 doi: 10.1109/TPAMI.2007.250598 – ident: ref74 doi: 10.1109/TIE.2019.2931255 – ident: ref186 doi: 10.1109/ACCESS.2020.3040340 – ident: ref220 doi: 10.1109/ICICIP47338.2019.9012200 – ident: ref146 doi: 10.1007/978-981-13-3549-5_2 – ident: ref72 doi: 10.1109/SIPROCESS.2019.8868769 – ident: ref143 doi: 10.1109/SMC.2018.00328 – ident: ref225 doi: 10.1016/j.neunet.2020.05.031 – ident: ref317 doi: 10.1007/978-3-030-22971-9_20 – ident: ref63 doi: 10.1109/TCYB.2020.2969705 – ident: ref149 doi: 10.1142/S0219691319500012 – ident: ref123 doi: 10.1109/ACCESS.2020.3006584 – ident: ref14 doi: 10.1038/323533a0 – ident: ref183 doi: 10.1007/978-3-030-26766-7_36 – ident: ref262 doi: 10.1613/jair.301 – ident: ref265 doi: 10.1109/JAS.2017.7510820 – ident: ref228 doi: 10.1016/j.engappai.2020.104139 – ident: ref164 doi: 10.1109/ICPICS50287.2020.9202108 – ident: ref79 doi: 10.1109/TNNLS.2020.3009417 – ident: ref162 doi: 10.1145/3383972.3384054 – ident: ref35 doi: 10.1109/3477.979966 – start-page: 4077 volume-title: Advances in Neural Information Processing Systems year: 2017 ident: ref131 article-title: Prototypical networks for few-shot learning – ident: ref188 doi: 10.1109/CCDC.2019.8832716 – ident: ref57 doi: 10.1109/TNNLS.2017.2648880 – ident: ref192 doi: 10.1109/EI247390.2019.9062263 – ident: ref39 doi: 10.1016/j.neucom.2019.04.017 – ident: ref234 doi: 10.1109/BIBM.2018.8621147 – volume: 656 start-page: 1 volume-title: Proc. NIPS Deep Learn. Workshop ident: ref299 article-title: How to do backpropagation in a brain – ident: ref105 doi: 10.1007/s12559-019-09698-0 – ident: ref12 doi: 10.1016/0893-6080(89)90044-0 – ident: ref102 doi: 10.1186/s12864-016-2931-8 – ident: ref25 doi: 10.1109/3477.740166 – ident: ref165 doi: 10.1109/SPAC46244.2018.8965520 – ident: ref175 doi: 10.1109/TSMC.2019.2956022 – ident: ref135 doi: 10.1016/j.robot.2020.103441 – ident: ref136 doi: 10.1109/TAFFC.2019.2937768 – ident: ref203 doi: 10.1109/ISCAS45731.2020.9180445 – start-page: 1536 volume-title: Proc. IEEE 12th Asian Control Conf. (ASCC) ident: ref191 article-title: Spatio-temporal broad learning networks for traffic speed prediction – ident: ref46 doi: 10.1109/TSMC.2020.2995205 – ident: ref260 doi: 10.1109/JSTSP.2016.2520912 – ident: ref111 doi: 10.1109/TGRS.2009.2037898 – ident: ref15 doi: 10.1016/j.ins.2015.11.039 – ident: ref23 doi: 10.1007/s11263-007-0075-7 – ident: ref10 doi: 10.1016/s0893-6080(05)80131-5 – ident: ref100 doi: 10.1016/j.asoc.2019.01.015 – ident: ref115 doi: 10.1109/TGRS.2014.2381602 – ident: ref198 doi: 10.1061/AJRUA6.0001066 – ident: ref274 doi: 10.7763/IJCTE.2013.V5.795 – ident: ref237 doi: 10.1016/S0031-3203(01)00203-5 – ident: ref65 doi: 10.1016/j.snb.2007.09.060 – ident: ref163 doi: 10.1109/LGRS.2019.2913999 – ident: ref254 doi: 10.1109/MCOM.2017.1600400 – ident: ref153 doi: 10.1109/CYBER46603.2019.9066761 – ident: ref194 doi: 10.1109/SPAC46244.2018.8965603 – ident: ref313 doi: 10.1145/3093337.3037698 – ident: ref13 doi: 10.1109/2.144401 – ident: ref129 doi: 10.1109/TCYB.2014.2307349 – ident: ref126 doi: 10.1109/TSP.2013.2254478 – ident: ref50 doi: 10.1162/neco.1995.7.2.219 – ident: ref88 doi: 10.1109/IROS.2003.1249705 – ident: ref134 doi: 10.1109/TCYB.2021.3050508 – ident: ref310 doi: 10.1007/springerreference_5816 – ident: ref17 doi: 10.1109/TNNLS.2017.2716952 – ident: ref288 doi: 10.1109/72.143378 – ident: ref122 doi: 10.1109/ICCSS.2017.8091501 – volume: 7 start-page: 2399 year: 2006 ident: ref113 article-title: Manifold regularization: A geometric framework for learning from labeled and unlabeled examples publication-title: J. Mach. Learn. Res. – ident: ref119 doi: 10.1109/ACCESS.2020.3003916 – ident: ref235 doi: 10.1109/TAMD.2015.2431497 – ident: ref219 doi: 10.1109/ACCESS.2019.2943188 – ident: ref221 doi: 10.1109/ACCESS.2019.2929094 – ident: ref294 doi: 10.1109/TSMCB.2009.2013721 – ident: ref137 doi: 10.1109/BIBM47256.2019.8983025 – ident: ref209 doi: 10.1109/TKDE.2020.3047857 – ident: ref240 doi: 10.1038/nature10887 – ident: ref297 doi: 10.1037/h0042519 – ident: ref86 doi: 10.1016/j.inffus.2017.02.007 – ident: ref312 doi: 10.1126/science.aaf2654 – ident: ref283 doi: 10.5555/2969033.2969153 – ident: ref305 doi: 10.1038/s41563-019-0291-x – ident: ref250 doi: 10.1109/TEC.2005.847955 – ident: ref151 doi: 10.1109/CAC48633.2019.8996625 – ident: ref251 doi: 10.1109/TITS.2019.2897583 – ident: ref315 doi: 10.1109/COMST.2017.2682318 – start-page: 448 volume-title: Proc. 12th Int. Conf. Artif. Intell. Stat. ident: ref5 article-title: Deep Boltzmann machines – ident: ref289 doi: 10.1109/TNNLS.2017.2712793 – ident: ref273 doi: 10.1007/s40815-020-00913-x – ident: ref316 doi: 10.1109/SEC.2018.00040 – ident: ref4 doi: 10.1126/science.1127647 – ident: ref160 doi: 10.1109/ROBIO49542.2019.8961680 – ident: ref9 doi: 10.4324/9781410605337-29 – ident: ref19 doi: 10.1109/YAC.2017.7967609 – ident: ref69 doi: 10.1134/s1054661816010065 – ident: ref245 doi: 10.1109/LSP.2006.882107 – ident: ref242 doi: 10.1007/s11042-020-09303-9 – ident: ref176 doi: 10.1109/SMC42975.2020.9283159 – ident: ref168 doi: 10.1109/SPAC.2017.8304274 – start-page: 1177 volume-title: Advances in Neural Information Processing Syst. year: 2008 ident: ref284 article-title: Random features for large-scale kernel machines – ident: ref34 doi: 10.1109/TSMC.1985.6313399 – ident: ref179 doi: 10.1109/TSMC.2020.2969686 – ident: ref229 doi: 10.1109/CVPRW.2010.5543262 – ident: ref167 doi: 10.1109/CAC48633.2019.8997252 – ident: ref314 doi: 10.1109/JPROC.2019.2918951 – ident: ref236 doi: 10.1109/JBHI.2017.2688239 – ident: ref6 doi: 10.5555/2999134.2999257 – ident: ref62 doi: 10.1162/neco.1997.9.8.1735 – ident: ref185 doi: 10.1109/ICECCE49384.2020.9179272 – ident: ref124 doi: 10.1109/LGRS.2019.2907598 – ident: ref270 doi: 10.1109/JSEE.2012.00015 – ident: ref271 doi: 10.1109/TNN.2006.889496 – ident: ref83 doi: 10.1109/TCYB.2019.2934823 – ident: ref104 doi: 10.3390/en12244750 – ident: ref169 doi: 10.1109/TNNLS.2020.3004634 – ident: ref213 doi: 10.1109/ICCChina.2019.8855958 – ident: ref290 doi: 10.1016/j.neucom.2017.08.043 – ident: ref24 doi: 10.1109/ICDM.2001.989589 – ident: ref252 doi: 10.3390/s17061356 – ident: ref157 doi: 10.1109/CCDC.2019.8833310 – ident: ref217 doi: 10.1109/TIE.2019.2950853 – ident: ref249 doi: 10.1016/j.jpowsour.2020.228581 – ident: ref130 doi: 10.1109/TIP.2017.2756450 – ident: ref295 doi: 10.1146/annurev.ne.13.030190.000325 – volume-title: Very deep convolutional networks for large-scale image recognition year: 2014 ident: ref7 – ident: ref178 doi: 10.1109/TSMC.2020.2964684 – ident: ref37 doi: 10.1016/j.knosys.2019.105295 – ident: ref215 doi: 10.1109/SMC.2019.8914249 – ident: ref224 doi: 10.1088/1361-6501/ab8fee – ident: ref64 doi: 10.1109/TCYB.2018.2863020 – ident: ref309 doi: 10.1016/j.maturitas.2009.07.014 – ident: ref200 doi: 10.1109/ICCSS48103.2019.9115436 – ident: ref21 doi: 10.1016/0925-2312(94)90053-1 – ident: ref51 doi: 10.1007/978-3-540-45167-9_12 – ident: ref76 doi: 10.1109/TIT.2015.2472522 – ident: ref261 doi: 10.1049/iet-com.2012.0222 – ident: ref82 doi: 10.1109/TFUZZ.2020.3009757 – ident: ref226 doi: 10.1109/ACCESS.2019.2950240 – start-page: 1 volume-title: Proc. IEEE Int. Joint Conf. Neural Netw. (IJCNN) ident: ref291 article-title: Adaptive weighted broad learning system for software defect prediction – ident: ref177 doi: 10.1109/EMBC.2019.8856666 – ident: ref40 doi: 10.1109/SMC.2019.8914328 – ident: ref218 doi: 10.1109/ACCESS.2018.2886202 – start-page: 649 volume-title: Advances in Neural Information Processing Systems year: 2015 ident: ref43 article-title: Character-level convolutional networks for text classification – ident: ref280 doi: 10.1007/s40747-020-00139-2 – ident: ref128 doi: 10.1109/TGRS.2016.2524557 – ident: ref187 doi: 10.1145/3364836.3364890 – ident: ref231 doi: 10.1109/ACCESS.2020.2978109 – ident: ref230 doi: 10.1109/SMC.2018.00162 – ident: ref77 doi: 10.1109/TNNLS.2019.2935033 – ident: ref138 doi: 10.23919/CCC50068.2020.9188835 – ident: ref267 doi: 10.1109/72.392253 – ident: ref202 doi: 10.1145/3395245.3395252 – ident: ref247 doi: 10.1007/s11069-009-9392-1 – ident: ref73 doi: 10.1109/CompComm.2018.8780984 – ident: ref85 doi: 10.1109/ICARM.2019.8833648 – ident: ref257 doi: 10.1109/MCOM.2007.4378332 – ident: ref150 doi: 10.1145/3319921.3319955 – start-page: 119 volume-title: Proc. Eur. Symp. Artif. Neural Netw. (ESANN) ident: ref287 article-title: Weight initialization methods for multilayer feedforward – ident: ref189 doi: 10.1109/TNNLS.2020.3004253 – ident: ref196 doi: 10.1111/mice.12494 – ident: ref8 doi: 10.1109/5.726791 – ident: ref222 doi: 10.1109/CAC.2018.8623741 – ident: ref61 doi: 10.1109/ICIEA49774.2020.9102007 – start-page: 73 volume-title: Proc. 12th Asian Control Conf. (ASCC) ident: ref181 article-title: Transfer and incremental learning method for blood glucose prediction of new subjects with type 1 diabetes – ident: ref41 doi: 10.1109/CVPR.2016.90 – ident: ref2 doi: 10.1561/2000000039 – ident: ref246 doi: 10.1016/j.asoc.2020.106698 – ident: ref94 doi: 10.1109/JSTARS.2020.3001198 – ident: ref303 doi: 10.1126/science.1211095 – ident: ref55 doi: 10.1109/TIP.2012.2235849 – ident: ref89 doi: 10.1038/nrn2148 – ident: ref195 doi: 10.1109/CCDC.2019.8832560 – ident: ref248 doi: 10.1109/SPAC49953.2019.237871 – ident: ref266 doi: 10.1109/72.80202 – ident: ref161 doi: 10.1109/SMC.2018.00716 – ident: ref255 doi: 10.1016/j.comnet.2010.05.010 – ident: ref60 doi: 10.1109/72.471375 – year: 2005 ident: ref109 article-title: Semi-supervised learning literature survey – ident: ref32 doi: 10.1109/TCYB.2018.2857815 – ident: ref156 doi: 10.1109/ICARCV.2018.8581232 – ident: ref208 doi: 10.1109/TSMC.2019.2958382 – ident: ref307 doi: 10.1016/j.adhoc.2012.02.016 – ident: ref48 doi: 10.1109/ICPR.1992.201708 – ident: ref166 doi: 10.1109/ACCESS.2019.2938349 – ident: ref117 doi: 10.3390/electronics8111273 – ident: ref173 doi: 10.1109/TCYB.2018.2875983 – ident: ref33 doi: 10.1016/j.neucom.2019.01.073 – ident: ref99 doi: 10.1007/bf00058655 – ident: ref211 doi: 10.1109/JIOT.2020.2980198 – ident: ref140 doi: 10.1162/153244303322753616 – ident: ref133 doi: 10.1109/ACCESS.2018.2885164 – ident: ref264 doi: 10.1109/IWCMC48107.2020.9148092 – ident: ref293 doi: 10.1155/2007/12725 – volume: 5 start-page: 845 year: 2004 ident: ref121 article-title: Feature selection for unsupervised learning publication-title: J. Mach. Learn. Res. – ident: ref108 doi: 10.2200/S00196ED1V01Y200906AIM006 – ident: ref38 doi: 10.1016/j.neucom.2019.10.059 – ident: ref302 doi: 10.1007/s00221-001-0932-5 – ident: ref66 doi: 10.1016/j.ymssp.2020.106738 – ident: ref278 doi: 10.1016/j.neunet.2014.10.001 – ident: ref95 doi: 10.1109/TKDE.2018.2866149 – ident: ref18 doi: 10.1109/TNNLS.2018.2866622 – ident: ref44 doi: 10.1016/j.neunet.2005.04.006 – ident: ref205 doi: 10.1109/SMC.2018.00719 – ident: ref42 doi: 10.1109/CVPR.2017.243 – ident: ref107 doi: 10.1109/TSMC.2020.3043147 – ident: ref112 doi: 10.1109/TCSI.2019.2959886 – volume-title: The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices year: 2010 ident: ref56 – ident: ref68 doi: 10.1007/s11263-015-0816-y – ident: ref272 doi: 10.1109/TCYB.2020.2998984 – ident: ref30 doi: 10.1109/TMI.2015.2458702 – ident: ref141 doi: 10.1109/IJCNN.2019.8852226 – ident: ref45 doi: 10.1109/TSMC.2018.2884996 – ident: ref145 doi: 10.1016/j.neucom.2020.05.025 – ident: ref58 doi: 10.1109/TCYB.2020.3015749 – ident: ref268 doi: 10.1109/TNNLS.2015.2508926 – ident: ref258 doi: 10.1145/1361684.1361686 – ident: ref125 doi: 10.1109/TGRS.2017.2689805 – ident: ref243 doi: 10.1007/BFb0080116 – ident: ref263 doi: 10.1038/nature14236 – volume: 9 start-page: 293 issue: 3 year: 1999 ident: ref27 article-title: Least squares support vector machine classifiers publication-title: Neural Process. Lett. doi: 10.1023/A:1018628609742 – ident: ref84 doi: 10.1109/TMM.2020.2987703 – ident: ref31 doi: 10.1016/j.measurement.2016.04.007 – ident: ref238 doi: 10.1534/genetics.112.146704 – ident: ref87 doi: 10.1109/TNSRE.2020.3003342 – ident: ref285 doi: 10.1016/j.neucom.2007.07.025 – start-page: 6231 volume-title: Advances in Neural Information Processing Systems year: 2017 ident: ref282 article-title: The expressive power of neural networks: A view from the width doi: 10.1007/978-3-319-70139-4 – ident: ref201 doi: 10.1002/stc.2571 – ident: ref304 doi: 10.1016/j.neuron.2016.10.050 – ident: ref118 doi: 10.1109/TBME.2010.2082539 – ident: ref70 doi: 10.1109/TCYB.2016.2588526 – ident: ref210 doi: 10.1109/MNET.001.1900078 – ident: ref90 doi: 10.1088/1741-2560/12/3/036009 – ident: ref214 doi: 10.1007/s40815-019-00739-2 – ident: ref20 doi: 10.1080/00207179208934315 – ident: ref16 doi: 10.1109/59.589648 – ident: ref152 doi: 10.1109/iThings/GreenCom/CPSCom/SmartData.2019.00091 – ident: ref241 doi: 10.1038/s41592-019-0330-1 – ident: ref97 doi: 10.1007/978-1-4419-9326-7_1 – ident: ref232 doi: 10.1016/j.knosys.2020.106319 – ident: ref193 doi: 10.1007/978-3-030-04224-0_6 – volume: 4 start-page: 86 issue: 2 year: 2008 ident: ref276 article-title: Neural network implementation using FPGA: Issues and application publication-title: Int. J. Inf. Technol. – ident: ref52 doi: 10.1016/0020-0190(87)90114-1 – ident: ref22 doi: 10.1016/j.ins.2015.09.025 – ident: ref75 doi: 10.1016/j.neucom.2014.08.098 – ident: ref159 doi: 10.1109/SPAC46244.2018.8965623 – ident: ref256 doi: 10.1109/ICACTE.2010.5579543 – ident: ref116 doi: 10.1109/DASC/PiCom/CBDCom/CyberSciTech.2019.00053 – ident: ref155 doi: 10.1145/3318299.3318318 – ident: ref311 doi: 10.1109/CCNC.2017.7983103 – ident: ref1 doi: 10.1038/nature14539 – ident: ref259 doi: 10.1109/LCOMM.2019.2952072 – ident: ref197 doi: 10.1177/1475921720916923 – ident: ref172 doi: 10.3390/app9061111 – ident: ref277 doi: 10.1109/TCSII.2012.2204112 – ident: ref286 doi: 10.1016/S0925-2312(99)00127-7 – ident: ref36 doi: 10.1109/SPAC46244.2018.8965489 – ident: ref308 doi: 10.1109/TSMCC.2012.2189204 – ident: ref71 doi: 10.1007/978-3-319-46487-9_6 – ident: ref132 doi: 10.1109/TSMC.2019.2957818 – ident: ref279 doi: 10.1016/j.neucom.2005.12.126 – ident: ref3 doi: 10.1162/neco.2006.18.7.1527 – ident: ref78 doi: 10.1109/TKDE.2008.239 – ident: ref93 doi: 10.1007/s11432-017-9421-3 – ident: ref233 doi: 10.1212/01.wnl.0000243257.85592.9a – ident: ref306 doi: 10.1002/adma.201505898 – ident: ref144 doi: 10.1007/s11042-019-07979-2 – ident: ref199 doi: 10.1109/TCYB.2020.2988792 – ident: ref139 doi: 10.1109/SSCI44817.2019.9002711 – ident: ref171 doi: 10.1109/TITS.2020.3011937 – ident: ref103 doi: 10.1093/nar/28.1.235 – ident: ref158 doi: 10.1109/SMC.2019.8914437 – ident: ref180 doi: 10.1007/978-3-030-01313-4_1 – ident: ref53 doi: 10.1016/j.neucom.2018.09.028
SSID	ssj0000816898
Score	2.666562
SecondaryResourceType	review_article
Snippet	In recent years, the appearance of the broad learning system (BLS) is poised to revolutionize conventional artificial intelligence methods. It represents a...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	8922
SubjectTerms	Algorithms Artificial intelligence Biomedical engineering Broad learning system (BLS) classification Computer architecture Computer science Computer vision Data mining feature learning Knowledge engineering Learning systems Machine learning Natural language processing Neural networks regression research review semisupervised learning (SSL) Task analysis Training Unsupervised learning
Title	Research Review for Broad Learning System: Algorithms, Theory, and Applications
URI	https://ieeexplore.ieee.org/document/9380770 https://www.ncbi.nlm.nih.gov/pubmed/33729975 https://www.proquest.com/docview/2704099231 https://www.proquest.com/docview/2502807723
Volume	52
WOSCitedRecordID	wos000732872900001&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: 2168-2275 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816898 issn: 2168-2267 databaseCode: RIE dateStart: 20130101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTuQwEC0B4sCFfQkwyEgcAHUgizuO59aDBnECDiA1pyhtVwCJSY964fupcpyIA4w0NytxFqXK8Xsu1yuAExOnsRwlMkx0JUOZlxjmVYYhki8huRRB5KbYhLq9zYdDfb8AvS4XBhHd5jO84KaL5duxmfNS2aVmdXRFBH1RKdXkanXrKa6AhCt9m1AjJFShfBAzjvTlw9XTLyKDSXxBEJkOcDmelCNWmjcYfpqRXImV79Gmm3Wu1_7vfddh1aNLMWjcYQMWsN6EtbZyg_ADeRM2fGsqTr3u9NkW3LW78EQTMBCEZwXR9NIKr8L6LBqB859i8PY8nrzOXv5Me6JJ7--JsrZi8Ckevg2P178frm5CX28hNDSNz0Kpy7JvlO0rAhVGltJqgzrSViKxoqpfYZYi_Vkx1VWisNJEhnLWe0FkVfco3YGlelzjHgib60yO4ryU8Ygl4HKiXXFWJSazsc2iKoCo_eaF8WLkXBPjrXCkJNIFW6xgixXeYgGcd5f8bZQ4_tV5i83RdfSWCOCwNWzhx-q0SBT9yDQD3QCOu9M0yjh0UtY4nlOfPoegiYmkAew2DtHdu_Wj_a-feQArCadMuH1ph7A0m8zxByyb99nrdHJErjzMj5wrfwAG6-lK
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5VBQku9AUl0IKROADatLHjPNzbUlEVURYOi1ROUdaelEoli_bB72fGcaIeKBI3K3Eeyozj7_N4vgF4bWUq9UzpWJlGx7qsMS6bHGMkX0JyKYLIXbGJYjIpLy_N1w0YDbkwiOg3n-ERN30s383tmpfKjg2roxdE0O9lWivZZWsNKyq-hIQvfquoEROuKEIYUybmeHr6_T3RQSWPCCTTAS7Ik3LMyvAWw1tzki-ycjfe9PPO2db_vfE2PAr4Uow7h9iBDWx3Yauv3SDCUN6FndBaijdBefrtHnzp9-GJLmQgCNEKIuq1E0GH9Up0EucnYnxzNV9cr378XI5El-A_EnXrxPhWRPwxfDv7MD09j0PFhdjSRL6KtanrzBYuKwhWWF1rZyyaxDiNxIuarME8Rfq3YmoaVWBjiA6VrPiCyLruSfoENtt5i09BuNLkeibLWssZi8CVRLxk3iibO-nypIkg6b95ZYMcOVfFuKk8LUlMxRar2GJVsFgE74ZLfnVaHP_qvMfmGDoGS0Rw0Bu2CqN1WamCfmWGoW4Er4bTNM44eFK3OF9Tn4yD0MRF0gj2O4cY7t370bO_P_MlPDiffr6oLj5OPj2Hh4oTKPwutQPYXC3WeAj37e_V9XLxwjv0H9Jn66k
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=Research+Review+for+Broad+Learning+System%3A+Algorithms%2C+Theory%2C+and+Applications&rft.jtitle=IEEE+transactions+on+cybernetics&rft.au=Gong%2C+Xinrong&rft.au=Zhang%2C+Tong&rft.au=Chen%2C+C.+L.+Philip&rft.au=Liu%2C+Zhulin&rft.date=2022-09-01&rft.issn=2168-2267&rft.eissn=2168-2275&rft.volume=52&rft.issue=9&rft.spage=8922&rft.epage=8950&rft_id=info:doi/10.1109%2FTCYB.2021.3061094&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TCYB_2021_3061094
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-2267&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-2267&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-2267&client=summon