Learning of a single-hidden layer feedforward neural network using an optimized extreme learning machine
This paper proposes a learning framework for single-hidden layer feedforward neural networks (SLFN) called optimized extreme learning machine (O-ELM). In O-ELM, the structure and the parameters of the SLFN are determined using an optimization method. The output weights, like in the batch ELM, are ob...
Saved in:
| Published in | Neurocomputing (Amsterdam) Vol. 129; pp. 428 - 436 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Amsterdam
Elsevier B.V
10.04.2014
Elsevier |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0925-2312 1872-8286 |
| DOI | 10.1016/j.neucom.2013.09.016 |
Cover
| Abstract | This paper proposes a learning framework for single-hidden layer feedforward neural networks (SLFN) called optimized extreme learning machine (O-ELM). In O-ELM, the structure and the parameters of the SLFN are determined using an optimization method. The output weights, like in the batch ELM, are obtained by a least squares algorithm, but using Tikhonov's regularization in order to improve the SLFN performance in the presence of noisy data. The optimization method is used to the set of input variables, the hidden-layer configuration and bias, the input weights and Tikhonov's regularization factor. The proposed framework has been tested with three optimization methods (genetic algorithms, simulated annealing, and differential evolution) over 16 benchmark problems available in public repositories. |
|---|---|
| AbstractList | This paper proposes a learning framework for single-hidden layer feedforward neural networks (SLFN) called optimized extreme learning machine (O-ELM). In O-ELM, the structure and the parameters of the SLFN are determined using an optimization method. The output weights, like in the batch ELM, are obtained by a least squares algorithm, but using Tikhonov's regularization in order to improve the SLFN performance in the presence of noisy data. The optimization method is used to the set of input variables, the hidden-layer configuration and bias, the input weights and Tikhonov's regularization factor. The proposed framework has been tested with three optimization methods (genetic algorithms, simulated annealing, and differential evolution) over 16 benchmark problems available in public repositories. |
| Author | Araújo, Rui Matias, Tiago Antunes, Carlos Henggeler Souza, Francisco |
| Author_xml | – sequence: 1 givenname: Tiago surname: Matias fullname: Matias, Tiago email: tmatias@isr.uc.pt organization: Institute of Systems and Robotics (ISR-UC), University of Coimbra, Pólo II, PT-3030-290 Coimbra, Portugal – sequence: 2 givenname: Francisco surname: Souza fullname: Souza, Francisco email: fasouza@isr.uc.pt organization: Institute of Systems and Robotics (ISR-UC), University of Coimbra, Pólo II, PT-3030-290 Coimbra, Portugal – sequence: 3 givenname: Rui surname: Araújo fullname: Araújo, Rui email: rui@isr.uc.pt organization: Institute of Systems and Robotics (ISR-UC), University of Coimbra, Pólo II, PT-3030-290 Coimbra, Portugal – sequence: 4 givenname: Carlos Henggeler surname: Antunes fullname: Antunes, Carlos Henggeler email: ch@deec.uc.pt organization: Department of Electrical and Computer Engineering (DEEC-UC), University of Coimbra, Pólo II, PT-3030-290 Coimbra, Portugal |
| BackLink | http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=28284407$$DView record in Pascal Francis |
| BookMark | eNqFkUuPFCEUhYkZE3tG_4ELNiZuqrxAvXBhYibjI-nEja4JBRebloIWqh3HXy-dntm4cFaX3HzncHPOJbmIKSIhLxm0DNjwZt9GPJq0tByYaEG2dfmEbNg08mbi03BBNiB533DB-DNyWcoegI2Myw3ZbVHn6ON3mhzVtNRXwGbnrcVIg77DTB2idSnf6mxp_SfrUMd6m_IPejzxVEeaDqtf_B-0FH-vGRek4cF30WbnIz4nT50OBV_czyvy7cPN1-tPzfbLx8_X77eN6YCvTQ-zYGxwIKWWw8gmCfNsQHeDG4wRfBx7HHS9zhrGoTPYucnYaRZiFjgjE1fk9dn3kNPPI5ZVLb4YDEFHTMeiWDXteTcN8DjaCwYga4wVfXWP6mJ0cFlH44s6ZL_ofKd4Tbnr4MS9PXMmp1IyOmX8qlef4pq1D4qBOjWm9urcmDo1pkCquqzi7h_xg_8jsndnGdZYf3nMqhiP0aD1Gc2qbPL_N_gLuSa1nQ |
| CitedBy_id | crossref_primary_10_1016_j_tust_2020_103595 crossref_primary_10_1016_j_knosys_2020_106599 crossref_primary_10_2166_wst_2023_249 crossref_primary_10_1109_ACCESS_2021_3068127 crossref_primary_10_1007_s13349_022_00603_2 crossref_primary_10_1016_j_tust_2022_104757 crossref_primary_10_3390_app12136599 crossref_primary_10_1007_s11356_022_24420_8 crossref_primary_10_1007_s11633_022_1315_6 crossref_primary_10_1016_j_matpr_2021_01_619 crossref_primary_10_1016_j_jsse_2019_10_005 crossref_primary_10_3233_JIFS_162162 crossref_primary_10_1016_j_eswa_2017_10_053 crossref_primary_10_1108_MMMS_07_2024_0199 crossref_primary_10_1166_jctn_2020_9114 crossref_primary_10_1016_j_enconman_2017_08_014 crossref_primary_10_1016_j_jvcir_2019_102585 crossref_primary_10_1017_S026357472200145X crossref_primary_10_17706_jsw_11_5_440_454 crossref_primary_10_1016_j_compmedimag_2024_102345 crossref_primary_10_1016_j_porgcoat_2022_107296 crossref_primary_10_1016_j_solener_2024_112785 crossref_primary_10_23919_CJEE_2023_000004 crossref_primary_10_1007_s11063_017_9700_9 crossref_primary_10_1016_j_apm_2016_10_002 crossref_primary_10_1016_j_ces_2021_117273 crossref_primary_10_1007_s11042_023_16381_y crossref_primary_10_3389_fenrg_2024_1376306 crossref_primary_10_1007_s10479_020_03878_0 crossref_primary_10_1007_s13369_023_08627_6 crossref_primary_10_1007_s42979_021_00601_z crossref_primary_10_1016_j_biosx_2023_100333 crossref_primary_10_1007_s13042_018_0833_6 crossref_primary_10_1155_2022_4744939 crossref_primary_10_1007_s12205_022_0128_z crossref_primary_10_1155_2015_529724 crossref_primary_10_1007_s10845_020_01627_5 crossref_primary_10_1155_2015_418060 crossref_primary_10_1016_j_neucom_2018_07_080 crossref_primary_10_1142_S1469026823410018 crossref_primary_10_1002_we_2323 crossref_primary_10_1186_s40069_023_00622_3 crossref_primary_10_1063_1_5113555 crossref_primary_10_1109_TNNLS_2016_2536649 crossref_primary_10_1016_j_eswa_2018_03_024 crossref_primary_10_1109_ACCESS_2019_2900563 crossref_primary_10_7498_aps_65_130501 crossref_primary_10_1038_s41598_024_74446_w crossref_primary_10_1109_TSMC_2022_3213628 crossref_primary_10_1007_s11063_016_9496_z crossref_primary_10_1016_j_apenergy_2024_123122 crossref_primary_10_1016_j_tust_2019_103103 crossref_primary_10_3390_electronics12040926 crossref_primary_10_1155_2016_7892875 crossref_primary_10_3390_su15129604 crossref_primary_10_1007_s13042_020_01073_y crossref_primary_10_1007_s00521_018_3652_5 |
| Cites_doi | 10.1109/ICNC.2007.13 10.1016/j.neucom.2005.12.126 10.1016/j.neucom.2010.11.035 10.1016/j.neucom.2008.10.010 10.1007/s11063-008-9077-x 10.1080/00207179608921659 10.1109/ETFA.2011.6059084 10.1016/0893-6080(89)90020-8 10.1016/j.patcog.2005.03.028 10.1109/TNN.2009.2036259 10.1109/TNN.2006.875977 10.1016/j.neucom.2011.04.009 10.1109/TNN.2002.804317 10.1016/j.neucom.2010.01.023 10.1007/BF01170953 10.1109/TAP.2007.891510 10.1007/s11063-012-9236-y 10.1109/IJCNN.1989.118638 10.1109/TNN.2005.860885 10.1016/j.neunet.2005.03.010 10.1016/j.neucom.2011.02.006 10.1109/TEVC.2004.826895 10.1073/pnas.89.23.11322 |
| ContentType | Journal Article |
| Copyright | 2013 Elsevier B.V. 2015 INIST-CNRS |
| Copyright_xml | – notice: 2013 Elsevier B.V. – notice: 2015 INIST-CNRS |
| DBID | AAYXX CITATION IQODW 7QO 8FD FR3 P64 7SC 7TB JQ2 L7M L~C L~D |
| DOI | 10.1016/j.neucom.2013.09.016 |
| DatabaseName | CrossRef Pascal-Francis Biotechnology Research Abstracts Technology Research Database Engineering Research Database Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Engineering Research Database Biotechnology Research Abstracts Technology Research Database Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Engineering Research Database Technology Research Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science Applied Sciences |
| EISSN | 1872-8286 |
| EndPage | 436 |
| ExternalDocumentID | 28284407 10_1016_j_neucom_2013_09_016 S0925231213009314 |
| 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 ABXDB 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 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 BNPGV IQODW SSH 7QO 8FD FR3 P64 7SC 7TB JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c402t-50b3116f099a9671890bbc0a46f6cc32775e6addedc1204ce4f8cd8b33b3ebe13 |
| IEDL.DBID | .~1 |
| ISSN | 0925-2312 |
| IngestDate | Sat Sep 27 21:07:14 EDT 2025 Tue Oct 07 10:00:24 EDT 2025 Wed Apr 02 07:35:47 EDT 2025 Thu Apr 24 22:53:28 EDT 2025 Wed Oct 01 03:45:19 EDT 2025 Fri Feb 23 02:27:14 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Differential evolution Single-hidden layer feedforward neural networks Optimized extreme learning machine Simulated annealing Genetic algorithms Evolutionary algorithm Bias Neural network Optimization Feedforward neural nets Genetic algorithm Least squares method Hidden variable theory Batch process Feedforward Learning algorithm Regularization Signal to noise ratio |
| Language | English |
| License | CC BY 4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c402t-50b3116f099a9671890bbc0a46f6cc32775e6addedc1204ce4f8cd8b33b3ebe13 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PQID | 1531009187 |
| PQPubID | 23462 |
| PageCount | 9 |
| ParticipantIDs | proquest_miscellaneous_1671524860 proquest_miscellaneous_1531009187 pascalfrancis_primary_28284407 crossref_citationtrail_10_1016_j_neucom_2013_09_016 crossref_primary_10_1016_j_neucom_2013_09_016 elsevier_sciencedirect_doi_10_1016_j_neucom_2013_09_016 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2014-04-10 |
| PublicationDateYYYYMMDD | 2014-04-10 |
| PublicationDate_xml | – month: 04 year: 2014 text: 2014-04-10 day: 10 |
| PublicationDecade | 2010 |
| PublicationPlace | Amsterdam |
| PublicationPlace_xml | – name: Amsterdam |
| PublicationTitle | Neurocomputing (Amsterdam) |
| PublicationYear | 2014 |
| Publisher | Elsevier B.V Elsevier |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier |
| References | S. Kirkpatrick, C.D. Gelatt, Jr., M. P. Vecchi, Optimization by Simulated Annealing, Technical Report, IBM Thomas J. Watson Research Center, Yorktown Heights, New York, 1982. R. Hecht-Nielsen, Theory of the back propagation neural network, in: International Joint Conference on Neural Networks, 1989, pp. 593–605. Tsai, Chou, Liu (bib12) 2006; 17 Feoktistov (bib27) 2006 DELVE Repository by University of Toronto. URL 〉 Haupt, Haupt (bib25) 2004 2010 Ferentinos (bib8) 2005; 18 Subudhi, Jena (bib9) 2008; 27 Leung, Lam, Ling, Tam (bib11) 2003; 14 Deng, Li, Irwin (bib1) 2011; 74 Holland (bib21) 1975 2013. Haupt (bib20) 2007; 55 T. Matias, F. Souza, R. Araújo, The O-ELM Toolbox. URL Miche, Sorjamaa, Bas, Simula, Jutten, Lendasse (bib5) 2010; 21 L. Torgo, URL Bi (bib24) 2010; 73 Ben-Israel, Greville (bib19) 2003 Chen, Chng, Alkadhimi (bib7) 1996; 64 Honerkamp, Weese (bib17) 1990; 2 Cao, Lin, Huang (bib16) 2012; 36 Subudhi, Jena (bib2) 2011; 74 F. Souza, T. Matias, R. Araújo, Co-evolutionary genetic multilayer perceptron for feature selection and model design, in: IEEE 16th Conference on Emerging Technologies Factory Automation (ETFA 2011), 2011, pp. 1–7. . Tsai, Liu, Chou (bib13) 2004; 8 J. Xu, Y. Lu, D.W.C. Ho, A combined genetic algorithm and orthogonal transformation for designing feedforward neural networks, in: 3rd International Conference on Natural Computation, vol. 1, 2007, pp. 10–14. Zhu, Qin, Suganthan, Huang (bib15) 2005; 38 Ragulskis, Lukoseviciute (bib33) 2009; 72 Huang, Chen, Siew (bib18) 2006; 17 R.D. King, S. Muggleton, R.A. Lewis, M.J. Sternberg, Drug design by machine learning: the use of inductive logic programming to model the structure-activity relationships of trimethoprim analogues binding to dihydrofolate reductase, in: Proceedings of the National Academy of Sciences of the United States of America, vol. 89, 1992, pp. 11322–11326. A. Frank, A. Asuncion, UCI machine Learning Repository. URL Huang, Zhu, Siew (bib6) 2006; 70 R. Storn, K. Price, Differential Evolution—A Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces, Technical Report, International Computer Science Institute (ICSI), Berkeley, California, 1995. P. A. C. Valdivieso, J. J. M. Guervós, J. González, V.M.R. Santos, G. Romero, Sa-prop: optimization of multilayer perceptron parameters using simulated annealing, in: Lecture Notes in Computer Science, vol. 1606, Springer, 1999, pp. 661–670. Hornik, Stinchcombe, White (bib4) 1989; 2 Mohamed (bib22) 2011; 74 Huang (10.1016/j.neucom.2013.09.016_bib18) 2006; 17 10.1016/j.neucom.2013.09.016_bib29 Tsai (10.1016/j.neucom.2013.09.016_bib12) 2006; 17 10.1016/j.neucom.2013.09.016_bib28 10.1016/j.neucom.2013.09.016_bib26 10.1016/j.neucom.2013.09.016_bib3 Huang (10.1016/j.neucom.2013.09.016_bib6) 2006; 70 Cao (10.1016/j.neucom.2013.09.016_bib16) 2012; 36 10.1016/j.neucom.2013.09.016_bib23 Ragulskis (10.1016/j.neucom.2013.09.016_bib33) 2009; 72 Haupt (10.1016/j.neucom.2013.09.016_bib25) 2004 Hornik (10.1016/j.neucom.2013.09.016_bib4) 1989; 2 Leung (10.1016/j.neucom.2013.09.016_bib11) 2003; 14 Chen (10.1016/j.neucom.2013.09.016_bib7) 1996; 64 Ferentinos (10.1016/j.neucom.2013.09.016_bib8) 2005; 18 Tsai (10.1016/j.neucom.2013.09.016_bib13) 2004; 8 Haupt (10.1016/j.neucom.2013.09.016_bib20) 2007; 55 Holland (10.1016/j.neucom.2013.09.016_bib21) 1975 10.1016/j.neucom.2013.09.016_bib14 Deng (10.1016/j.neucom.2013.09.016_bib1) 2011; 74 Mohamed (10.1016/j.neucom.2013.09.016_bib22) 2011; 74 10.1016/j.neucom.2013.09.016_bib34 10.1016/j.neucom.2013.09.016_bib10 Ben-Israel (10.1016/j.neucom.2013.09.016_bib19) 2003 10.1016/j.neucom.2013.09.016_bib32 10.1016/j.neucom.2013.09.016_bib31 Subudhi (10.1016/j.neucom.2013.09.016_bib9) 2008; 27 Honerkamp (10.1016/j.neucom.2013.09.016_bib17) 1990; 2 Bi (10.1016/j.neucom.2013.09.016_bib24) 2010; 73 10.1016/j.neucom.2013.09.016_bib30 Miche (10.1016/j.neucom.2013.09.016_bib5) 2010; 21 Subudhi (10.1016/j.neucom.2013.09.016_bib2) 2011; 74 Feoktistov (10.1016/j.neucom.2013.09.016_bib27) 2006 Zhu (10.1016/j.neucom.2013.09.016_bib15) 2005; 38 |
| References_xml | – volume: 64 start-page: 829 year: 1996 end-page: 837 ident: bib7 article-title: Regularized orthogonal least squares algorithm for constructing radial basis function networks publication-title: Int. J. Control – volume: 17 start-page: 879 year: 2006 end-page: 892 ident: bib18 article-title: Universal approximation using incremental constructive feedforward networks with random hidden nodes publication-title: IEEE Trans. Neural Netw. – volume: 70 start-page: 489 year: 2006 end-page: 501 ident: bib6 article-title: Extreme learning machine publication-title: Neurocomputing – volume: 2 start-page: 17 year: 1990 end-page: 30 ident: bib17 article-title: Tikhonov's regularization method for ill-posed problems publication-title: Contin. Mech. Thermodyn. – reference: 〉, 2010 – reference: T. Matias, F. Souza, R. Araújo, The O-ELM Toolbox. URL: 〈 – reference: P. A. C. Valdivieso, J. J. M. Guervós, J. González, V.M.R. Santos, G. Romero, Sa-prop: optimization of multilayer perceptron parameters using simulated annealing, in: Lecture Notes in Computer Science, vol. 1606, Springer, 1999, pp. 661–670. – reference: R. Hecht-Nielsen, Theory of the back propagation neural network, in: International Joint Conference on Neural Networks, 1989, pp. 593–605. – reference: F. Souza, T. Matias, R. Araújo, Co-evolutionary genetic multilayer perceptron for feature selection and model design, in: IEEE 16th Conference on Emerging Technologies Factory Automation (ETFA 2011), 2011, pp. 1–7. – year: 2004 ident: bib25 article-title: Practical Genetic Algorithms – volume: 36 start-page: 285 year: 2012 end-page: 305 ident: bib16 article-title: Self-adaptive evolutionary extreme learning machine publication-title: Neural Process. Lett. – volume: 74 start-page: 1696 year: 2011 end-page: 1709 ident: bib2 article-title: Nonlinear system identification using memetic differential evolution trained neural networks publication-title: Neurocomputing – volume: 72 start-page: 2618 year: 2009 end-page: 2626 ident: bib33 article-title: Non-uniform attractor embedding for time series forecasting by fuzzy inference systems publication-title: Neurocomputing – reference: L. Torgo, URL: 〈 – reference: DELVE Repository by University of Toronto. URL: 〈 – reference: J. Xu, Y. Lu, D.W.C. Ho, A combined genetic algorithm and orthogonal transformation for designing feedforward neural networks, in: 3rd International Conference on Natural Computation, vol. 1, 2007, pp. 10–14. – volume: 55 start-page: 577 year: 2007 end-page: 582 ident: bib20 article-title: Antenna design with a mixed integer genetic algorithm publication-title: IEEE Trans. Antennas Propag. – reference: 〉, 2013. – volume: 2 start-page: 359 year: 1989 end-page: 366 ident: bib4 article-title: Multilayer feedforward networks are universal approximators publication-title: Neural Netw. – volume: 27 start-page: 285 year: 2008 end-page: 296 ident: bib9 article-title: Differential evolution and levenberg marquardt trained neural network scheme for nonlinear system identification publication-title: Neural Process. Lett. – volume: 74 start-page: 2422 year: 2011 end-page: 2429 ident: bib1 article-title: Fast automatic two-stage nonlinear model identification based on the extreme learning machine publication-title: Neurocomputing – year: 2003 ident: bib19 article-title: Generalized Inverses – reference: 〉 – volume: 74 start-page: 3180 year: 2011 end-page: 3192 ident: bib22 article-title: Rules extraction from constructively trained neural networks based on genetic algorithms publication-title: Neurocomputing – reference: . – volume: 18 start-page: 934 year: 2005 end-page: 950 ident: bib8 article-title: Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms publication-title: Neural Netw. – volume: 17 start-page: 69 year: 2006 end-page: 80 ident: bib12 article-title: Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm publication-title: IEEE Trans. Neural Netw. – volume: 38 start-page: 1759 year: 2005 end-page: 1763 ident: bib15 article-title: Evolutionary extreme learning machine publication-title: Pattern Recogn. – reference: S. Kirkpatrick, C.D. Gelatt, Jr., M. P. Vecchi, Optimization by Simulated Annealing, Technical Report, IBM Thomas J. Watson Research Center, Yorktown Heights, New York, 1982. – year: 2006 ident: bib27 article-title: Differential Evolution – reference: A. Frank, A. Asuncion, UCI machine Learning Repository. URL: 〈 – volume: 8 start-page: 365 year: 2004 end-page: 377 ident: bib13 article-title: Hybrid Taguchi-genetic algorithm for global numerical optimization publication-title: IEEE Trans. Evol. Comput. – volume: 14 start-page: 79 year: 2003 end-page: 88 ident: bib11 article-title: Tuning of the structure and parameters of neural network using an improved genetic algorithm publication-title: IEEE Trans. Neural Netw. – reference: R. Storn, K. Price, Differential Evolution—A Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces, Technical Report, International Computer Science Institute (ICSI), Berkeley, California, 1995. – volume: 21 start-page: 158 year: 2010 end-page: 162 ident: bib5 article-title: Op-elm publication-title: IEEE Trans. Neural Netw. – reference: R.D. King, S. Muggleton, R.A. Lewis, M.J. Sternberg, Drug design by machine learning: the use of inductive logic programming to model the structure-activity relationships of trimethoprim analogues binding to dihydrofolate reductase, in: Proceedings of the National Academy of Sciences of the United States of America, vol. 89, 1992, pp. 11322–11326. – volume: 73 start-page: 2394 year: 2010 end-page: 2406 ident: bib24 article-title: Deterministic local alignment methods improved by a simple genetic algorithm publication-title: Neurocomputing – year: 1975 ident: bib21 article-title: Adaptation in Natural and Artificial Systems – ident: 10.1016/j.neucom.2013.09.016_bib14 doi: 10.1109/ICNC.2007.13 – volume: 70 start-page: 489 issue: 1–3 year: 2006 ident: 10.1016/j.neucom.2013.09.016_bib6 article-title: Extreme learning machine publication-title: Neurocomputing doi: 10.1016/j.neucom.2005.12.126 – volume: 74 start-page: 2422 issue: 16 year: 2011 ident: 10.1016/j.neucom.2013.09.016_bib1 article-title: Fast automatic two-stage nonlinear model identification based on the extreme learning machine publication-title: Neurocomputing doi: 10.1016/j.neucom.2010.11.035 – year: 2003 ident: 10.1016/j.neucom.2013.09.016_bib19 – volume: 72 start-page: 2618 issue: 10–12 year: 2009 ident: 10.1016/j.neucom.2013.09.016_bib33 article-title: Non-uniform attractor embedding for time series forecasting by fuzzy inference systems publication-title: Neurocomputing doi: 10.1016/j.neucom.2008.10.010 – volume: 27 start-page: 285 issue: 3 year: 2008 ident: 10.1016/j.neucom.2013.09.016_bib9 article-title: Differential evolution and levenberg marquardt trained neural network scheme for nonlinear system identification publication-title: Neural Process. Lett. doi: 10.1007/s11063-008-9077-x – volume: 64 start-page: 829 issue: 5 year: 1996 ident: 10.1016/j.neucom.2013.09.016_bib7 article-title: Regularized orthogonal least squares algorithm for constructing radial basis function networks publication-title: Int. J. Control doi: 10.1080/00207179608921659 – ident: 10.1016/j.neucom.2013.09.016_bib23 doi: 10.1109/ETFA.2011.6059084 – ident: 10.1016/j.neucom.2013.09.016_bib34 – ident: 10.1016/j.neucom.2013.09.016_bib31 – volume: 2 start-page: 359 issue: 5 year: 1989 ident: 10.1016/j.neucom.2013.09.016_bib4 article-title: Multilayer feedforward networks are universal approximators publication-title: Neural Netw. doi: 10.1016/0893-6080(89)90020-8 – year: 2006 ident: 10.1016/j.neucom.2013.09.016_bib27 – volume: 38 start-page: 1759 issue: 10 year: 2005 ident: 10.1016/j.neucom.2013.09.016_bib15 article-title: Evolutionary extreme learning machine publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2005.03.028 – volume: 21 start-page: 158 issue: 1 year: 2010 ident: 10.1016/j.neucom.2013.09.016_bib5 article-title: Op-elm publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2009.2036259 – volume: 17 start-page: 879 issue: 4 year: 2006 ident: 10.1016/j.neucom.2013.09.016_bib18 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 – ident: 10.1016/j.neucom.2013.09.016_bib28 – volume: 74 start-page: 3180 issue: 17 year: 2011 ident: 10.1016/j.neucom.2013.09.016_bib22 article-title: Rules extraction from constructively trained neural networks based on genetic algorithms publication-title: Neurocomputing doi: 10.1016/j.neucom.2011.04.009 – ident: 10.1016/j.neucom.2013.09.016_bib26 – volume: 14 start-page: 79 issue: 1 year: 2003 ident: 10.1016/j.neucom.2013.09.016_bib11 article-title: Tuning of the structure and parameters of neural network using an improved genetic algorithm publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2002.804317 – volume: 73 start-page: 2394 issue: 13–15 year: 2010 ident: 10.1016/j.neucom.2013.09.016_bib24 article-title: Deterministic local alignment methods improved by a simple genetic algorithm publication-title: Neurocomputing doi: 10.1016/j.neucom.2010.01.023 – volume: 2 start-page: 17 year: 1990 ident: 10.1016/j.neucom.2013.09.016_bib17 article-title: Tikhonov's regularization method for ill-posed problems publication-title: Contin. Mech. Thermodyn. doi: 10.1007/BF01170953 – volume: 55 start-page: 577 issue: 3 year: 2007 ident: 10.1016/j.neucom.2013.09.016_bib20 article-title: Antenna design with a mixed integer genetic algorithm publication-title: IEEE Trans. Antennas Propag. doi: 10.1109/TAP.2007.891510 – ident: 10.1016/j.neucom.2013.09.016_bib10 – year: 2004 ident: 10.1016/j.neucom.2013.09.016_bib25 – volume: 36 start-page: 285 issue: 3 year: 2012 ident: 10.1016/j.neucom.2013.09.016_bib16 article-title: Self-adaptive evolutionary extreme learning machine publication-title: Neural Process. Lett. doi: 10.1007/s11063-012-9236-y – ident: 10.1016/j.neucom.2013.09.016_bib29 – ident: 10.1016/j.neucom.2013.09.016_bib30 – ident: 10.1016/j.neucom.2013.09.016_bib3 doi: 10.1109/IJCNN.1989.118638 – volume: 17 start-page: 69 issue: 1 year: 2006 ident: 10.1016/j.neucom.2013.09.016_bib12 article-title: Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2005.860885 – volume: 18 start-page: 934 issue: 7 year: 2005 ident: 10.1016/j.neucom.2013.09.016_bib8 article-title: Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms publication-title: Neural Netw. doi: 10.1016/j.neunet.2005.03.010 – volume: 74 start-page: 1696 issue: 10 year: 2011 ident: 10.1016/j.neucom.2013.09.016_bib2 article-title: Nonlinear system identification using memetic differential evolution trained neural networks publication-title: Neurocomputing doi: 10.1016/j.neucom.2011.02.006 – volume: 8 start-page: 365 issue: 4 year: 2004 ident: 10.1016/j.neucom.2013.09.016_bib13 article-title: Hybrid Taguchi-genetic algorithm for global numerical optimization publication-title: IEEE Trans. Evol. Comput. doi: 10.1109/TEVC.2004.826895 – ident: 10.1016/j.neucom.2013.09.016_bib32 doi: 10.1073/pnas.89.23.11322 – year: 1975 ident: 10.1016/j.neucom.2013.09.016_bib21 |
| SSID | ssj0017129 |
| Score | 2.3834457 |
| Snippet | This paper proposes a learning framework for single-hidden layer feedforward neural networks (SLFN) called optimized extreme learning machine (O-ELM). In... |
| SourceID | proquest pascalfrancis crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 428 |
| SubjectTerms | Algorithmics. Computability. Computer arithmetics Applied sciences Artificial intelligence Computer science; control theory; systems Computer simulation Connectionism. Neural networks Differential evolution Evolution Exact sciences and technology Feedforward Genetic algorithms Learning Neural networks Optimization Optimized extreme learning machine Regularization Simulated annealing Single-hidden layer feedforward neural networks Theoretical computing |
| Title | Learning of a single-hidden layer feedforward neural network using an optimized extreme learning machine |
| URI | https://dx.doi.org/10.1016/j.neucom.2013.09.016 https://www.proquest.com/docview/1531009187 https://www.proquest.com/docview/1671524860 |
| Volume | 129 |
| 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 ScienceDirect 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: PRVESC databaseName: ScienceDirect Freedom Collection Journals 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: 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/eLvHCXMwnV1LaxsxEBbGuRRKm_RB3SRGhV5V67WvYzAxTktzaQO-CUmWbBdn1yT2JYf89szswxBSauhxhaRdZqR5aD_NR8hXK6XPcm5Z7mzOdNQpK6K1zMbIE-eVsA6PBn5ep9Mb_X2WzHpk3N2FQVhla_sbm15b67Zl1EpztFmtRr94ISGLwpJkmJbXZNZaZ8hi8O1xD_MQmZBNvT2ZMOzdXZ-rMV5l2CFmBJygqqudIuv5393T6429B6HFhu3iheGuvdHkmLxpw0h60XzpCemF8h1521E00HbHvifLtn7qglaRWooHA-vAllg3pKRrC_E2jeC_IHJF9CzF6pYwbdlgwymC4hfUlrQCw3K7eghzCrYcTxTpupv3tkZjhg_kZnL5ezxlLbkC85AyblnCnRIijRAh2iIFD1Vw5zy3Oo2p90pmWRJSNH5zLyTXPuiY-3nulHIKFC_UR9IvqzJ8IjQr8qBCIW2uLNiDBCJON4e8K0Ao5nkoBkR1MjW-rTyOBBhr00HM_phGEwY1YXhhoHFA2H7Upqm8caB_1qnLPFtBBpzDgZHDZ9rdvw7TUQ0Z74B86dRtYPfhLxVbhmp3b8BfCFh9Iv9XH5BuIpHs6_N_f-IpeQVPNWRI8DPS397twjlEQ1s3rJf7kBxdXP2YXj8BZKcMZg |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1JSwMxFA6iBwVxF-sawWtsllmPIkpdLyp4C0maaKWdFm0vHvztvjdLQRQFrzNJJryXvCXz5XuEHBkpXZpxwzJrMhaFKGF5MIaZEHhsnRLG4tHAzW3SeYguH-PHGXLa3IVBWGVt-yubXlrr-km7lmZ71Ou173guIYtCSjJMy7GY9VwUyxQzsOOPKc5DpEJWhHsyZti8uT9XgrwKP0HQCHhBVdKdYtnzn_3T4si8gdRCVe7im-Uu3dH5Clmq40h6Uk11lcz4Yo0sNzUaaL1l18lzTaD6RIeBGoonA33PnpE4pKB9AwE3DeDAIHRF-CxFeksYtqjA4RRR8U_UFHQIlmXQe_ddCsYcjxRpvxl3UMIx_QZ5OD-7P-2wuroCc5AzjlnMrRIiCRAimjwBF5Vzax03URIS5xQIMvYJWr-uE5JHzkchc93MKmUVaF6oTTJbDAu_RWiaZ175XJpMGTAIMYSctguJl4dYzHGft4hqZKpdTT2OFTD6usGYvehKExo1oXmu4WGLsGmvUUW98Uf7tFGX_rKENHiHP3ruf9Hu9HOYj0aQ8rbIYaNuDdsP_6mYwg8nbxochoDlJ7Lf2oB0Y4nVvrb_PcUDMt-5v7nW1xe3VztkAd6U-CHBd8ns-HXi9yA0Gtv9cul_AnvqDfs |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Learning+of+a+single-hidden+layer+feedforward+neural+network+using+an+optimized+extreme+learning+machine&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Matias%2C+Tiago&rft.au=Souza%2C+Francisco&rft.au=Araujo%2C+Rui&rft.au=Antunes%2C+Carlos&rft.date=2014-04-10&rft.issn=0925-2312&rft.volume=129&rft.spage=428&rft.epage=436&rft_id=info:doi/10.1016%2Fj.neucom.2013.09.016&rft.externalDBID=NO_FULL_TEXT |
| 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 |