An improved incremental constructive single-hidden-layer feedforward networks for extreme learning machine based on particle swarm optimization
How to determine the network structure is an open problem in extreme learning machine (ELM). Error minimized extreme learning machine (EM-ELM) is a simple and efficient approach to determine the number of hidden nodes. However, similar to other constructive ELM, EM-ELM lays much emphasis on the conv...
Saved in:
| Published in | Neurocomputing (Amsterdam) Vol. 228; pp. 133 - 142 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
08.03.2017
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0925-2312 1872-8286 |
| DOI | 10.1016/j.neucom.2016.09.092 |
Cover
| Abstract | How to determine the network structure is an open problem in extreme learning machine (ELM). Error minimized extreme learning machine (EM-ELM) is a simple and efficient approach to determine the number of hidden nodes. However, similar to other constructive ELM, EM-ELM lays much emphasis on the convergence accuracy, which may obtain a single-hidden-layer feedforward neural networks (SLFN) with good convergence performance but bad condition. In this paper, an effective approach based on error minimized ELM and particle swarm optimization (PSO) is proposed to adaptively determine the structure of SLFN for regression problem. In the new method, to establish a compact and well-conditioning SLFN, the hidden node optimized by PSO is added to the SLFN one by one. Moreover, not only the regression accuracy but also the condition value of the hidden output matrix of the network is considered in the optimization process. Experiment results on various regression problems verify that the proposed algorithm achieves better generalization performance with fewer hidden nodes than other constructive ELM. |
|---|---|
| AbstractList | How to determine the network structure is an open problem in extreme learning machine (ELM). Error minimized extreme learning machine (EM-ELM) is a simple and efficient approach to determine the number of hidden nodes. However, similar to other constructive ELM, EM-ELM lays much emphasis on the convergence accuracy, which may obtain a single-hidden-layer feedforward neural networks (SLFN) with good convergence performance but bad condition. In this paper, an effective approach based on error minimized ELM and particle swarm optimization (PSO) is proposed to adaptively determine the structure of SLFN for regression problem. In the new method, to establish a compact and well-conditioning SLFN, the hidden node optimized by PSO is added to the SLFN one by one. Moreover, not only the regression accuracy but also the condition value of the hidden output matrix of the network is considered in the optimization process. Experiment results on various regression problems verify that the proposed algorithm achieves better generalization performance with fewer hidden nodes than other constructive ELM. |
| Author | Han, Fei Zhao, Min-Ru Zhang, Jian-Ming Ling, Qing-Hua |
| Author_xml | – sequence: 1 givenname: Fei surname: Han fullname: Han, Fei organization: School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu, China – sequence: 2 givenname: Min-Ru surname: Zhao fullname: Zhao, Min-Ru organization: School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu, China – sequence: 3 givenname: Jian-Ming surname: Zhang fullname: Zhang, Jian-Ming organization: School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu, China – sequence: 4 givenname: Qing-Hua surname: Ling fullname: Ling, Qing-Hua organization: School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu, China |
| BookMark | eNqFkN9KXDEQxkOx0NX2DXqRFzhrkvO_FwURrQWhN3odciaTOttzkiWJq_YlfOVm3V55oTAwzAe_b2a-Y3bkg0fGvkqxlkJ2p5u1x3sIy1qVaS3GUuoDW8mhV9Wghu6IrYrSVqqW6hM7TmkjhOylGlfs-cxzWrYx7NBy8hBxQZ_NzCH4lOM9ZNohT-R_z1jdkbXoq9k8YeQO0boQH0y03GN-CPFP4kXg-Jj3LnxGE30B-WLgjjzyyaSyJHi-NTETzMW30AsP20wL_TWZgv_MPjozJ_zyv5-w28uLm_Or6vrXj5_nZ9cV1KLLFTZ9jz1CeVg4205uMqJtVIfN0I9D041951pULdSuF0MzOWegq9UEk5GqA1ufsG8HX4ghpYhOA-WXC3I0NGsp9D5avdGHaPU-Wi3GUqrAzSt4G2kx8ek97PsBw_LYjjDqBIQe0FJEyNoGetvgHyVknWA |
| CitedBy_id | crossref_primary_10_1007_s11063_018_9865_x crossref_primary_10_1016_j_bdr_2022_100356 crossref_primary_10_1016_j_tre_2020_102189 crossref_primary_10_1108_IMDS_07_2019_0361 crossref_primary_10_1007_s00521_019_04398_0 crossref_primary_10_3390_rs16091565 crossref_primary_10_1016_j_jairtraman_2023_102488 crossref_primary_10_1109_TII_2024_3423487 crossref_primary_10_1007_s00170_023_10957_6 crossref_primary_10_1016_j_swevo_2021_100863 crossref_primary_10_1016_j_neucom_2019_03_086 crossref_primary_10_1016_j_neucom_2018_07_080 crossref_primary_10_1002_we_2323 crossref_primary_10_1080_00032719_2023_2212821 crossref_primary_10_1007_s11042_019_7543_2 crossref_primary_10_1016_j_jprocont_2023_103159 crossref_primary_10_1038_s41598_024_74446_w crossref_primary_10_1109_ACCESS_2018_2873627 crossref_primary_10_1016_j_neucom_2021_03_077 crossref_primary_10_3390_app9050835 crossref_primary_10_1007_s40430_021_03257_1 crossref_primary_10_1007_s13042_022_01578_8 crossref_primary_10_1177_0040517518764020 crossref_primary_10_1109_TIM_2024_3470037 crossref_primary_10_1007_s10489_018_01403_2 crossref_primary_10_1108_IMDS_06_2019_0351 crossref_primary_10_1177_0954406220928370 crossref_primary_10_1016_j_neucom_2017_09_047 crossref_primary_10_1016_j_neucom_2024_129020 crossref_primary_10_1007_s10845_023_02303_0 crossref_primary_10_1007_s12065_022_00813_z |
| Cites_doi | 10.1109/TNNLS.2011.2178124 10.1109/TNN.2006.875977 10.1016/j.neucom.2015.08.121 10.1109/ICNN.1995.488968 10.1080/00207179208934315 10.1109/TCYB.2013.2239987 10.1109/TEVC.2006.886448 10.1109/IJCNN.2004.1380068 10.1016/j.neucom.2007.10.008 10.1016/j.neucom.2011.12.062 10.1109/ICICS.2009.5397617 10.1109/TNN.2004.824424 10.1162/089976604774201668 10.1109/MHS.1995.494215 10.1109/TEVC.2005.859468 10.1109/TNN.2005.844912 10.1109/TNN.2009.2036259 10.1109/IJCNN.2008.4633951 10.1007/978-3-319-22053-6_11 10.1007/11759966_95 10.1016/j.neucom.2005.12.126 10.1016/j.neucom.2016.01.005 10.1109/TNN.2006.880583 10.1109/TNN.2009.2024147 |
| ContentType | Journal Article |
| Copyright | 2016 |
| Copyright_xml | – notice: 2016 |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.neucom.2016.09.092 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-8286 |
| EndPage | 142 |
| ExternalDocumentID | 10_1016_j_neucom_2016_09_092 S0925231216312826 |
| GroupedDBID | --- --K --M .DC .~1 0R~ 123 1B1 1~. 1~5 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXLA AAXUO AAYFN ABBOA ABCQJ ABFNM ABJNI ABMAC ABYKQ ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE AEBSH AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W KOM LG9 M41 MO0 MOBAO N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RIG ROL RPZ SDF SDG SDP SES SPC SPCBC SSN SSV SSZ T5K ZMT ~G- 29N AAQXK AATTM AAXKI AAYWO AAYXX ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS FEDTE FGOYB HLZ HVGLF HZ~ R2- SBC SEW WUQ XPP ~HD |
| ID | FETCH-LOGICAL-c306t-e477e7ec2010fd5bfba05426e4879846976f5e25c3f7084bffac632bcba126cd3 |
| IEDL.DBID | .~1 |
| ISSN | 0925-2312 |
| IngestDate | Wed Oct 01 06:02:17 EDT 2025 Thu Apr 24 22:57:47 EDT 2025 Fri Feb 23 02:30:23 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Generalization performance Network structure Condition value Extreme learning machine Particle swarm optimization |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c306t-e477e7ec2010fd5bfba05426e4879846976f5e25c3f7084bffac632bcba126cd3 |
| PageCount | 10 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_neucom_2016_09_092 crossref_primary_10_1016_j_neucom_2016_09_092 elsevier_sciencedirect_doi_10_1016_j_neucom_2016_09_092 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2017-03-08 |
| PublicationDateYYYYMMDD | 2017-03-08 |
| PublicationDate_xml | – month: 03 year: 2017 text: 2017-03-08 day: 08 |
| PublicationDecade | 2010 |
| PublicationTitle | Neurocomputing (Amsterdam) |
| PublicationYear | 2017 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Feng, Huang, Lin, Gay (bib15) 2009; 20 Huang, Chen, Siew (bib12) 2006; 17 G.-B.Huang, Q.-Y.Zhu, C.-K.Siew, Extreme learning machine: a new learning scheme of feedforward neural networks, in: Proceedings International Joint Conference Neural Netwvol. 2, pp. 985–990, 2004. Zhao, Huerta (bib7) 2016; 191 Huang, H.S.Ip, Chi (bib3) 2004; 16 Han, Yao, Ling (bib20) 2013; 116 Huang (bib2) 2004; 15 Huang, Zhu, Siew (bib13) 2006; 70 R.C. Eberhart, J. Kennedy, A new optimizer using particles swarm theory, in: Proceedings of the Sixth International Symposium on Micro Machine and Human science, Nagoya, Japan, 1995, pp. 39–43. Huang, H.S.Ip, C K, Chi (bib4) 2005; 16 J.Kennedy, R.Eberhart, Particle , Particle swarm optimization, in: Proceedings of IEEE International Conference on Neural Networks, Perth, Australia, vol. 4, 1995, pp. 1942–1948. Langdon, Poli (bib23) 2007; 11 Miche, Sorjamaa, Bas, Simula, Jutten, Lendasse (bib1) 2010; 21 Huang, Chen (bib14) 2008; 71 Y.Shi, R.C.Eberhart, A modified particle swarm optimizer, in: Proceedings of IEEE World Conference on Computation Intelligence, 1998, pp. 69–73. You Xu, Yang Shu, Evolutionary extreme learning machine-based on particle swarm op-timization, in: International Symposium on Neural Networks 2006 (ISNN2006), LNCS, vol. 3971, 2006, pp. 644–652. G.P. Zhao, Z.Q. Shen, C.Y. Miao, Z.H. Man, On improving the conditioning of extreme learning machine: a linear case, in: Proceedings of the 7th International Conference on Information, Communi-cations and Signal Processing, 2009 (ICICS2009), Maucu, China, December 8–10, 2009, pp. 1–5. C.L.Black, C.J.Merz, UCI Repository of Machine Learning Databases. Dept. Inf. Comput. Sci., Univ. California, Irvine Han, Yang, Jiang (bib8) 2016; 198 Pao, Phillips, Sobajic (bib5) 1992; 56 G.-B.Huang, N.-Y.Liang, H.-J.Rong, P.Saratchandran, N.Sundararajan, On-line sequential extreme learning machine, in: Proceedings IASTED International Conference Comput. Intell., Calgary, AB, Canada, 2005. G.Zhao, Z.Shen, C.Miao, R..Gay, Enhanced extreme learning machine with stacked generalization, in: Proceedings International Joint Conference on Neural Networkspp. 1192–1199, 2008. Liang, Huang, Saratchandran, Sundararajan (bib11) 2006; 17 Zhang, Lan, Huang, Xu (bib16) 2012; 23 Han, Zhao, Zhang (bib25) 2015; 9927 Parrott, dong Li (bib22) 2006; 10 G.-B.Huang, C.-K.Siew, Extreme learning machine: RBF network case, in: Proceedings of the 8th International Conference Control Autom. Robot. Visvol. 2, pp. 1029–1036, 2004. Zhang, Lan, Huang, Xu, Soh (bib17) 2013; 43 Zhang (10.1016/j.neucom.2016.09.092_bib17) 2013; 43 Zhang (10.1016/j.neucom.2016.09.092_bib16) 2012; 23 10.1016/j.neucom.2016.09.092_bib24 10.1016/j.neucom.2016.09.092_bib27 10.1016/j.neucom.2016.09.092_bib26 Han (10.1016/j.neucom.2016.09.092_bib25) 2015; 9927 10.1016/j.neucom.2016.09.092_bib28 10.1016/j.neucom.2016.09.092_bib10 Huang (10.1016/j.neucom.2016.09.092_bib13) 2006; 70 Feng (10.1016/j.neucom.2016.09.092_bib15) 2009; 20 Liang (10.1016/j.neucom.2016.09.092_bib11) 2006; 17 Pao (10.1016/j.neucom.2016.09.092_bib5) 1992; 56 Huang (10.1016/j.neucom.2016.09.092_bib14) 2008; 71 10.1016/j.neucom.2016.09.092_bib19 10.1016/j.neucom.2016.09.092_bib6 Han (10.1016/j.neucom.2016.09.092_bib8) 2016; 198 Zhao (10.1016/j.neucom.2016.09.092_bib7) 2016; 191 Huang (10.1016/j.neucom.2016.09.092_bib4) 2005; 16 Han (10.1016/j.neucom.2016.09.092_bib20) 2013; 116 Parrott (10.1016/j.neucom.2016.09.092_bib22) 2006; 10 10.1016/j.neucom.2016.09.092_bib9 Miche (10.1016/j.neucom.2016.09.092_bib1) 2010; 21 Huang (10.1016/j.neucom.2016.09.092_bib2) 2004; 15 10.1016/j.neucom.2016.09.092_bib18 10.1016/j.neucom.2016.09.092_bib21 Huang (10.1016/j.neucom.2016.09.092_bib3) 2004; 16 Langdon (10.1016/j.neucom.2016.09.092_bib23) 2007; 11 Huang (10.1016/j.neucom.2016.09.092_bib12) 2006; 17 |
| References_xml | – volume: 71 start-page: 3460 year: 2008 end-page: 3468 ident: bib14 article-title: Enhanced random search based incremental extreme learning machine, publication-title: Neurocomputing – volume: 70 start-page: 489 year: 2006 end-page: 501 ident: bib13 article-title: Extreme learning machine: theory and applications, publication-title: Neurocomputing – reference: G.-B.Huang, N.-Y.Liang, H.-J.Rong, P.Saratchandran, N.Sundararajan, On-line sequential extreme learning machine, in: Proceedings IASTED International Conference Comput. Intell., Calgary, AB, Canada, 2005. – volume: 116 start-page: 87 year: 2013 end-page: 93 ident: bib20 article-title: An improved evolutionary extreme learning machine based on particle swarm optimization, publication-title: Neurocomputing – volume: 9927 start-page: 94 year: 2015 end-page: 100 ident: bib25 article-title: An improved incremental error minimized extreme learning machine for regression problem based on particle swarm optimization, publication-title: Lect. Notes Comput. Sci. – volume: 21 start-page: 158 year: 2010 end-page: 162 ident: bib1 article-title: OP-ELM: optimally pruned extreme learning machine, publication-title: IEEE Trans. Neural Netw. – volume: 17 start-page: 1411 year: 2006 end-page: 1423 ident: bib11 article-title: A fast and accurate online sequential learning algorithm for feedforward networks, publication-title: IEEE Trans. Neural Netw. – reference: R.C. Eberhart, J. Kennedy, A new optimizer using particles swarm theory, in: Proceedings of the Sixth International Symposium on Micro Machine and Human science, Nagoya, Japan, 1995, pp. 39–43. – reference: G.-B.Huang, Q.-Y.Zhu, C.-K.Siew, Extreme learning machine: a new learning scheme of feedforward neural networks, in: Proceedings International Joint Conference Neural Netwvol. 2, pp. 985–990, 2004. – volume: 15 start-page: 477 year: 2004 end-page: 491 ident: bib2 article-title: A constructive approach for finding arbitrary roots of polynomials by neural networks, publication-title: IEEE Trans. Neural Netw. – volume: 17 start-page: 879 year: 2006 end-page: 892 ident: bib12 article-title: Universal approximation using incremental constructive feedforward networks with random hidden nodes, publication-title: IEEE Trans. Neural Netw. – volume: 56 start-page: 263 year: 1992 end-page: 289 ident: bib5 article-title: Neural-net computing and the intelligent control of systems, publication-title: Int. J. Control – volume: 191 start-page: 82 year: 2016 end-page: 94 ident: bib7 article-title: Improvements on parsimonious extreme learning machine using recursive orthogonal least squares, publication-title: Neurocomputing – volume: 23 start-page: 365 year: 2012 end-page: 371 ident: bib16 article-title: Universal approximation of extreme learning machine with adaptive growth of hidden nodes, publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 20 start-page: 1352 year: 2009 end-page: 1357 ident: bib15 article-title: Error minimized extreme learning machine with growth of hidden nodes and incremental learning, publication-title: IEEE Trans. Neural Netw. – volume: 10 start-page: 440 year: 2006 end-page: 458 ident: bib22 article-title: Locating and tracking multiple dynamic optima by a particle swarm model using speciation publication-title: IEEE Trans. Evol. Comput. – volume: 198 start-page: 27 year: 2016 end-page: 34 ident: bib8 article-title: An extreme learning machine based on Celluar Automata of edge detection for remote sensing images, publication-title: Neurocomputing – reference: G.-B.Huang, C.-K.Siew, Extreme learning machine: RBF network case, in: Proceedings of the 8th International Conference Control Autom. Robot. Visvol. 2, pp. 1029–1036, 2004. – reference: G.P. Zhao, Z.Q. Shen, C.Y. Miao, Z.H. Man, On improving the conditioning of extreme learning machine: a linear case, in: Proceedings of the 7th International Conference on Information, Communi-cations and Signal Processing, 2009 (ICICS2009), Maucu, China, December 8–10, 2009, pp. 1–5. – reference: C.L.Black, C.J.Merz, UCI Repository of Machine Learning Databases. Dept. Inf. Comput. Sci., Univ. California, Irvine, – volume: 16 start-page: 721 year: 2005 end-page: 732 ident: bib4 article-title: ”Zeroing polynomials using modified constrained neural network approach,” publication-title: IEEE Trans. Neural Netw. – volume: 16 start-page: 1721 year: 2004 end-page: 1762 ident: bib3 article-title: " A neural root finder of polynomials based on root moments publication-title: Neural Comput. – reference: J.Kennedy, R.Eberhart, Particle , Particle swarm optimization, in: Proceedings of IEEE International Conference on Neural Networks, Perth, Australia, vol. 4, 1995, pp. 1942–1948. – volume: 11 start-page: 561 year: 2007 end-page: 578 ident: bib23 article-title: Evolving problems to learn about particle swarm optimizers and other search algorithms, publication-title: IEEE Trans. Evol. Comput. – reference: You Xu, Yang Shu, Evolutionary extreme learning machine-based on particle swarm op-timization, in: International Symposium on Neural Networks 2006 (ISNN2006), LNCS, vol. 3971, 2006, pp. 644–652. – reference: G.Zhao, Z.Shen, C.Miao, R..Gay, Enhanced extreme learning machine with stacked generalization, in: Proceedings International Joint Conference on Neural Networkspp. 1192–1199, 2008. – reference: Y.Shi, R.C.Eberhart, A modified particle swarm optimizer, in: Proceedings of IEEE World Conference on Computation Intelligence, 1998, pp. 69–73. – volume: 43 start-page: 2054 year: 2013 end-page: 2065 ident: bib17 article-title: Dynamic extreme learning machine and its approximation capability, publication-title: IEEE Trans. Cybern. – volume: 23 start-page: 365 issue: 2 year: 2012 ident: 10.1016/j.neucom.2016.09.092_bib16 article-title: Universal approximation of extreme learning machine with adaptive growth of hidden nodes, publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2011.2178124 – volume: 17 start-page: 879 issue: 4 year: 2006 ident: 10.1016/j.neucom.2016.09.092_bib12 article-title: Universal approximation using incremental constructive feedforward networks with random hidden nodes, publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2006.875977 – volume: 198 start-page: 27 year: 2016 ident: 10.1016/j.neucom.2016.09.092_bib8 article-title: An extreme learning machine based on Celluar Automata of edge detection for remote sensing images, publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.08.121 – ident: 10.1016/j.neucom.2016.09.092_bib21 doi: 10.1109/ICNN.1995.488968 – volume: 56 start-page: 263 issue: 2 year: 1992 ident: 10.1016/j.neucom.2016.09.092_bib5 article-title: Neural-net computing and the intelligent control of systems, publication-title: Int. J. Control doi: 10.1080/00207179208934315 – volume: 43 start-page: 2054 year: 2013 ident: 10.1016/j.neucom.2016.09.092_bib17 article-title: Dynamic extreme learning machine and its approximation capability, publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2013.2239987 – ident: 10.1016/j.neucom.2016.09.092_bib9 – ident: 10.1016/j.neucom.2016.09.092_bib27 – volume: 11 start-page: 561 issue: 5 year: 2007 ident: 10.1016/j.neucom.2016.09.092_bib23 article-title: Evolving problems to learn about particle swarm optimizers and other search algorithms, publication-title: IEEE Trans. Evol. Comput. doi: 10.1109/TEVC.2006.886448 – ident: 10.1016/j.neucom.2016.09.092_bib6 doi: 10.1109/IJCNN.2004.1380068 – volume: 71 start-page: 3460 issue: 16–18 year: 2008 ident: 10.1016/j.neucom.2016.09.092_bib14 article-title: Enhanced random search based incremental extreme learning machine, publication-title: Neurocomputing doi: 10.1016/j.neucom.2007.10.008 – volume: 116 start-page: 87 year: 2013 ident: 10.1016/j.neucom.2016.09.092_bib20 article-title: An improved evolutionary extreme learning machine based on particle swarm optimization, publication-title: Neurocomputing doi: 10.1016/j.neucom.2011.12.062 – ident: 10.1016/j.neucom.2016.09.092_bib19 doi: 10.1109/ICICS.2009.5397617 – volume: 15 start-page: 477 issue: 2 year: 2004 ident: 10.1016/j.neucom.2016.09.092_bib2 article-title: A constructive approach for finding arbitrary roots of polynomials by neural networks, publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2004.824424 – volume: 16 start-page: 1721 issue: 8 year: 2004 ident: 10.1016/j.neucom.2016.09.092_bib3 article-title: " A neural root finder of polynomials based on root moments publication-title: Neural Comput. doi: 10.1162/089976604774201668 – ident: 10.1016/j.neucom.2016.09.092_bib26 doi: 10.1109/MHS.1995.494215 – volume: 10 start-page: 440 issue: 4 year: 2006 ident: 10.1016/j.neucom.2016.09.092_bib22 article-title: Locating and tracking multiple dynamic optima by a particle swarm model using speciation publication-title: IEEE Trans. Evol. Comput. doi: 10.1109/TEVC.2005.859468 – volume: 16 start-page: 721 issue: 3 year: 2005 ident: 10.1016/j.neucom.2016.09.092_bib4 article-title: ”Zeroing polynomials using modified constrained neural network approach,” publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2005.844912 – volume: 21 start-page: 158 issue: 1 year: 2010 ident: 10.1016/j.neucom.2016.09.092_bib1 article-title: OP-ELM: optimally pruned extreme learning machine, publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2009.2036259 – ident: 10.1016/j.neucom.2016.09.092_bib10 – ident: 10.1016/j.neucom.2016.09.092_bib18 doi: 10.1109/IJCNN.2008.4633951 – ident: 10.1016/j.neucom.2016.09.092_bib28 – volume: 9927 start-page: 94 year: 2015 ident: 10.1016/j.neucom.2016.09.092_bib25 article-title: An improved incremental error minimized extreme learning machine for regression problem based on particle swarm optimization, publication-title: Lect. Notes Comput. Sci. doi: 10.1007/978-3-319-22053-6_11 – ident: 10.1016/j.neucom.2016.09.092_bib24 doi: 10.1007/11759966_95 – volume: 70 start-page: 489 issue: 1–3 year: 2006 ident: 10.1016/j.neucom.2016.09.092_bib13 article-title: Extreme learning machine: theory and applications, publication-title: Neurocomputing doi: 10.1016/j.neucom.2005.12.126 – volume: 191 start-page: 82 year: 2016 ident: 10.1016/j.neucom.2016.09.092_bib7 article-title: Improvements on parsimonious extreme learning machine using recursive orthogonal least squares, publication-title: Neurocomputing doi: 10.1016/j.neucom.2016.01.005 – volume: 17 start-page: 1411 issue: 6 year: 2006 ident: 10.1016/j.neucom.2016.09.092_bib11 article-title: A fast and accurate online sequential learning algorithm for feedforward networks, publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2006.880583 – volume: 20 start-page: 1352 issue: 8 year: 2009 ident: 10.1016/j.neucom.2016.09.092_bib15 article-title: Error minimized extreme learning machine with growth of hidden nodes and incremental learning, publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2009.2024147 |
| SSID | ssj0017129 |
| Score | 2.356115 |
| Snippet | How to determine the network structure is an open problem in extreme learning machine (ELM). Error minimized extreme learning machine (EM-ELM) is a simple and... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 133 |
| SubjectTerms | Condition value Extreme learning machine Generalization performance Network structure Particle swarm optimization |
| Title | An improved incremental constructive single-hidden-layer feedforward networks for extreme learning machine based on particle swarm optimization |
| URI | https://dx.doi.org/10.1016/j.neucom.2016.09.092 |
| Volume | 228 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier) customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: GBLVA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: Elsevier SD Complete Freedom Collection [SCCMFC] customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: ACRLP dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: .~1 dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals [SCFCJ] customDbUrl: eissn: 1872-8286 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: AIKHN dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVLSH databaseName: Elsevier Journals customDbUrl: mediaType: online eissn: 1872-8286 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017129 issn: 0925-2312 databaseCode: AKRWK dateStart: 19930201 isFulltext: true providerName: Library Specific Holdings |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEA6iFy--xTdz8BrbzT7SPRZRqkIvKnhbktlEK21aqHr0L_iXnWSzRUEUhD2FzLJkkpkv2S_fMHaa6hRpHSU8tSrjGRbIVaIkNxQHu6GqcR3YFsNicJ9dP-QPS-y8vQvjaZUx9jcxPUTr2NKJo9mZjUad224paBeVCEIUFGSFl9326l80p8_eFzSPRCai0dsTOfe92-tzgePlzKvnjFASLILaaSl-Tk9fUs7lBluLWBH6zedssiXjtth6W4cB4rLcZh99B6NwOGBqGDlsjvzIEqetPuybAX8oMDb8yWuGOD5WhLXBUu4i1OqZs-AaQvgcqAEoZPu3QCwq8QiTQLo04LNeDVMHszhKMCfrCUwp9Ezinc4ddn95cXc-4LHQAkfaMbxwk0lppEH_Z9zWubZaEZIThaHdTEkAhSCLzY3IMbWy28u0tQqLVGjUKhEF1ukuW3ZTZ_YYSIuGEFavUKrMUNc6C5s0NJjoUua4z9J2fCuMKuS-GMa4aulmz1Xjlcp7peqW9Ih9xhdWs0aF44_-snVd9W02VZQofrU8-LflIVsVPuV7flrviC2Te80xAZYXfRJm5Alb6V_dDIafc8bwHg |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1NT-MwEB1BOSyXZWEXwX7OgavVxvlwc6wQqGy7vQASt8ie2FDUupWA_Rv8ZcaJg3YlBBJSTlYmijz2m2f7eQbgKDUp8TxKROp0JjIqSOhEK2EZBwdNVeO6UVvMivFl9vsqv9qA4-4uTJBVRuxvMb1B69jSj73ZX8_n_fNBKXkVlUhmFAyystiErSxnTO7B1uhsMp49HyaoRLYp92QugkF3g66ReXn7EGQjHAeLJuFpKV-OUP9EndNP8DHSRRy1f7QLG9bvwU5XigHjzPwMjyOP82Z_wNY499Tu-rElrboUsX8thn2BhRU3IW2IFwvNdBsdhy8mrkE8i77VhN8hNyCjdvgKxroS17hsdJcWQ-CrceVxHTsK79h6iStGn2W81vkFLk9PLo7HItZaEMSLhnthM6WsshQOx12dG2c0kzlZWF7QlMxRmLW43MqcUqcGw8w4p6lIpSGjE1lQne5Dz6-8PQBUjiyTrGGhdZmRqU3WrNPIUmJKldMhpF3_VhQTkYd6GIuqU5zdVq1XquCValDyIw9BPFut20Qcb7yvOtdV_w2oimPFq5Zf3235Cz6ML_5Mq-nZbPINtmVgAEGuNvwOPXa1_cH85d78jOPzCZGw8sk |
| 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=An+improved+incremental+constructive+single-hidden-layer+feedforward+networks+for+extreme+learning+machine+based+on+particle+swarm+optimization&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Han%2C+Fei&rft.au=Zhao%2C+Min-Ru&rft.au=Zhang%2C+Jian-Ming&rft.au=Ling%2C+Qing-Hua&rft.date=2017-03-08&rft.issn=0925-2312&rft.volume=228&rft.spage=133&rft.epage=142&rft_id=info:doi/10.1016%2Fj.neucom.2016.09.092&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neucom_2016_09_092 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon |