A hybrid learning algorithm combined with generalized RLS approach for radial basis function neural networks
In this paper, a new hybrid learning method for radial basis function neural networks based on generalized recursive least square algorithm is proposed. Firstly the generalized recursive least square (GRLS) model including a general quadratic weight decay term in the energy function for the training...
Saved in:
| Published in | Applied mathematics and computation Vol. 205; no. 2; pp. 908 - 915 |
|---|---|
| Main Authors | , |
| Format | Journal Article Conference Proceeding |
| Language | English |
| Published |
Amsterdam
Elsevier Inc
15.11.2008
Elsevier |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0096-3003 1873-5649 |
| DOI | 10.1016/j.amc.2008.05.075 |
Cover
Loading…
| Abstract | In this paper, a new hybrid learning method for radial basis function neural networks based on generalized recursive least square algorithm is proposed. Firstly the generalized recursive least square (GRLS) model including a general quadratic weight decay term in the energy function for the training of RBF neural networks is described. Then combined with the GRLS approach, a new hybrid learning method is proposed to meet the design goals: improving the generalization ability of the trained network. Finally experimental results demonstrate that our approach can achieve a significantly improved generalization performance of the RBF networks. |
|---|---|
| AbstractList | In this paper, a new hybrid learning method for radial basis function neural networks based on generalized recursive least square algorithm is proposed. Firstly the generalized recursive least square (GRLS) model including a general quadratic weight decay term in the energy function for the training of RBF neural networks is described. Then combined with the GRLS approach, a new hybrid learning method is proposed to meet the design goals: improving the generalization ability of the trained network. Finally experimental results demonstrate that our approach can achieve a significantly improved generalization performance of the RBF networks. |
| Author | Zhai, Chuan-Min Du, Ji-Xiang |
| Author_xml | – sequence: 1 givenname: Ji-Xiang surname: Du fullname: Du, Ji-Xiang email: du_jx@iim.ac.cn organization: Department of Computer Science and Technology, Huaqiao University, Quanzhou, Fujian 362021, PR China – sequence: 2 givenname: Chuan-Min surname: Zhai fullname: Zhai, Chuan-Min organization: Department of Computer Science and Technology, Huaqiao University, Quanzhou, Fujian 362021, PR China |
| BackLink | http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=21205206$$DView record in Pascal Francis |
| BookMark | eNp9kE1rGzEQhkVJoM7HD-hNlx53O5K8q116CqFfYCi0zVmMRpItd6010qYh_fWVcemhh5xeZniegXmv2EWak2fsjYBWgOjf7Vs8UCsBhha6FnT3iq3EoFXT9evxgq0Axr5RAOo1uyplDwC6F-sVm-747tnm6PjkMaeYthyn7Zzjsjtwmg82Ju_4Ux351iefcYq_6-Lb5jvH4zHPSDse5swzuogTt1hi4eEx0RLnxJN_rEaN5WnOP8sNuww4FX_7N6_Zw8cPP-4_N5uvn77c320aUlIvTae1koOwivqwpjAQaegshNH1NEgrFdI4AgbrvHWDG4PASii7lohaa6mu2dvz3SMWwilkTBSLOeZ4wPxspJDQSegrJ84c5bmU7MM_RIA51Wr2ptZqTrUa6EyttTr6P4figqdvl4xxetF8fzZ9ff1X9NkUij6RdzF7Woyb4wv2H7kxll0 |
| CODEN | AMHCBQ |
| CitedBy_id | crossref_primary_10_4018_IJORIS_2018040102 crossref_primary_10_1016_j_engappai_2017_04_017 crossref_primary_10_4028_www_scientific_net_AMR_317_319_1529 |
| Cites_doi | 10.1142/S0218001499000525 10.1162/089976604774201668 10.1016/j.amc.2003.12.105 10.1016/j.neucom.2006.05.003 10.1515/JISYS.1999.9.1.1 10.1109/TNN.2004.836229 10.1109/72.963768 10.1109/34.531803 10.1109/TNN.2005.860857 10.1109/NNSP.1991.239541 10.1162/neco.1992.4.3.448 10.1109/TNN.2004.824424 10.1109/72.839002 10.1142/S0218001499000604 |
| ContentType | Journal Article Conference Proceeding |
| Copyright | 2008 Elsevier Inc. 2009 INIST-CNRS |
| Copyright_xml | – notice: 2008 Elsevier Inc. – notice: 2009 INIST-CNRS |
| DBID | AAYXX CITATION IQODW |
| DOI | 10.1016/j.amc.2008.05.075 |
| DatabaseName | CrossRef Pascal-Francis |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Mathematics |
| EISSN | 1873-5649 |
| EndPage | 915 |
| ExternalDocumentID | 21205206 10_1016_j_amc_2008_05_075 S0096300308003706 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 1B1 1RT 1~. 1~5 23M 4.4 457 4G. 5GY 5VS 6J9 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO ABAOU ABEFU ABFNM ABFRF ABJNI ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFO ACGFS ACRLP ADBBV ADEZE ADGUI ADIYS ADMUD AEBSH AEFWE AEKER AENEX AFFNX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AI. AIEXJ AIGVJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ARUGR ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC CS3 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HLZ HMJ HVGLF HZ~ IHE J1W KOM LG9 M26 M41 MHUIS MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ RXW SBC SDF SDG SES SEW SME SPC SPCBC SSW SSZ T5K TAE TN5 VH1 VOH WH7 WUQ X6Y XPP ZMT ~02 ~G- AATTM AAXKI AAYWO AAYXX ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH EFKBS IQODW |
| ID | FETCH-LOGICAL-c327t-5773281b3c6f4cf8cc705b0f9d6c82b23ac990afbdebd8d9f1ac703b42aa77723 |
| IEDL.DBID | AIKHN |
| ISSN | 0096-3003 |
| IngestDate | Mon Jul 21 09:17:32 EDT 2025 Thu Apr 24 23:08:52 EDT 2025 Tue Jul 01 04:07:07 EDT 2025 Fri Feb 23 02:18:48 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Keywords | Hybrid learning Radial basis function neural networks Generalized recursive least square mode Learning Experimental result Numerical analysis Applied mathematics Least squares method Neural network Learning algorithm Recursive algorithm |
| Language | English |
| License | https://www.elsevier.com/tdm/userlicense/1.0 CC BY 4.0 |
| LinkModel | DirectLink |
| MeetingName | Special Issue on Advanced Intelligent Computing Theory and Methodology in Applied Mathematics and Computation |
| MergedId | FETCHMERGED-LOGICAL-c327t-5773281b3c6f4cf8cc705b0f9d6c82b23ac990afbdebd8d9f1ac703b42aa77723 |
| PageCount | 8 |
| ParticipantIDs | pascalfrancis_primary_21205206 crossref_primary_10_1016_j_amc_2008_05_075 crossref_citationtrail_10_1016_j_amc_2008_05_075 elsevier_sciencedirect_doi_10_1016_j_amc_2008_05_075 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2008-11-15 |
| PublicationDateYYYYMMDD | 2008-11-15 |
| PublicationDate_xml | – month: 11 year: 2008 text: 2008-11-15 day: 15 |
| PublicationDecade | 2000 |
| PublicationPlace | Amsterdam |
| PublicationPlace_xml | – name: Amsterdam |
| PublicationTitle | Applied mathematics and computation |
| PublicationYear | 2008 |
| Publisher | Elsevier Inc Elsevier |
| Publisher_xml | – name: Elsevier Inc – name: Elsevier |
| References | Leung, Tsoi, Chan (bib5) 2001; 12 Huang, Horace, Chi (bib12) 2004; 16 Du, Huang (bib8) 2006; 70 Huang (bib13) 2004; 15 Manjunath, Ma (bib9) 1996; 18 Huang, Ma (bib14) 1999; 9 Xu, Wong, Leung (bib4) 2006; 17 Huang, Zhao (bib3) 2005; 162 Mackay (bib6) 1992; 1 Huang (bib11) 1996 J.E. Moody, Note on generalization, regularization and architecture selection in nonlinear systems, in Proceedings of the IEEE Workshop on Neural Networks for Signal Processing, 1991, pp. 1–10. Oyang, Hwang, Ou, Chen, Chen (bib1) 2005; 16 Gomm, Yu (bib2) 2000; 11 Huang (bib10) 1999; 13 Huang (bib15) 1999; 13 Huang (10.1016/j.amc.2008.05.075_bib3) 2005; 162 Huang (10.1016/j.amc.2008.05.075_bib11) 1996 Mackay (10.1016/j.amc.2008.05.075_bib6) 1992; 1 Xu (10.1016/j.amc.2008.05.075_bib4) 2006; 17 Huang (10.1016/j.amc.2008.05.075_bib12) 2004; 16 10.1016/j.amc.2008.05.075_bib7 Huang (10.1016/j.amc.2008.05.075_bib13) 2004; 15 Huang (10.1016/j.amc.2008.05.075_bib14) 1999; 9 Gomm (10.1016/j.amc.2008.05.075_bib2) 2000; 11 Leung (10.1016/j.amc.2008.05.075_bib5) 2001; 12 Huang (10.1016/j.amc.2008.05.075_bib15) 1999; 13 Du (10.1016/j.amc.2008.05.075_bib8) 2006; 70 Huang (10.1016/j.amc.2008.05.075_bib10) 1999; 13 Oyang (10.1016/j.amc.2008.05.075_bib1) 2005; 16 Manjunath (10.1016/j.amc.2008.05.075_bib9) 1996; 18 |
| References_xml | – volume: 11 start-page: 306 year: 2000 end-page: 314 ident: bib2 article-title: Selecting radial basis function network centers with recursive orthogonal least squares training publication-title: IEEE Trans. Neural Network – year: 1996 ident: bib11 article-title: Systematic Theory of Neural Networks for Pattern Recognition – volume: 70 start-page: 592 year: 2006 end-page: 596 ident: bib8 article-title: A novel full structure optimization algorithm for radial basis probabilistic neural networks publication-title: Neurocomputing – volume: 17 start-page: 19 year: 2006 end-page: 34 ident: bib4 article-title: Generalized RLS approach to the training of neural networks publication-title: IEEE Trans. Neural Network – volume: 12 start-page: 1314 year: 2001 end-page: 1332 ident: bib5 article-title: Two regularizers for recursive least squared algorithms in feedforward multilayered neural networks publication-title: IEEE Trans. Neural Network – reference: J.E. Moody, Note on generalization, regularization and architecture selection in nonlinear systems, in Proceedings of the IEEE Workshop on Neural Networks for Signal Processing, 1991, pp. 1–10. – volume: 1 start-page: 448 year: 1992 end-page: 472 ident: bib6 article-title: A practical Bayesian framework for backpropagation networks publication-title: Neural Comput. – volume: 162 start-page: 461 year: 2005 end-page: 473 ident: bib3 article-title: Determining the centers of radial basis probabilities neural networks by recursive orthogonal least square algorithms publication-title: Appl. Math. Comput. – volume: 13 start-page: 945 year: 1999 end-page: 962 ident: bib15 article-title: Application of generalized radial basis function networks to recognition of radar targets publication-title: Int. J. Pattern Recogn. Artif. Intell. – volume: 16 start-page: 1721 year: 2004 end-page: 1762 ident: bib12 article-title: A neural root finder of polynomials based on root moments publication-title: Neural. Comput. – volume: 18 start-page: 837 year: 1996 end-page: 842 ident: bib9 article-title: Texture features for browsing and retrieval of large image data publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 16 start-page: 225 year: 2005 end-page: 236 ident: bib1 article-title: Data classification with radial basis function networks based on a novel kernel density estimation algorithm publication-title: IEEE Trans. Neural Network – volume: 9 start-page: 1 year: 1999 end-page: 38 ident: bib14 article-title: Linear and nonlinear feedforward neural network classifiers: a comprehensive understanding publication-title: J. Intell. Syst. – volume: 15 start-page: 477 year: 2004 end-page: 491 ident: bib13 article-title: A constructive approach for finding arbitrary roots of polynomials by neural networks publication-title: IEEE Trans. Neural Network – volume: 13 start-page: 1083 year: 1999 end-page: 1101 ident: bib10 article-title: Radial basis probabilistic neural networks: model and application publication-title: Int. J. Pattern Recogn. Artif. Intell. – year: 1996 ident: 10.1016/j.amc.2008.05.075_bib11 – volume: 13 start-page: 945 issue: 6 year: 1999 ident: 10.1016/j.amc.2008.05.075_bib15 article-title: Application of generalized radial basis function networks to recognition of radar targets publication-title: Int. J. Pattern Recogn. Artif. Intell. doi: 10.1142/S0218001499000525 – volume: 16 start-page: 1721 issue: 8 year: 2004 ident: 10.1016/j.amc.2008.05.075_bib12 article-title: A neural root finder of polynomials based on root moments publication-title: Neural. Comput. doi: 10.1162/089976604774201668 – volume: 162 start-page: 461 year: 2005 ident: 10.1016/j.amc.2008.05.075_bib3 article-title: Determining the centers of radial basis probabilities neural networks by recursive orthogonal least square algorithms publication-title: Appl. Math. Comput. doi: 10.1016/j.amc.2003.12.105 – volume: 70 start-page: 592 year: 2006 ident: 10.1016/j.amc.2008.05.075_bib8 article-title: A novel full structure optimization algorithm for radial basis probabilistic neural networks publication-title: Neurocomputing doi: 10.1016/j.neucom.2006.05.003 – volume: 9 start-page: 1 issue: 1 year: 1999 ident: 10.1016/j.amc.2008.05.075_bib14 article-title: Linear and nonlinear feedforward neural network classifiers: a comprehensive understanding publication-title: J. Intell. Syst. doi: 10.1515/JISYS.1999.9.1.1 – volume: 16 start-page: 225 issue: 1 year: 2005 ident: 10.1016/j.amc.2008.05.075_bib1 article-title: Data classification with radial basis function networks based on a novel kernel density estimation algorithm publication-title: IEEE Trans. Neural Network doi: 10.1109/TNN.2004.836229 – volume: 12 start-page: 1314 year: 2001 ident: 10.1016/j.amc.2008.05.075_bib5 article-title: Two regularizers for recursive least squared algorithms in feedforward multilayered neural networks publication-title: IEEE Trans. Neural Network doi: 10.1109/72.963768 – volume: 18 start-page: 837 year: 1996 ident: 10.1016/j.amc.2008.05.075_bib9 article-title: Texture features for browsing and retrieval of large image data publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/34.531803 – volume: 17 start-page: 19 year: 2006 ident: 10.1016/j.amc.2008.05.075_bib4 article-title: Generalized RLS approach to the training of neural networks publication-title: IEEE Trans. Neural Network doi: 10.1109/TNN.2005.860857 – ident: 10.1016/j.amc.2008.05.075_bib7 doi: 10.1109/NNSP.1991.239541 – volume: 1 start-page: 448 year: 1992 ident: 10.1016/j.amc.2008.05.075_bib6 article-title: A practical Bayesian framework for backpropagation networks publication-title: Neural Comput. doi: 10.1162/neco.1992.4.3.448 – volume: 15 start-page: 477 issue: 2 year: 2004 ident: 10.1016/j.amc.2008.05.075_bib13 article-title: A constructive approach for finding arbitrary roots of polynomials by neural networks publication-title: IEEE Trans. Neural Network doi: 10.1109/TNN.2004.824424 – volume: 11 start-page: 306 issue: 2 year: 2000 ident: 10.1016/j.amc.2008.05.075_bib2 article-title: Selecting radial basis function network centers with recursive orthogonal least squares training publication-title: IEEE Trans. Neural Network doi: 10.1109/72.839002 – volume: 13 start-page: 1083 year: 1999 ident: 10.1016/j.amc.2008.05.075_bib10 article-title: Radial basis probabilistic neural networks: model and application publication-title: Int. J. Pattern Recogn. Artif. Intell. doi: 10.1142/S0218001499000604 |
| SSID | ssj0007614 |
| Score | 1.9047596 |
| Snippet | In this paper, a new hybrid learning method for radial basis function neural networks based on generalized recursive least square algorithm is proposed.... |
| SourceID | pascalfrancis crossref elsevier |
| SourceType | Index Database Enrichment Source Publisher |
| StartPage | 908 |
| SubjectTerms | Combinatorics Combinatorics. Ordered structures Designs and configurations Exact sciences and technology Generalized recursive least square mode Hybrid learning Mathematical analysis Mathematics Numerical analysis Numerical analysis. Scientific computation Radial basis function neural networks Sciences and techniques of general use |
| Title | A hybrid learning algorithm combined with generalized RLS approach for radial basis function neural networks |
| URI | https://dx.doi.org/10.1016/j.amc.2008.05.075 |
| Volume | 205 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8JAEN4gXDTG-Iz4IHvwZFJou90-joRI8AEHlYRbs91usQYKoXjQg7_dGbolkhgOXje7fcxM5tF-8w0hNwrshgvwfsKG2sQxk8AITDM2hFTShppIOQIbhfsDtzd0HkZ8VCGdshcGYZXa9xc-feWt9UpLS7M1T1Ps8Q2QL4phzsM8pN2u2SxwwbRr7fvH3mDtkKFSL8iYA4R5maz8ubmCeYmp1IhK3jQRbfh3eNqfixyElhTTLn6FoO4hOdC5I20Xj3dEKio7Jnv9NfFqfkImbfr2iU1YVI-DGFMxGc8W6fJtSuEdoQ5WMcWPr3RcEE6nX7Dw_PRCS3ZxCmksXSBlwYRCjEtzirEP9UeR_BJWswI6np-SYffutdMz9EAFQzLbWxrcQ2oeK2LSTRyZ-FJ6Jo9AP7ErfTuymZAQnEQSxSqK_ThILAE7WOTYQniQhrMzUs1mmTonVPmWa1uuRLYdx_O5cGUkFZfKM5Fvx6sTs5RjKDXbOA69mIQlrOw9BNHrKZg8BNHXye36yLyg2ti22SmVE27YSwihYNuxxoYi1zeCCI6IIPfif9e9JLsrIAniA_kVqS4XH-oaspVl1CA7zW-roW3yB_606e4 |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8JAEN4QPKgxxmfEB-7Bk0mhtLt9HAmRoAIHhYRbs91uoaY8AnjQg7_dGbpFSQwHr5vdPmZ259F-8w0hdwr2DRdg_YQFuQkzY9_wTTMyhFTSgpxIMYGFwp2u0-qzpwEfFEgjr4VBWKW2_ZlNX1lrPVLV0qzOkgRrfH3ki7Ix5rFdpN3eYXB88XRWvn5wHpCnZ1TMPoK8TDv_tbkCeYmx1HhKXjERa_i3czqYiQWILM56XfxyQM0jcqgjR1rPHu6YFNTkhOx31rSri1OS1unoA0uwqG4GMaQiHU4h_x-NKbwhZMEqovjplQ4zuunkEwZe2q805xanEMTSORIWpBQ8XLKg6PlQexSpL2F0kgHHF2ek33zoNVqGbqdgSNtylwZ3kZinFtrSiZmMPSldk4egnciRnhVatpDgmkQcRiqMvMiPawJm2CGzhHAhCLfPSXEynagLQpVXc6yaI5Frh7keF44MpeJSuSay7bglYuZyDKTmGseWF2mQg8reAhC97oHJAxB9idyvl8wyoo1tk1munGBjtwTgCLYtK28ocn0j8N-IB3Iu_3fdW7Lb6nXaQfux-3xF9laQEkQK8mtSXM7f1Q3ELcuwvNqX3-ap6rI |
| 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=proceeding&rft.title=Applied+mathematics+and+computation&rft.atitle=A+hybrid+learning+algorithm+combined+with+generalized+RLS+approach+for+radial+basis+function+neural+networks&rft.au=DU%2C+Ji-Xiang&rft.au=ZHAI%2C+Chuan-Min&rft.date=2008-11-15&rft.pub=Elsevier&rft.issn=0096-3003&rft.volume=205&rft.issue=2&rft.spage=908&rft.epage=915&rft_id=info:doi/10.1016%2Fj.amc.2008.05.075&rft.externalDBID=n%2Fa&rft.externalDocID=21205206 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0096-3003&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0096-3003&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0096-3003&client=summon |