The annealing robust backpropagation (ARBP) learning algorithm
Multilayer feedforward neural networks are often referred to as universal approximators. Nevertheless, if the used training data are corrupted by large noise, such as outliers, traditional backpropagation learning schemes may not always come up with acceptable performance. Even though various robust...
Uloženo v:
| Vydáno v: | IEEE transactions on neural networks Ročník 11; číslo 5; s. 1067 - 1077 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
IEEE
01.09.2000
|
| Témata: | |
| ISSN: | 1045-9227 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Multilayer feedforward neural networks are often referred to as universal approximators. Nevertheless, if the used training data are corrupted by large noise, such as outliers, traditional backpropagation learning schemes may not always come up with acceptable performance. Even though various robust learning algorithms have been proposed in the literature, those approaches still suffer from the initialization problem. In those robust learning algorithms, the so-called M-estimator is employed. For the M-estimation type of learning algorithms, the loss function is used to play the role in discriminating against outliers from the majority by degrading the effects of those outliers in learning. However, the loss function used in those algorithms may not correctly discriminate against those outliers. In the paper, the annealing robust backpropagation learning algorithm (ARBP) that adopts the annealing concept into the robust learning algorithms is proposed to deal with the problem of modeling under the existence of outliers. The proposed algorithm has been employed in various examples. Those results all demonstrated the superiority over other robust learning algorithms independent of outliers. In the paper, not only is the annealing concept adopted into the robust learning algorithms but also the annealing schedule k/t was found experimentally to achieve the best performance among other annealing schedules, where k is a constant and t is the epoch number. |
|---|---|
| AbstractList | Multilayer feedforward neural networks are often referred to as universal approximators. Nevertheless, if the used training data are corrupted by large noise, such as outliers, traditional backpropagation learning schemes may not always come up with acceptable performance. Even though various robust learning algorithms have been proposed in the literature, those approaches still suffer from the initialization problem. In those robust learning algorithms, the so-called M-estimator is employed. For the M-estimation type of learning algorithms, the loss function is used to play the role in discriminating against outliers from the majority by degrading the effects of those outliers in learning. However, the loss function used in those algorithms may not correctly discriminate against those outliers. In the paper, the annealing robust backpropagation learning algorithm (ARBP) that adopts the annealing concept into the robust learning algorithms is proposed to deal with the problem of modeling under the existence of outliers. The proposed algorithm has been employed in various examples. Those results all demonstrated the superiority over other robust learning algorithms independent of outliers. In the paper, not only is the annealing concept adopted into the robust learning algorithms but also the annealing schedule k/t was found experimentally to achieve the best performance among other annealing schedules, where k is a constant and t is the epoch number. Multilayer feedforward neural networks are often referred to as universal approximators. Nevertheless, if the used training data are corrupted by large noise, such as outliers, traditional backpropagation learning schemes may not always come up with acceptable performance. Even though various robust learning algorithms have been proposed in the literature, those approaches still suffer from the initialization problem. In those robust learning algorithms, the so-called M-estimator is employed. For the M-estimation type of learning algorithms, the loss function is used to play the role in discriminating against outliers from the majority by degrading the effects of those outliers in learning. However, the loss function used in those algorithms may not correctly discriminate against those outliers. In this paper, the annealing robust backpropagation learning algorithm (ARBP) that adopts the annealing concept into the robust learning algorithms is proposed to deal with the problem of modeling under the existence of outliers. The proposed algorithm has been employed in various examples. Those results all demonstrated the superiority over other robust learning algorithms independent of outliers. In the paper, not only is the annealing concept adopted into the robust learning algorithms but also the annealing schedule k/t was found experimentally to achieve the best performance among other annealing schedules, where k is a constant and is the epoch number.Multilayer feedforward neural networks are often referred to as universal approximators. Nevertheless, if the used training data are corrupted by large noise, such as outliers, traditional backpropagation learning schemes may not always come up with acceptable performance. Even though various robust learning algorithms have been proposed in the literature, those approaches still suffer from the initialization problem. In those robust learning algorithms, the so-called M-estimator is employed. For the M-estimation type of learning algorithms, the loss function is used to play the role in discriminating against outliers from the majority by degrading the effects of those outliers in learning. However, the loss function used in those algorithms may not correctly discriminate against those outliers. In this paper, the annealing robust backpropagation learning algorithm (ARBP) that adopts the annealing concept into the robust learning algorithms is proposed to deal with the problem of modeling under the existence of outliers. The proposed algorithm has been employed in various examples. Those results all demonstrated the superiority over other robust learning algorithms independent of outliers. In the paper, not only is the annealing concept adopted into the robust learning algorithms but also the annealing schedule k/t was found experimentally to achieve the best performance among other annealing schedules, where k is a constant and is the epoch number. Multilayer feedforward neural networks are often referred to as universal approximators. Nevertheless, if the used training data are corrupted by large noise, such as outliers, traditional backpropagation learning schemes may not always come up with acceptable performance. Even though various robust learning algorithms have been proposed in the literature, those approaches still suffer from the initialization problem. In those robust learning algorithms, the so-called M-estimator is employed. For the M-estimation type of learning algorithms, the loss function is used to play the role in discriminating against outliers from the majority by degrading the effects of those outliers in learning. However, the loss function used in those algorithms may not correctly discriminate against those outliers. In the paper, the annealing robust backpropagation learning algorithm (ARBP) that adopts the annealing concept into the robust learning algorithms is proposed to deal with the problem of modeling under the existence of outliers. The proposed algorithm has been employed in various examples. Those results all demonstrated the superiority over other robust learning algorithms independent of outliers. In the paper, not only is the annealing concept adopted into the robust learning algorithms but also the annealing schedule k/t was found experimentally to achieve the best performance among other annealing schedules, where k is a constant and t is the epoch number Multilayer feedforward neural networks are often referred to as universal approximators. Nevertheless, if the used training data are corrupted by large noise, such as outliers, traditional backpropagation learning schemes may not always come up with acceptable performance. Even though various robust learning algorithms have been proposed in the literature, those approaches still suffer from the initialization problem. In those robust learning algorithms, the so-called M-estimator is employed. For the M-estimation type of learning algorithms, the loss function is used to play the role in discriminating against outliers from the majority by degrading the effects of those outliers in learning. However, the loss function used in those algorithms may not correctly discriminate against those outliers. In this paper, the annealing robust backpropagation learning algorithm (ARBP) that adopts the annealing concept into the robust learning algorithms is proposed to deal with the problem of modeling under the existence of outliers. The proposed algorithm has been employed in various examples. Those results all demonstrated the superiority over other robust learning algorithms independent of outliers. In the paper, not only is the annealing concept adopted into the robust learning algorithms but also the annealing schedule k/t was found experimentally to achieve the best performance among other annealing schedules, where k is a constant and is the epoch number. |
| Author | Chin-Ching Hsiao Shun-Feng Su Chen-Chia Chuang |
| Author_xml | – sequence: 1 givenname: C C surname: Chuang fullname: Chuang, C C organization: Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan 10772, R.O.C – sequence: 2 givenname: S F surname: Su fullname: Su, S F – sequence: 3 givenname: C C surname: Hsiao fullname: Hsiao, C C |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/18249835$$D View this record in MEDLINE/PubMed |
| BookMark | eNqF0T1PwzAQBmAPRbQUBlYGlAno0NZ2_LkglYovqRIIdbccx2kDiVPsZODfk5LSASGYbrjnXp3ujkDPVc4CcIrgBCEopxxPBIeQwB4YIEjoWGLM--AohFcIEaGQHYI-EphIEdMBuF6ubaSds7rI3SryVdKEOkq0edv4aqNXus4rF13NXm6eR1FhtXdbpotV5fN6XR6Dg0wXwZ7s6hAs726X84fx4un-cT5bjA2hvB4jIyXDkguTQE0QTkViZMaYRKTtZIynHEGDTEY0NZrJhKY4wbFJmICYmngILrvYdqn3xoZalXkwtii0s1UTVJvDCEIi_lfyOCaUQCxbefGnxIIRjgRq4fkONklpU7Xxean9h_o-YgumHTC-CsHbTJm8_jpc7XVeKATV9jWKY9W9pp0Y_ZjYh_5izzqbW2v3btf8BMcslUw |
| CODEN | ITNNEP |
| CitedBy_id | crossref_primary_10_1049_el_2018_7980 crossref_primary_10_1016_j_petsci_2023_11_010 crossref_primary_10_1007_s10015_014_0150_4 crossref_primary_10_1016_S0165_0114_02_00570_5 crossref_primary_10_1016_j_engappai_2010_10_018 crossref_primary_10_1179_174328105X28829 crossref_primary_10_1002_apj_207 crossref_primary_10_1016_j_jfranklin_2012_02_006 crossref_primary_10_1016_j_neunet_2004_11_007 crossref_primary_10_1016_j_eswa_2016_02_051 crossref_primary_10_1109_TNNLS_2014_2306915 crossref_primary_10_3390_a14090267 crossref_primary_10_1016_j_ins_2015_03_039 crossref_primary_10_1007_s11633_017_1062_2 crossref_primary_10_1007_s10015_009_0710_1 crossref_primary_10_1016_j_eswa_2008_06_017 crossref_primary_10_1016_j_asoc_2006_04_009 crossref_primary_10_1016_j_cmpb_2014_01_016 crossref_primary_10_1109_TNNLS_2013_2251001 crossref_primary_10_1177_1077546309346235 crossref_primary_10_4028_www_scientific_net_AMM_284_287_2120 crossref_primary_10_1002_nbm_3833 crossref_primary_10_1016_j_neucom_2013_04_008 crossref_primary_10_1016_j_asoc_2009_10_017 crossref_primary_10_1016_j_neucom_2017_05_087 crossref_primary_10_1109_TNN_2002_804227 crossref_primary_10_1016_j_eswa_2008_11_053 crossref_primary_10_1109_TR_2024_3399735 crossref_primary_10_1109_TSMCB_2003_811292 crossref_primary_10_20965_jaciii_2007_p0433 crossref_primary_10_1109_TNN_2007_904035 crossref_primary_10_1016_S0925_2312_03_00436_3 crossref_primary_10_1109_TNNLS_2012_2188414 crossref_primary_10_1631_FITEE_1900593 crossref_primary_10_1016_j_neucom_2006_10_033 crossref_primary_10_1016_j_engappai_2011_09_019 crossref_primary_10_1016_j_asoc_2010_12_010 crossref_primary_10_1016_j_eswa_2011_05_078 crossref_primary_10_1016_j_fss_2010_06_003 crossref_primary_10_1080_02331934_2012_674946 crossref_primary_10_1016_j_neunet_2014_06_010 crossref_primary_10_1080_02533839_2003_9670751 crossref_primary_10_1016_j_eswa_2009_12_067 crossref_primary_10_1002_mrm_26749 crossref_primary_10_1016_j_asoc_2010_05_028 crossref_primary_10_1155_2014_256815 crossref_primary_10_1007_s11063_012_9227_z crossref_primary_10_1109_91_971730 crossref_primary_10_1007_s10015_009_0629_6 crossref_primary_10_1007_s00521_024_10289_w crossref_primary_10_1016_j_neunet_2013_11_012 crossref_primary_10_1007_BF02714740 crossref_primary_10_1016_j_gsf_2020_04_011 crossref_primary_10_1016_j_ijar_2009_05_004 crossref_primary_10_1016_j_ijheatmasstransfer_2013_03_025 crossref_primary_10_1109_TII_2019_2954351 crossref_primary_10_3390_s110302426 crossref_primary_10_1016_j_amc_2009_02_058 crossref_primary_10_3390_en9120987 crossref_primary_10_4028_www_scientific_net_AMR_143_144_1295 crossref_primary_10_1007_s00500_015_1690_9 crossref_primary_10_1016_j_eswa_2008_08_072 |
| Cites_doi | 10.1016/0925-2312(95)00000-V 10.1117/12.235956 10.1016/0031-3203(95)00071-2 10.1002/0471725382 10.1049/ip-vis:19960407 10.1109/59.486098 10.1117/12.271496 10.1109/72.105415 10.1109/72.286917 10.1109/18.661502 10.1016/0893-6080(89)90020-8 10.1016/S0165-0114(96)00325-9 10.1109/72.478411 10.7551/mitpress/5271.001.0001 10.1007/978-4-431-66933-3 10.1002/0471725250 10.1007/978-94-015-3994-4 10.1109/72.279188 |
| ContentType | Journal Article |
| DBID | RIA RIE AAYXX CITATION NPM 7SC 8FD JQ2 L7M L~C L~D 7X8 7SP F28 FR3 |
| DOI | 10.1109/72.870040 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic Electronics & Communications Abstracts ANTE: Abstracts in New Technology & Engineering Engineering Research Database |
| DatabaseTitle | CrossRef PubMed Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional MEDLINE - Academic Electronics & Communications Abstracts Engineering Research Database ANTE: Abstracts in New Technology & Engineering |
| DatabaseTitleList | MEDLINE - Academic Technology Research Database PubMed Computer and Information Systems Abstracts |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Anatomy & Physiology Computer Science |
| EndPage | 1077 |
| ExternalDocumentID | 18249835 10_1109_72_870040 870040 |
| Genre | Journal Article |
| GroupedDBID | --- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG ACGFS AETIX AGQYO AGSQL AHBIQ AI. AIBXA ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS S10 TAE TN5 VH1 AAYXX CITATION AAYOK NPM RIG 7SC 8FD JQ2 L7M L~C L~D 7X8 7SP F28 FR3 |
| ID | FETCH-LOGICAL-c457t-1c9962978cb0a412d8bc9f66914c99f67d710c1cf4a5ca69b5d2b23cb68025c3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 131 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000089508300004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1045-9227 |
| IngestDate | Thu Sep 04 17:12:40 EDT 2025 Fri Sep 05 10:30:33 EDT 2025 Thu Sep 04 21:16:03 EDT 2025 Thu Apr 03 06:58:26 EDT 2025 Sat Nov 29 03:59:16 EST 2025 Tue Nov 18 22:13:26 EST 2025 Tue Aug 26 21:00:27 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 5 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c457t-1c9962978cb0a412d8bc9f66914c99f67d710c1cf4a5ca69b5d2b23cb68025c3 |
| Notes | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 ObjectType-Article-1 ObjectType-Feature-2 |
| PMID | 18249835 |
| PQID | 28647181 |
| PQPubID | 23500 |
| PageCount | 11 |
| ParticipantIDs | crossref_citationtrail_10_1109_72_870040 pubmed_primary_18249835 proquest_miscellaneous_914641183 proquest_miscellaneous_28647181 proquest_miscellaneous_733454029 crossref_primary_10_1109_72_870040 ieee_primary_870040 |
| PublicationCentury | 2000 |
| PublicationDate | 2000-09-01 |
| PublicationDateYYYYMMDD | 2000-09-01 |
| PublicationDate_xml | – month: 09 year: 2000 text: 2000-09-01 day: 01 |
| PublicationDecade | 2000 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | IEEE transactions on neural networks |
| PublicationTitleAbbrev | TNN |
| PublicationTitleAlternate | IEEE Trans Neural Netw |
| PublicationYear | 2000 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | kosko (ref1) 1992 ref12 ref14 ref11 ref10 sarle (ref6) 1995 ref2 ref17 li (ref27) 1995 ref16 carpenter (ref28) 1991 kendall (ref21) 1997 sarle (ref24) 1995 chen (ref8) 1998 mcdowall (ref13) 1997; 3077 smith (ref5) 1993 cichocki (ref20) 1993 umasuthan (ref15) 1996; 143 li (ref23) 1995 ref25 ref22 rousseeuw (ref18) 1987 ref7 ref9 ref4 ref3 chen (ref26) 1998 huber (ref19) 1981 |
| References_xml | – ident: ref12 doi: 10.1016/0925-2312(95)00000-V – ident: ref14 doi: 10.1117/12.235956 – year: 1998 ident: ref8 publication-title: On the study of the learning performance for neural networks and neural fuzzy networks – year: 1995 ident: ref27 publication-title: Linear $L_1$ estimator and Huber M-estimator – year: 1993 ident: ref5 publication-title: Neural Networks for Statistical Modeling – ident: ref22 doi: 10.1016/0031-3203(95)00071-2 – year: 1987 ident: ref18 publication-title: Robust Regression and Outlier Detection doi: 10.1002/0471725382 – volume: 143 start-page: 191 year: 1996 ident: ref15 article-title: outlier removal and discontinuity preserving smoothing of range data publication-title: Vision Image and Signal Processing IEE Proceedings- doi: 10.1049/ip-vis:19960407 – ident: ref16 doi: 10.1109/59.486098 – volume: 3077 start-page: 344 year: 1997 ident: ref13 article-title: robust partial least-squares regression: a modular neural network approach publication-title: Proc SPIE doi: 10.1117/12.271496 – start-page: 352 year: 1995 ident: ref6 article-title: stopped training and other remedies for overfitting publication-title: Proc 27th Symp Interface Comput Sci Statist – ident: ref4 doi: 10.1109/72.105415 – ident: ref9 doi: 10.1109/72.286917 – ident: ref7 doi: 10.1109/18.661502 – ident: ref2 doi: 10.1016/0893-6080(89)90020-8 – year: 1998 ident: ref26 publication-title: On the study of the learning performance for neural networks and neural fuzzy networks – ident: ref25 doi: 10.1109/18.661502 – ident: ref17 doi: 10.1016/S0165-0114(96)00325-9 – start-page: 352 year: 1995 ident: ref24 article-title: stopped training and other remedies for overfitting publication-title: Proc 27th Symp Interface Computing Sci Statist – ident: ref11 doi: 10.1109/72.478411 – year: 1997 ident: ref21 publication-title: The Advanced Theory of Statistics – year: 1991 ident: ref28 publication-title: Pattern Recognition by Self-Organizing Neural Networks doi: 10.7551/mitpress/5271.001.0001 – year: 1992 ident: ref1 publication-title: Neural Networks and Fuzzy Systems A Dynamical Systems Approach to Machine Intelligence – year: 1993 ident: ref20 publication-title: Neural Networks for Optimization and Signal Processing – year: 1995 ident: ref23 publication-title: Markov Random Field Modeling in Computer Vision doi: 10.1007/978-4-431-66933-3 – year: 1981 ident: ref19 publication-title: Robust Statistics doi: 10.1002/0471725250 – ident: ref3 doi: 10.1007/978-94-015-3994-4 – ident: ref10 doi: 10.1109/72.279188 |
| SSID | ssj0014506 |
| Score | 2.0508277 |
| Snippet | Multilayer feedforward neural networks are often referred to as universal approximators. Nevertheless, if the used training data are corrupted by large noise,... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1067 |
| SubjectTerms | Algorithms Annealing Approximation Back propagation Backpropagation algorithms Degradation Feedforward neural networks Learning Mathematical model Mathematical models Neural networks Neurons Noise robustness Schedules Scheduling algorithm Training data |
| Title | The annealing robust backpropagation (ARBP) learning algorithm |
| URI | https://ieeexplore.ieee.org/document/870040 https://www.ncbi.nlm.nih.gov/pubmed/18249835 https://www.proquest.com/docview/28647181 https://www.proquest.com/docview/733454029 https://www.proquest.com/docview/914641183 |
| Volume | 11 |
| WOSCitedRecordID | wos000089508300004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) issn: 1045-9227 databaseCode: RIE dateStart: 19900101 customDbUrl: isFulltext: true dateEnd: 20111231 titleUrlDefault: https://ieeexplore.ieee.org/ omitProxy: false ssIdentifier: ssj0014506 providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB4V1AMcoF1eCwWsqkJwCCSOY8cXpAUVcagQqjjsLfIrFBUStJtF4t8zdrILSOyBW5RMpNF47JnP8wL4ZbljaCbTyGqbRcyUPgnAxVFsUAHi0snchaklf8TVVT4cyuuuz3aohXHOheQzd-wfQyzf1mbir8pOct-LHfH5ghC8LdWaBQxYFsZoIrjIIkmp6JoIJbE8EfS4_fGd6QmzVOa7lcG8XKx-irFvsNJ5kWTQLvt3-OKqHqwNKkTQD8_kgIS8znBh3oPV6eAG0u3jHiy_6UK4BqeoKkTheat8aToZ1XoybohW5j9yjedNWDtyOPh7dn1EuikTt0Td39aju-bfwzrcXPy-Ob-MurEKkWGZaKLEIMahiB6NjhVLqM21kSXnMmH4peTCotdhElMylRnFpc4s1TQ1mufoIJl0AxarunJbQBIbKyGtUxkTTKGsy5hpzqktUyWFNH04nAq8MF3LcT_54r4I0COWhaBFK7s-_JyRPrZ9Nj4i6nnZzwimb_eni1jg3vABD1W5ejIuaM697U36QOZQiDT1LQipnE-CYuEMYVjah81WQ14ZzBG8ogu7_SFfO7DU1u37hLQfsNiMJm4Xvpqn5m482kMlHuZ7QYlfAM1Q7ZU |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3da9RAEB-kCtYHW69-nFq7FJH6kHaz2exmX4SztFQ8jyL30LewX6nFNpG7nOB_7-wmd1boPfQtJBMYZmd35rfzBfDeCc_RTGaJMy5PuK1CEoCnCbWoALTyqvBxaslYTibFxYU67_tsx1oY731MPvOH4THG8l1jF-Gq7KgIvdgRnz_MOWe0K9ZahQx4HgdpIrzIE8WY7NsIpVQdSXbY_fqf8YnTVNY7ltHAnG7di7VteNr7kWTULfwzeODrAeyMasTQN3_IBxIzO-OV-QC2lqMbSL-TB_DkVh_CHfiEykI0nrg6FKeTWWMW85YYbX8i13jixNUjB6Pvn88_kn7OxCXR15fN7Kr9cfMcpqcn0-OzpB-skFieyzZJLaIchvjRGqp5ylxhrKqEUCnHL5WQDv0Om9qK69xqoUzumGGZNaJAF8lmL2Cjbmr_CkjqqJbKeZ1zyTXKuqLcCMFclWkllR3CwVLgpe2bjofZF9dlBB9UlZKVneyGsL8i_dV12riLaBBkvyJYvt1bLmKJuyOEPHTtm8W8ZIUI1jcdAllDIbMsNCFkaj0JikVwBGLZEF52GvKPwQLhKzqxr-_kaw8en02_jcvxl8nXN7DZVfGH9LS3sNHOFn4XHtnf7dV89i6q8l-xN-_0 |
| 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=The+annealing+robust+backpropagation+%28ARBP%29+learning+algorithm&rft.jtitle=IEEE+transactions+on+neural+networks&rft.au=Chen-Chia+Chuang&rft.au=Shun-Feng+Su&rft.au=Chin-Ching+Hsiao&rft.date=2000-09-01&rft.pub=IEEE&rft.issn=1045-9227&rft.volume=11&rft.issue=5&rft.spage=1067&rft.epage=1077&rft_id=info:doi/10.1109%2F72.870040&rft.externalDocID=870040 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1045-9227&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1045-9227&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1045-9227&client=summon |