Stability Analysis of the Modified Levenberg-Marquardt Algorithm for the Artificial Neural Network Training
The Levenberg-Marquardt and Newton are two algorithms that use the Hessian for the artificial neural network learning. In this article, we propose a modified Levenberg-Marquardt algorithm for the artificial neural network learning containing the training and testing stages. The modified Levenberg-Ma...
Saved in:
| Published in | IEEE transaction on neural networks and learning systems Vol. 32; no. 8; pp. 3510 - 3524 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | English |
| Published |
Piscataway
IEEE
01.08.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
| ISSN | 2162-237X 2162-2388 2162-2388 |
| DOI | 10.1109/TNNLS.2020.3015200 |
Cover
| Abstract | The Levenberg-Marquardt and Newton are two algorithms that use the Hessian for the artificial neural network learning. In this article, we propose a modified Levenberg-Marquardt algorithm for the artificial neural network learning containing the training and testing stages. The modified Levenberg-Marquardt algorithm is based on the Levenberg-Marquardt and Newton algorithms but with the following two differences to assure the error stability and weights boundedness: 1) there is a singularity point in the learning rates of the Levenberg-Marquardt and Newton algorithms, while there is not a singularity point in the learning rate of the modified Levenberg-Marquardt algorithm and 2) the Levenberg-Marquardt and Newton algorithms have three different learning rates, while the modified Levenberg-Marquardt algorithm only has one learning rate. The error stability and weights boundedness of the modified Levenberg-Marquardt algorithm are assured based on the Lyapunov technique. We compare the artificial neural network learning with the modified Levenberg-Marquardt, Levenberg-Marquardt, Newton, and stable gradient algorithms for the learning of the electric and brain signals data set. |
|---|---|
| AbstractList | The Levenberg-Marquardt and Newton are two algorithms that use the Hessian for the artificial neural network learning. In this article, we propose a modified Levenberg-Marquardt algorithm for the artificial neural network learning containing the training and testing stages. The modified Levenberg-Marquardt algorithm is based on the Levenberg-Marquardt and Newton algorithms but with the following two differences to assure the error stability and weights boundedness: 1) there is a singularity point in the learning rates of the Levenberg-Marquardt and Newton algorithms, while there is not a singularity point in the learning rate of the modified Levenberg-Marquardt algorithm and 2) the Levenberg-Marquardt and Newton algorithms have three different learning rates, while the modified Levenberg-Marquardt algorithm only has one learning rate. The error stability and weights boundedness of the modified Levenberg-Marquardt algorithm are assured based on the Lyapunov technique. We compare the artificial neural network learning with the modified Levenberg-Marquardt, Levenberg-Marquardt, Newton, and stable gradient algorithms for the learning of the electric and brain signals data set. The Levenberg-Marquardt and Newton are two algorithms that use the Hessian for the artificial neural network learning. In this article, we propose a modified Levenberg-Marquardt algorithm for the artificial neural network learning containing the training and testing stages. The modified Levenberg-Marquardt algorithm is based on the Levenberg-Marquardt and Newton algorithms but with the following two differences to assure the error stability and weights boundedness: 1) there is a singularity point in the learning rates of the Levenberg-Marquardt and Newton algorithms, while there is not a singularity point in the learning rate of the modified Levenberg-Marquardt algorithm and 2) the Levenberg-Marquardt and Newton algorithms have three different learning rates, while the modified Levenberg-Marquardt algorithm only has one learning rate. The error stability and weights boundedness of the modified Levenberg-Marquardt algorithm are assured based on the Lyapunov technique. We compare the artificial neural network learning with the modified Levenberg-Marquardt, Levenberg-Marquardt, Newton, and stable gradient algorithms for the learning of the electric and brain signals data set.The Levenberg-Marquardt and Newton are two algorithms that use the Hessian for the artificial neural network learning. In this article, we propose a modified Levenberg-Marquardt algorithm for the artificial neural network learning containing the training and testing stages. The modified Levenberg-Marquardt algorithm is based on the Levenberg-Marquardt and Newton algorithms but with the following two differences to assure the error stability and weights boundedness: 1) there is a singularity point in the learning rates of the Levenberg-Marquardt and Newton algorithms, while there is not a singularity point in the learning rate of the modified Levenberg-Marquardt algorithm and 2) the Levenberg-Marquardt and Newton algorithms have three different learning rates, while the modified Levenberg-Marquardt algorithm only has one learning rate. The error stability and weights boundedness of the modified Levenberg-Marquardt algorithm are assured based on the Lyapunov technique. We compare the artificial neural network learning with the modified Levenberg-Marquardt, Levenberg-Marquardt, Newton, and stable gradient algorithms for the learning of the electric and brain signals data set. |
| Author | Rubio, Jose de Jesus |
| Author_xml | – sequence: 1 givenname: Jose de Jesus orcidid: 0000-0002-2005-5979 surname: Rubio fullname: Rubio, Jose de Jesus email: rubio.josedejesus@gmail.com organization: Sección de Estudios de Posgrado e Investigación, Esime Azcapotzalco, Instituto Politécnico Nacional, Ciudad de México, Mexico |
| BookMark | eNp9kcFO3DAQhq2KqlDKC7QXS730ku3YsRP7uEIUKi3bA1upt8hJxoshG4PtgPbt8e4iDhzqy_jw_TOj-T6To9GPSMhXBjPGQP9cLZeLmxkHDrMSmOQAH8gJZxUveKnU0du__ndMzmK8g_wqkJXQn8hxyRVoLeoTcn-TTOsGl7Z0PpphG12k3tJ0i_Ta98467OkCn3BsMayLaxMeJxP6ROfD2geXbjfU-rDH5yFlvHNmoEucwr6kZx_u6SoYN7px_YV8tGaIePZaT8nfXxer86ti8efy9_l8UXSlFqlgkimFBi1oK7Rgpq1Ur4Hn3eu2N13XgsFSaWitVlWvhe4qFAiWQysEt-Up-XHo-xD844QxNRsXOxwGM6KfYsNFKSVXSkJGv79D7_wU8iEyJWWta1VJnSl-oLrgYwxom4fgNiZsGwbNzkazt9HsbDSvNnJIvQt1Lpnk_JjyPYb_R78dog4R32ZpVmd_VfkCDpuYXQ |
| CODEN | ITNNAL |
| CitedBy_id | crossref_primary_10_1016_j_neunet_2023_01_039 crossref_primary_10_1155_2022_8585978 crossref_primary_10_3390_polym15132813 crossref_primary_10_1007_s11664_023_10897_7 crossref_primary_10_1016_j_tws_2024_112289 crossref_primary_10_1016_j_ins_2022_09_038 crossref_primary_10_1007_s10489_021_02905_2 crossref_primary_10_1016_j_ins_2022_08_060 crossref_primary_10_1016_j_clon_2023_11_031 crossref_primary_10_1109_TFUZZ_2022_3171844 crossref_primary_10_3390_app11146269 crossref_primary_10_1016_j_matdes_2022_110880 crossref_primary_10_1016_j_engappai_2023_106812 crossref_primary_10_1109_TITS_2022_3192574 crossref_primary_10_1007_s00180_024_01457_6 crossref_primary_10_1007_s00521_021_05727_y crossref_primary_10_1016_j_engappai_2023_106138 crossref_primary_10_1016_j_ins_2022_07_090 crossref_primary_10_1109_ACCESS_2020_3035896 crossref_primary_10_1007_s00484_024_02763_w crossref_primary_10_1186_s12885_023_10875_6 crossref_primary_10_1007_s00521_022_08047_x crossref_primary_10_1177_09544070221126021 crossref_primary_10_3233_JIFS_212824 crossref_primary_10_1186_s12871_023_02021_3 crossref_primary_10_1007_s11227_021_04045_3 crossref_primary_10_1016_j_future_2023_11_012 crossref_primary_10_1016_j_ins_2022_12_053 crossref_primary_10_1016_j_asoc_2021_108258 crossref_primary_10_1016_j_neucom_2022_06_118 crossref_primary_10_1080_01496395_2025_2452425 crossref_primary_10_1007_s12145_022_00869_6 crossref_primary_10_1088_1755_1315_1348_1_012046 crossref_primary_10_1016_j_engappai_2022_105132 crossref_primary_10_3390_en17225525 crossref_primary_10_1016_j_eswa_2022_118120 crossref_primary_10_1007_s11042_022_12630_8 crossref_primary_10_1016_j_ins_2023_119506 crossref_primary_10_1080_02652048_2024_2437362 crossref_primary_10_1007_s11053_024_10367_9 crossref_primary_10_1016_j_energy_2023_128470 crossref_primary_10_3390_en14227632 crossref_primary_10_1007_s12555_020_0902_y crossref_primary_10_1016_j_eswa_2022_116982 crossref_primary_10_1155_2021_5124841 crossref_primary_10_1007_s11227_021_04269_3 crossref_primary_10_1109_JESTIE_2021_3095018 crossref_primary_10_1016_j_ins_2022_10_018 crossref_primary_10_1016_j_eswa_2022_117837 crossref_primary_10_1109_TII_2024_3413325 crossref_primary_10_1007_s40747_021_00567_8 crossref_primary_10_3390_coatings14121587 crossref_primary_10_1007_s00521_021_06253_7 crossref_primary_10_1109_TMECH_2022_3174510 crossref_primary_10_1016_j_ins_2022_11_159 crossref_primary_10_1002_srin_202200694 crossref_primary_10_3390_ma16247683 crossref_primary_10_1038_s41598_024_62629_4 crossref_primary_10_1016_j_engappai_2024_109133 crossref_primary_10_1177_09544070221133967 crossref_primary_10_1109_TED_2021_3077206 crossref_primary_10_1016_j_asoc_2024_111458 crossref_primary_10_1061_JMCEE7_MTENG_17430 crossref_primary_10_1109_TCSII_2023_3335140 crossref_primary_10_1007_s11270_025_07778_6 crossref_primary_10_1016_j_ins_2022_09_027 crossref_primary_10_1016_j_neucom_2024_127246 crossref_primary_10_1109_JSEN_2023_3277483 crossref_primary_10_1364_AO_470907 crossref_primary_10_1016_j_optlaseng_2022_107225 crossref_primary_10_1109_TIE_2022_3219106 crossref_primary_10_1007_s00521_021_06203_3 crossref_primary_10_1016_j_ins_2023_119725 crossref_primary_10_1007_s12667_023_00634_8 crossref_primary_10_1016_j_dsp_2022_103796 crossref_primary_10_1007_s10462_024_10802_6 crossref_primary_10_1111_exsy_13454 crossref_primary_10_1109_TEC_2024_3401483 crossref_primary_10_1016_j_eswa_2022_117499 crossref_primary_10_3389_fpubh_2022_892789 crossref_primary_10_1016_j_eswa_2023_121633 crossref_primary_10_1016_j_energy_2025_135396 crossref_primary_10_1177_00405175241235400 crossref_primary_10_1038_s41598_022_04943_3 crossref_primary_10_1007_s00170_024_14980_z crossref_primary_10_1016_j_measurement_2024_116293 crossref_primary_10_1007_s13369_022_07377_1 crossref_primary_10_1364_OE_522516 crossref_primary_10_1016_j_jestch_2024_101816 crossref_primary_10_1007_s12530_021_09383_4 crossref_primary_10_1109_TFUZZ_2021_3113560 crossref_primary_10_1109_TCSII_2022_3206792 crossref_primary_10_1016_j_matcom_2024_11_012 crossref_primary_10_1007_s12555_021_0392_6 crossref_primary_10_1007_s11227_022_04439_x crossref_primary_10_3390_math10244730 crossref_primary_10_1016_j_engappai_2024_108979 crossref_primary_10_1007_s11042_022_12502_1 crossref_primary_10_1007_s10489_022_04276_8 crossref_primary_10_1016_j_jprocont_2023_103158 crossref_primary_10_3390_metrology4020019 crossref_primary_10_1007_s11053_022_10034_x crossref_primary_10_1016_j_ins_2023_03_143 crossref_primary_10_1016_j_saa_2024_124678 crossref_primary_10_1016_j_biortech_2025_132291 crossref_primary_10_1155_2021_6665509 crossref_primary_10_1016_j_neucom_2024_127437 crossref_primary_10_3390_polym16172423 crossref_primary_10_3390_computation9100109 crossref_primary_10_1007_s00521_021_05833_x crossref_primary_10_1007_s00500_022_07678_5 crossref_primary_10_1016_j_isci_2024_109093 crossref_primary_10_1007_s00521_021_06169_2 crossref_primary_10_1002_rob_22144 crossref_primary_10_1007_s10489_022_04082_2 crossref_primary_10_1016_j_eswa_2022_117065 crossref_primary_10_1080_00102202_2024_2435303 crossref_primary_10_1155_2022_5106942 crossref_primary_10_3390_app14114416 crossref_primary_10_1016_j_ymssp_2024_111509 crossref_primary_10_1109_TNNLS_2021_3093700 crossref_primary_10_1038_s41598_024_58630_6 crossref_primary_10_1109_TBME_2022_3202751 crossref_primary_10_1007_s10853_024_10178_6 crossref_primary_10_1016_j_neucom_2025_129400 crossref_primary_10_1007_s00521_021_05791_4 crossref_primary_10_1016_j_jmst_2022_05_010 crossref_primary_10_1080_09540091_2022_2026295 |
| Cites_doi | 10.1016/j.neucom.2016.08.109 10.1016/j.asoc.2015.04.013 10.1016/j.jfranklin.2016.10.002 10.1016/j.jfranklin.2017.02.033 10.1007/s00521-017-3156-8 10.1162/neco.1992.4.4.494 10.1016/j.neucom.2016.09.109 10.1016/j.jfranklin.2016.03.005 10.1142/S0129065791000212 10.1007/s00521-014-1763-1 10.1016/j.ins.2017.07.020 10.3233/JIFS-169460 10.1049/ip-cta:20030204 10.1007/BF02551274 10.1109/TII.2017.2777460 10.1016/j.asoc.2015.09.051 10.1049/iet-smt.2012.0138 10.1109/ACCESS.2018.2810190 10.1016/j.asoc.2015.01.045 10.3390/app10124239 10.1016/j.ins.2017.09.059 10.1016/j.asoc.2016.05.030 10.3233/JIFS-17899 10.1007/s00500-019-03775-0 10.1016/j.neucom.2015.08.124 10.1016/j.jfranklin.2017.06.006 10.1016/j.neucom.2015.01.107 10.3233/JIFS-181014 10.1109/TNN.2010.2098481 10.1016/j.neucom.2017.09.079 10.1109/TNNLS.2018.2846775 10.1016/j.neucom.2016.08.150 10.1007/s00521-016-2667-z |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| DBID | 97E RIA RIE AAYXX CITATION 7QF 7QO 7QP 7QQ 7QR 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8 |
| DOI | 10.1109/TNNLS.2020.3015200 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Aluminium Industry Abstracts Biotechnology Research Abstracts Calcium & Calcified Tissue Abstracts Ceramic Abstracts Chemoreception Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Neurosciences Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Biotechnology and BioEngineering Abstracts MEDLINE - Academic |
| DatabaseTitle | CrossRef Materials Research Database Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Materials Business File Aerospace Database Engineered Materials Abstracts Biotechnology Research Abstracts Chemoreception Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Civil Engineering Abstracts Aluminium Industry Abstracts Electronics & Communications Abstracts Ceramic Abstracts Neurosciences Abstracts METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Solid State and Superconductivity Abstracts Engineering Research Database Calcium & Calcified Tissue Abstracts Corrosion Abstracts MEDLINE - Academic |
| DatabaseTitleList | Materials Research Database MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2162-2388 |
| EndPage | 3524 |
| ExternalDocumentID | 10_1109_TNNLS_2020_3015200 9170566 |
| Genre | orig-research |
| GroupedDBID | 0R~ 4.4 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK ACPRK AENEX AFRAH AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF M43 MS~ O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION 7QF 7QO 7QP 7QQ 7QR 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8 |
| ID | FETCH-LOGICAL-c394t-15188eaef09f4941ab68d9025647bdaccb0ae3890bf986d949c6e4e0f20b442f3 |
| IEDL.DBID | RIE |
| ISSN | 2162-237X 2162-2388 |
| IngestDate | Sat Sep 27 20:39:58 EDT 2025 Mon Jun 30 02:27:59 EDT 2025 Thu Apr 24 23:04:16 EDT 2025 Wed Oct 01 00:44:53 EDT 2025 Wed Aug 27 02:39:34 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 8 |
| 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-c394t-15188eaef09f4941ab68d9025647bdaccb0ae3890bf986d949c6e4e0f20b442f3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-2005-5979 |
| PMID | 32809947 |
| PQID | 2557978659 |
| PQPubID | 85436 |
| PageCount | 15 |
| ParticipantIDs | proquest_miscellaneous_2435528850 crossref_citationtrail_10_1109_TNNLS_2020_3015200 ieee_primary_9170566 proquest_journals_2557978659 crossref_primary_10_1109_TNNLS_2020_3015200 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2021-08-01 |
| PublicationDateYYYYMMDD | 2021-08-01 |
| PublicationDate_xml | – month: 08 year: 2021 text: 2021-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE transaction on neural networks and learning systems |
| PublicationTitleAbbrev | TNNLS |
| PublicationYear | 2021 |
| 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 | ref35 ref13 ash (ref29) 1972 ref34 ref12 ref15 ref36 ref14 ref31 ref33 ref11 ref32 ref10 ref2 ref1 ref17 bishop (ref27) 1990 ref16 ref19 ref18 lv (ref8) 2018; 14 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref7 ref9 ref4 ref3 ref6 ref5 jang (ref30) 1996 |
| References_xml | – ident: ref33 doi: 10.1016/j.neucom.2016.08.109 – year: 1972 ident: ref29 publication-title: Real Analysis and Probability – ident: ref23 doi: 10.1016/j.asoc.2015.04.013 – ident: ref20 doi: 10.1016/j.jfranklin.2016.10.002 – ident: ref4 doi: 10.1016/j.jfranklin.2017.02.033 – ident: ref9 doi: 10.1007/s00521-017-3156-8 – ident: ref25 doi: 10.1162/neco.1992.4.4.494 – ident: ref22 doi: 10.1016/j.neucom.2016.09.109 – ident: ref21 doi: 10.1016/j.jfranklin.2016.03.005 – ident: ref26 doi: 10.1142/S0129065791000212 – ident: ref1 doi: 10.1007/s00521-014-1763-1 – ident: ref10 doi: 10.1016/j.ins.2017.07.020 – ident: ref18 doi: 10.3233/JIFS-169460 – ident: ref32 doi: 10.1049/ip-cta:20030204 – ident: ref28 doi: 10.1007/BF02551274 – volume: 14 start-page: 3436 year: 2018 ident: ref8 article-title: Levenberg-arquardt backpropagation training of multilayer neural networks for state estimation of a safety-critical cyber-physical system publication-title: IEEE Trans Ind Informat doi: 10.1109/TII.2017.2777460 – year: 1996 ident: ref30 publication-title: Neuro-Fuzzy and Soft Computing – start-page: 749 year: 1990 ident: ref27 article-title: Curvature-driven smoothing in feedforward networks publication-title: Proc Seattle Int Joint Conf Neural Netw (IJCNN) – ident: ref12 doi: 10.1016/j.asoc.2015.09.051 – ident: ref36 doi: 10.1049/iet-smt.2012.0138 – ident: ref13 doi: 10.1109/ACCESS.2018.2810190 – ident: ref5 doi: 10.1016/j.asoc.2015.01.045 – ident: ref35 doi: 10.3390/app10124239 – ident: ref19 doi: 10.1016/j.ins.2017.09.059 – ident: ref16 doi: 10.1016/j.asoc.2016.05.030 – ident: ref7 doi: 10.3233/JIFS-17899 – ident: ref2 doi: 10.1007/s00500-019-03775-0 – ident: ref15 doi: 10.1016/j.neucom.2015.08.124 – ident: ref24 doi: 10.1016/j.jfranklin.2017.06.006 – ident: ref17 doi: 10.1016/j.neucom.2015.01.107 – ident: ref3 doi: 10.3233/JIFS-181014 – ident: ref31 doi: 10.1109/TNN.2010.2098481 – ident: ref6 doi: 10.1016/j.neucom.2017.09.079 – ident: ref11 doi: 10.1109/TNNLS.2018.2846775 – ident: ref34 doi: 10.1016/j.neucom.2016.08.150 – ident: ref14 doi: 10.1007/s00521-016-2667-z |
| SSID | ssj0000605649 |
| Score | 2.6723194 |
| Snippet | The Levenberg-Marquardt and Newton are two algorithms that use the Hessian for the artificial neural network learning. In this article, we propose a modified... The Levenberg–Marquardt and Newton are two algorithms that use the Hessian for the artificial neural network learning. In this article, we propose a modified... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 3510 |
| SubjectTerms | Algorithms Artificial neural networks Biological neural networks Cost function Error stability Learning Levenberg–Marquardt Machine learning Neural networks Newton Prediction algorithms Singularities Stability analysis Testing Training weights boundedness |
| Title | Stability Analysis of the Modified Levenberg-Marquardt Algorithm for the Artificial Neural Network Training |
| URI | https://ieeexplore.ieee.org/document/9170566 https://www.proquest.com/docview/2557978659 https://www.proquest.com/docview/2435528850 |
| Volume | 32 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2162-2388 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000605649 issn: 2162-237X databaseCode: RIE dateStart: 20120101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT9wwEB4BB8SlvIq6La1ciVvrxes4TnxEqAhV7F5YpL1FflIEbGCbPbS_vmPnoaqtKk6JlEniaMaZb-yZbwBOSmcQd-uCMmc1FVpLakzGKLfCBYTnweSxGnk6k5c34usiX2zA56EWxnufks_8OJ6mvXxX23VcKjtVkftFyk3YLErZ1moN6ykMcblMaJdPJKc8KxZ9jQxTp_PZ7Ooao0GOQSo6QDSNHdjOeIn4KDZW-c0lpR4rf_2Yk7e52IVpP842yeR-vG7M2P78g8LxpR-yB6862EnOWjvZhw2_PIDdvqUD6Wb4Idwj-Ezpsj9IT1dC6kAQJZJp7e4CAlZyFUmfYloYnerVczSxhpw93Naru-bbI0EQnMTjq1p2ChIJQNIhZZyTedeV4jXcXHyZn1_Srh8DtZkSDZ1E8javfWAqCCUm2sjSxW1KKQrjtLWGaY8AiJmgSumUUFZ64VngzAjBQ3YEW8t66d8AybQrOA9cGGOE8h79pEQArWUIhcqNHMGkV0llO7Ly2DPjoUpBC1NV0mgVNVp1Gh3Bp-Gep5aq47_Sh1Evg2SnkhEc95qvutn8vcKwq8BoW-ZqBB-HyzgP4-aKXvp6jTKIO3Neljl7--8nv4MdHvNhUvLgMWw1q7V_j4CmMR-SJf8CbnfxEw |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB6VIkEvFCiIhQJG4gbeeh3HiY8Volpgsxe20t4iP0vVsoEle4Bfz9h5CAFCnBIpk8TRjDPf2DPfALwsnUHcrQvKnNVUaC2pMRmj3AoXEJ4Hk8dq5Gop5-fi_Tpf78HrsRbGe5-Sz_w0nqa9fNfYXVwqO1GR-0XKG3AzF0LkXbXWuKLCEJnLhHf5THLKs2I9VMkwdbJaLhcfMR7kGKaiC0TjOIBbGS8RIcXWKr84pdRl5Y9fc_I3Z4dQDSPt0kyuprvWTO2P30gc__dT7sKdHniS085S7sGe39yHw6GpA-nn-BFcIfxMCbPfyUBYQppAECeSqnGXASErWUTap5gYRiu9_RqNrCWn1xfN9rL99JkgDE7i8VUdPwWJFCDpkHLOyarvS_EAzs_ert7Mad-RgdpMiZbOIn2b1z4wFYQSM21k6eJGpRSFcdpaw7RHCMRMUKV0SigrvfAscGaE4CF7CPubZuMfAcm0KzgPXBhjhPIePaVECK1lCIXKjZzAbFBJbXu68tg147pOYQtTddJoHTVa9xqdwKvxni8dWcc_pY-iXkbJXiUTOB40X_fz-VuNgVeB8bbM1QRejJdxJsbtFb3xzQ5lEHnmvCxz9vjvT34Ot-eralEv3i0_PIEDHrNjUirhMey3251_ivCmNc-SVf8EMzn0YA |
| 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=Stability+Analysis+of+the+Modified+Levenberg-Marquardt+Algorithm+for+the+Artificial+Neural+Network+Training&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Rubio%2C+Jose+de+Jesus&rft.date=2021-08-01&rft.pub=IEEE&rft.issn=2162-237X&rft.volume=32&rft.issue=8&rft.spage=3510&rft.epage=3524&rft_id=info:doi/10.1109%2FTNNLS.2020.3015200&rft_id=info%3Apmid%2F32809947&rft.externalDocID=9170566 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon |