A pruning algorithm with L1/2 regularizer for extreme learning machine View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2014-02

AUTHORS

Ye-tian Fan, Wei Wu, Wen-yu Yang, Qin-wei Fan, Jian Wang

ABSTRACT

Compared with traditional learning methods such as the back propagation (BP) method, extreme learning machine provides much faster learning speed and needs less human intervention, and thus has been widely used. In this paper we combine the L1/2 regularization method with extreme learning machine to prune extreme learning machine. A variable learning coefficient is employed to prevent too large a learning increment. A numerical experiment demonstrates that a network pruned L1/2 regularization has fewer hidden nodes but provides better performance than both the original network and the network pruned by L2 regularization. More... »

PAGES

119-125

References to SciGraph publications

  • 2011-06. Extreme learning machines: a survey in INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
  • 2010-06. L1/2 regularization in SCIENCE CHINA INFORMATION SCIENCES
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1631/jzus.c1300197

    DOI

    http://dx.doi.org/10.1631/jzus.c1300197

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1022137428


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Dalian University of Technology", 
              "id": "https://www.grid.ac/institutes/grid.30055.33", 
              "name": [
                "School of Mathematical Sciences, Dalian University of Technology, 116023, Dalian, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Fan", 
            "givenName": "Ye-tian", 
            "id": "sg:person.01366733747.55", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01366733747.55"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Dalian University of Technology", 
              "id": "https://www.grid.ac/institutes/grid.30055.33", 
              "name": [
                "School of Mathematical Sciences, Dalian University of Technology, 116023, Dalian, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Wu", 
            "givenName": "Wei", 
            "id": "sg:person.07764041751.41", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07764041751.41"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Huazhong Agricultural University", 
              "id": "https://www.grid.ac/institutes/grid.35155.37", 
              "name": [
                "College of Science, Huazhong Agricultural University, 430070, Wuhan, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Yang", 
            "givenName": "Wen-yu", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Dalian University of Technology", 
              "id": "https://www.grid.ac/institutes/grid.30055.33", 
              "name": [
                "School of Mathematical Sciences, Dalian University of Technology, 116023, Dalian, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Fan", 
            "givenName": "Qin-wei", 
            "id": "sg:person.01001100104.42", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01001100104.42"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Dalian University of Technology", 
              "id": "https://www.grid.ac/institutes/grid.30055.33", 
              "name": [
                "School of Mathematical Sciences, Dalian University of Technology, 116023, Dalian, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Wang", 
            "givenName": "Jian", 
            "id": "sg:person.010260171703.53", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010260171703.53"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/j.neucom.2011.12.045", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1006604319"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13042-011-0019-y", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031892380", 
              "https://doi.org/10.1007/s13042-011-0019-y"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11432-010-0090-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031971789", 
              "https://doi.org/10.1007/s11432-010-0090-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11432-010-0090-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031971789", 
              "https://doi.org/10.1007/s11432-010-0090-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tnn.2010.2103956", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1032283951"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0893-6080(89)90020-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1034169987"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0893-6080(89)90020-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1034169987"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2010.12.042", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1034411196"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2005.12.126", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038265102"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1049/el.2012.3642", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1056753764"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/18.959265", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061101789"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tnn.2009.2036259", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061717641"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1137/s003614450037906x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1062877747"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/ijcnn.2004.1380068", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094360980"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icarcv.2004.1468985", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094465133"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1142/9789814324359_0184", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1096017941"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2014-02", 
        "datePublishedReg": "2014-02-01", 
        "description": "Compared with traditional learning methods such as the back propagation (BP) method, extreme learning machine provides much faster learning speed and needs less human intervention, and thus has been widely used. In this paper we combine the L1/2 regularization method with extreme learning machine to prune extreme learning machine. A variable learning coefficient is employed to prevent too large a learning increment. A numerical experiment demonstrates that a network pruned L1/2 regularization has fewer hidden nodes but provides better performance than both the original network and the network pruned by L2 regularization.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1631/jzus.c1300197", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1043550", 
            "issn": [
              "1869-1951", 
              "1869-196X"
            ], 
            "name": "Journal of Zhejiang University SCIENCE C", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "2", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "15"
          }
        ], 
        "name": "A pruning algorithm with L1/2 regularizer for extreme learning machine", 
        "pagination": "119-125", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "6977f12e170914d7bdd1afaba9ea1c4b09b6855e0e13e1a5bdae31f1b6cad123"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1631/jzus.c1300197"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1022137428"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1631/jzus.c1300197", 
          "https://app.dimensions.ai/details/publication/pub.1022137428"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-10T15:48", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8664_00000499.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "http://link.springer.com/10.1631/jzus.C1300197"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1631/jzus.c1300197'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1631/jzus.c1300197'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1631/jzus.c1300197'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1631/jzus.c1300197'


     

    This table displays all metadata directly associated to this object as RDF triples.

    135 TRIPLES      21 PREDICATES      41 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1631/jzus.c1300197 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nc52ef2c9963646b0bca81152bb5a7107
    4 schema:citation sg:pub.10.1007/s11432-010-0090-0
    5 sg:pub.10.1007/s13042-011-0019-y
    6 https://doi.org/10.1016/0893-6080(89)90020-8
    7 https://doi.org/10.1016/j.neucom.2005.12.126
    8 https://doi.org/10.1016/j.neucom.2010.12.042
    9 https://doi.org/10.1016/j.neucom.2011.12.045
    10 https://doi.org/10.1049/el.2012.3642
    11 https://doi.org/10.1109/18.959265
    12 https://doi.org/10.1109/icarcv.2004.1468985
    13 https://doi.org/10.1109/ijcnn.2004.1380068
    14 https://doi.org/10.1109/tnn.2009.2036259
    15 https://doi.org/10.1109/tnn.2010.2103956
    16 https://doi.org/10.1137/s003614450037906x
    17 https://doi.org/10.1142/9789814324359_0184
    18 schema:datePublished 2014-02
    19 schema:datePublishedReg 2014-02-01
    20 schema:description Compared with traditional learning methods such as the back propagation (BP) method, extreme learning machine provides much faster learning speed and needs less human intervention, and thus has been widely used. In this paper we combine the L1/2 regularization method with extreme learning machine to prune extreme learning machine. A variable learning coefficient is employed to prevent too large a learning increment. A numerical experiment demonstrates that a network pruned L1/2 regularization has fewer hidden nodes but provides better performance than both the original network and the network pruned by L2 regularization.
    21 schema:genre research_article
    22 schema:inLanguage en
    23 schema:isAccessibleForFree false
    24 schema:isPartOf Na671c60e6bdf4e3e87f21d94763a1ed4
    25 Ne95e23bce96f41b68b7d54335c884528
    26 sg:journal.1043550
    27 schema:name A pruning algorithm with L1/2 regularizer for extreme learning machine
    28 schema:pagination 119-125
    29 schema:productId N2d2f8d963793440dac89818e9bb16206
    30 Nf169f99881374250bdc1ed18bbb3a093
    31 Nf2c4395a0cd8400fae5cd026e9df54fb
    32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022137428
    33 https://doi.org/10.1631/jzus.c1300197
    34 schema:sdDatePublished 2019-04-10T15:48
    35 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    36 schema:sdPublisher Na8de2302dfcd48ac8f4806e59a08f8c7
    37 schema:url http://link.springer.com/10.1631/jzus.C1300197
    38 sgo:license sg:explorer/license/
    39 sgo:sdDataset articles
    40 rdf:type schema:ScholarlyArticle
    41 N0338bf501bff496f933cffba091afb17 rdf:first sg:person.01001100104.42
    42 rdf:rest N74c416cea46a47f0850433d5683e9ccf
    43 N2d2f8d963793440dac89818e9bb16206 schema:name dimensions_id
    44 schema:value pub.1022137428
    45 rdf:type schema:PropertyValue
    46 N320b08b2211d4b449b127ab76c14eac4 schema:affiliation https://www.grid.ac/institutes/grid.35155.37
    47 schema:familyName Yang
    48 schema:givenName Wen-yu
    49 rdf:type schema:Person
    50 N41ac6348c0c2412aa4c252137b748a40 rdf:first sg:person.07764041751.41
    51 rdf:rest Nd89b5212c9da4570b8903cb4f5f84aed
    52 N74c416cea46a47f0850433d5683e9ccf rdf:first sg:person.010260171703.53
    53 rdf:rest rdf:nil
    54 Na671c60e6bdf4e3e87f21d94763a1ed4 schema:issueNumber 2
    55 rdf:type schema:PublicationIssue
    56 Na8de2302dfcd48ac8f4806e59a08f8c7 schema:name Springer Nature - SN SciGraph project
    57 rdf:type schema:Organization
    58 Nc52ef2c9963646b0bca81152bb5a7107 rdf:first sg:person.01366733747.55
    59 rdf:rest N41ac6348c0c2412aa4c252137b748a40
    60 Nd89b5212c9da4570b8903cb4f5f84aed rdf:first N320b08b2211d4b449b127ab76c14eac4
    61 rdf:rest N0338bf501bff496f933cffba091afb17
    62 Ne95e23bce96f41b68b7d54335c884528 schema:volumeNumber 15
    63 rdf:type schema:PublicationVolume
    64 Nf169f99881374250bdc1ed18bbb3a093 schema:name readcube_id
    65 schema:value 6977f12e170914d7bdd1afaba9ea1c4b09b6855e0e13e1a5bdae31f1b6cad123
    66 rdf:type schema:PropertyValue
    67 Nf2c4395a0cd8400fae5cd026e9df54fb schema:name doi
    68 schema:value 10.1631/jzus.c1300197
    69 rdf:type schema:PropertyValue
    70 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    71 schema:name Information and Computing Sciences
    72 rdf:type schema:DefinedTerm
    73 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    74 schema:name Artificial Intelligence and Image Processing
    75 rdf:type schema:DefinedTerm
    76 sg:journal.1043550 schema:issn 1869-1951
    77 1869-196X
    78 schema:name Journal of Zhejiang University SCIENCE C
    79 rdf:type schema:Periodical
    80 sg:person.01001100104.42 schema:affiliation https://www.grid.ac/institutes/grid.30055.33
    81 schema:familyName Fan
    82 schema:givenName Qin-wei
    83 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01001100104.42
    84 rdf:type schema:Person
    85 sg:person.010260171703.53 schema:affiliation https://www.grid.ac/institutes/grid.30055.33
    86 schema:familyName Wang
    87 schema:givenName Jian
    88 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010260171703.53
    89 rdf:type schema:Person
    90 sg:person.01366733747.55 schema:affiliation https://www.grid.ac/institutes/grid.30055.33
    91 schema:familyName Fan
    92 schema:givenName Ye-tian
    93 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01366733747.55
    94 rdf:type schema:Person
    95 sg:person.07764041751.41 schema:affiliation https://www.grid.ac/institutes/grid.30055.33
    96 schema:familyName Wu
    97 schema:givenName Wei
    98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07764041751.41
    99 rdf:type schema:Person
    100 sg:pub.10.1007/s11432-010-0090-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031971789
    101 https://doi.org/10.1007/s11432-010-0090-0
    102 rdf:type schema:CreativeWork
    103 sg:pub.10.1007/s13042-011-0019-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1031892380
    104 https://doi.org/10.1007/s13042-011-0019-y
    105 rdf:type schema:CreativeWork
    106 https://doi.org/10.1016/0893-6080(89)90020-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034169987
    107 rdf:type schema:CreativeWork
    108 https://doi.org/10.1016/j.neucom.2005.12.126 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038265102
    109 rdf:type schema:CreativeWork
    110 https://doi.org/10.1016/j.neucom.2010.12.042 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034411196
    111 rdf:type schema:CreativeWork
    112 https://doi.org/10.1016/j.neucom.2011.12.045 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006604319
    113 rdf:type schema:CreativeWork
    114 https://doi.org/10.1049/el.2012.3642 schema:sameAs https://app.dimensions.ai/details/publication/pub.1056753764
    115 rdf:type schema:CreativeWork
    116 https://doi.org/10.1109/18.959265 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061101789
    117 rdf:type schema:CreativeWork
    118 https://doi.org/10.1109/icarcv.2004.1468985 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094465133
    119 rdf:type schema:CreativeWork
    120 https://doi.org/10.1109/ijcnn.2004.1380068 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094360980
    121 rdf:type schema:CreativeWork
    122 https://doi.org/10.1109/tnn.2009.2036259 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061717641
    123 rdf:type schema:CreativeWork
    124 https://doi.org/10.1109/tnn.2010.2103956 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032283951
    125 rdf:type schema:CreativeWork
    126 https://doi.org/10.1137/s003614450037906x schema:sameAs https://app.dimensions.ai/details/publication/pub.1062877747
    127 rdf:type schema:CreativeWork
    128 https://doi.org/10.1142/9789814324359_0184 schema:sameAs https://app.dimensions.ai/details/publication/pub.1096017941
    129 rdf:type schema:CreativeWork
    130 https://www.grid.ac/institutes/grid.30055.33 schema:alternateName Dalian University of Technology
    131 schema:name School of Mathematical Sciences, Dalian University of Technology, 116023, Dalian, China
    132 rdf:type schema:Organization
    133 https://www.grid.ac/institutes/grid.35155.37 schema:alternateName Huazhong Agricultural University
    134 schema:name College of Science, Huazhong Agricultural University, 430070, Wuhan, China
    135 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...