Discriminative Representation Learning with Supervised Auto-encoder View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-04

AUTHORS

Fang Du, Jiangshe Zhang, Nannan Ji, Junying Hu, Chunxia Zhang

ABSTRACT

Auto-encoders have been proved to be powerful unsupervised learning methods that able to extract useful features from input data or construct deep artificial neural networks by recent studies. In such settings, the extracted features or the initialized networks only learn the data structure while contain no class information which is a disadvantage in classification tasks. In this paper, we aim to leverage the class information of input to learn a reconstructive and discriminative auto-encoder. More specifically, we introduce a supervised auto-encoder that combines the reconstruction error and the classification error to form a unified objective function while taking the noisy concatenate data and label as input. The noisy concatenate input is constructed in such a method that one third has only original data and zero labels, one third has only label and zero data, the last one third has both original data and label. We show that the representations learned by the proposed supervised auto-encoder are more discriminative and more suitable for classification tasks. Experimental results demonstrate that our model outperforms many existing learning algorithms. More... »

PAGES

507-520

References to SciGraph publications

  • 2014. Contractive De-noising Auto-Encoder in INTELLIGENT COMPUTING THEORY
  • 1988-09. Auto-association by multilayer perceptrons and singular value decomposition in BIOLOGICAL CYBERNETICS
  • 2011. Higher Order Contractive Auto-Encoder in MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES
  • 1986-10. Learning representations by back-propagating errors in NATURE
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s11063-018-9828-2

    DOI

    http://dx.doi.org/10.1007/s11063-018-9828-2

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1103170271


    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": "Xi'an Jiaotong University", 
              "id": "https://www.grid.ac/institutes/grid.43169.39", 
              "name": [
                "School of Mathematics and Statistics, Xi\u2019an Jiaotong University, 710049, Xi\u2019an, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Du", 
            "givenName": "Fang", 
            "id": "sg:person.013544124622.38", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013544124622.38"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Xi'an Jiaotong University", 
              "id": "https://www.grid.ac/institutes/grid.43169.39", 
              "name": [
                "School of Mathematics and Statistics, Xi\u2019an Jiaotong University, 710049, Xi\u2019an, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhang", 
            "givenName": "Jiangshe", 
            "id": "sg:person.010777237601.50", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010777237601.50"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Chang'an University", 
              "id": "https://www.grid.ac/institutes/grid.440661.1", 
              "name": [
                "Department of Mathmatics and Information Science, Chang\u2019an University, 710046, Xi\u2019an, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Ji", 
            "givenName": "Nannan", 
            "id": "sg:person.016101160745.87", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016101160745.87"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Xi'an Jiaotong University", 
              "id": "https://www.grid.ac/institutes/grid.43169.39", 
              "name": [
                "School of Mathematics and Statistics, Xi\u2019an Jiaotong University, 710049, Xi\u2019an, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Hu", 
            "givenName": "Junying", 
            "id": "sg:person.010245516550.14", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010245516550.14"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Xi'an Jiaotong University", 
              "id": "https://www.grid.ac/institutes/grid.43169.39", 
              "name": [
                "School of Mathematics and Statistics, Xi\u2019an Jiaotong University, 710049, Xi\u2019an, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhang", 
            "givenName": "Chunxia", 
            "id": "sg:person.016610531514.07", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016610531514.07"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1145/1273496.1273556", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1002982013"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1162/neco.2006.18.7.1527", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1004707137"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-23783-6_41", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007627921", 
              "https://doi.org/10.1007/978-3-642-23783-6_41"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-23783-6_41", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007627921", 
              "https://doi.org/10.1007/978-3-642-23783-6_41"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tcyb.2014.2361472", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017907727"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/323533a0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018367015", 
              "https://doi.org/10.1038/323533a0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2015.02.023", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026982403"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2015.07.119", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029215156"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-09333-8_84", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1032143737", 
              "https://doi.org/10.1007/978-3-319-09333-8_84"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1390156.1390294", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1034603392"
            ], 
            "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": "sg:pub.10.1007/bf00332918", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1044770331", 
              "https://doi.org/10.1007/bf00332918"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/b978-1-4832-1448-1.50039-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1053572681"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tnnls.2015.2479223", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061718972"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1121/1.395916", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1062347208"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.sigpro.2017.05.030", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1085967134"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icpr.2014.607", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095354143"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icaci.2013.6748512", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095794752"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icassp.2017.7953183", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095991750"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icassp.2017.7953183", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095991750"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2019-04", 
        "datePublishedReg": "2019-04-01", 
        "description": "Auto-encoders have been proved to be powerful unsupervised learning methods that able to extract useful features from input data or construct deep artificial neural networks by recent studies. In such settings, the extracted features or the initialized networks only learn the data structure while contain no class information which is a disadvantage in classification tasks. In this paper, we aim to leverage the class information of input to learn a reconstructive and discriminative auto-encoder. More specifically, we introduce a supervised auto-encoder that combines the reconstruction error and the classification error to form a unified objective function while taking the noisy concatenate data and label as input. The noisy concatenate input is constructed in such a method that one third has only original data and zero labels, one third has only label and zero data, the last one third has both original data and label. We show that the representations learned by the proposed supervised auto-encoder are more discriminative and more suitable for classification tasks. Experimental results demonstrate that our model outperforms many existing learning algorithms.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s11063-018-9828-2", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1132792", 
            "issn": [
              "1370-4621", 
              "1573-773X"
            ], 
            "name": "Neural Processing Letters", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "2", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "49"
          }
        ], 
        "name": "Discriminative Representation Learning with Supervised Auto-encoder", 
        "pagination": "507-520", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "aeedafbcdfbe0f2393e79878cdeea26200c1ccf84fc25c2a03dd764cb9ea5181"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s11063-018-9828-2"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1103170271"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s11063-018-9828-2", 
          "https://app.dimensions.ai/details/publication/pub.1103170271"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T14:20", 
        "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/v90/0000000372_0000000372/records_117123_00000003.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1007%2Fs11063-018-9828-2"
      }
    ]
     

    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.10.1007/s11063-018-9828-2'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s11063-018-9828-2'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11063-018-9828-2'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11063-018-9828-2'


     

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

    150 TRIPLES      21 PREDICATES      45 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s11063-018-9828-2 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nd43d841bb064453d96cba80cefdc6f4b
    4 schema:citation sg:pub.10.1007/978-3-319-09333-8_84
    5 sg:pub.10.1007/978-3-642-23783-6_41
    6 sg:pub.10.1007/bf00332918
    7 sg:pub.10.1038/323533a0
    8 https://doi.org/10.1016/b978-1-4832-1448-1.50039-1
    9 https://doi.org/10.1016/j.neucom.2005.12.126
    10 https://doi.org/10.1016/j.neucom.2015.02.023
    11 https://doi.org/10.1016/j.neucom.2015.07.119
    12 https://doi.org/10.1016/j.sigpro.2017.05.030
    13 https://doi.org/10.1109/icaci.2013.6748512
    14 https://doi.org/10.1109/icassp.2017.7953183
    15 https://doi.org/10.1109/icpr.2014.607
    16 https://doi.org/10.1109/tcyb.2014.2361472
    17 https://doi.org/10.1109/tnnls.2015.2479223
    18 https://doi.org/10.1121/1.395916
    19 https://doi.org/10.1145/1273496.1273556
    20 https://doi.org/10.1145/1390156.1390294
    21 https://doi.org/10.1162/neco.2006.18.7.1527
    22 schema:datePublished 2019-04
    23 schema:datePublishedReg 2019-04-01
    24 schema:description Auto-encoders have been proved to be powerful unsupervised learning methods that able to extract useful features from input data or construct deep artificial neural networks by recent studies. In such settings, the extracted features or the initialized networks only learn the data structure while contain no class information which is a disadvantage in classification tasks. In this paper, we aim to leverage the class information of input to learn a reconstructive and discriminative auto-encoder. More specifically, we introduce a supervised auto-encoder that combines the reconstruction error and the classification error to form a unified objective function while taking the noisy concatenate data and label as input. The noisy concatenate input is constructed in such a method that one third has only original data and zero labels, one third has only label and zero data, the last one third has both original data and label. We show that the representations learned by the proposed supervised auto-encoder are more discriminative and more suitable for classification tasks. Experimental results demonstrate that our model outperforms many existing learning algorithms.
    25 schema:genre research_article
    26 schema:inLanguage en
    27 schema:isAccessibleForFree false
    28 schema:isPartOf N265ec49ed0344d0c8d9f76799d862542
    29 Nf7ecdae157fb466290add1b1fdac3d4d
    30 sg:journal.1132792
    31 schema:name Discriminative Representation Learning with Supervised Auto-encoder
    32 schema:pagination 507-520
    33 schema:productId N576a667b42254e5088d62fc06a917e67
    34 N63bc4fdc99dc44cfa7347bc22c7ae4b1
    35 N83ea7988391f4167acec325a259b85bd
    36 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103170271
    37 https://doi.org/10.1007/s11063-018-9828-2
    38 schema:sdDatePublished 2019-04-11T14:20
    39 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    40 schema:sdPublisher Nbbcca67a16154a108fc39833f5a1c464
    41 schema:url https://link.springer.com/10.1007%2Fs11063-018-9828-2
    42 sgo:license sg:explorer/license/
    43 sgo:sdDataset articles
    44 rdf:type schema:ScholarlyArticle
    45 N265ec49ed0344d0c8d9f76799d862542 schema:volumeNumber 49
    46 rdf:type schema:PublicationVolume
    47 N51a4617e7d5e4084810dd96b2642fa7a rdf:first sg:person.016610531514.07
    48 rdf:rest rdf:nil
    49 N576a667b42254e5088d62fc06a917e67 schema:name readcube_id
    50 schema:value aeedafbcdfbe0f2393e79878cdeea26200c1ccf84fc25c2a03dd764cb9ea5181
    51 rdf:type schema:PropertyValue
    52 N63bc4fdc99dc44cfa7347bc22c7ae4b1 schema:name doi
    53 schema:value 10.1007/s11063-018-9828-2
    54 rdf:type schema:PropertyValue
    55 N83ea7988391f4167acec325a259b85bd schema:name dimensions_id
    56 schema:value pub.1103170271
    57 rdf:type schema:PropertyValue
    58 Nbbcca67a16154a108fc39833f5a1c464 schema:name Springer Nature - SN SciGraph project
    59 rdf:type schema:Organization
    60 Nbcba14fcc91d4bbe9d360ebc1e71b0a2 rdf:first sg:person.010245516550.14
    61 rdf:rest N51a4617e7d5e4084810dd96b2642fa7a
    62 Nd43d841bb064453d96cba80cefdc6f4b rdf:first sg:person.013544124622.38
    63 rdf:rest Nf7f95f38cf3848f5b29a408caaa0b3ee
    64 Ne2d981dad4404351b419b5a11517c6e9 rdf:first sg:person.016101160745.87
    65 rdf:rest Nbcba14fcc91d4bbe9d360ebc1e71b0a2
    66 Nf7ecdae157fb466290add1b1fdac3d4d schema:issueNumber 2
    67 rdf:type schema:PublicationIssue
    68 Nf7f95f38cf3848f5b29a408caaa0b3ee rdf:first sg:person.010777237601.50
    69 rdf:rest Ne2d981dad4404351b419b5a11517c6e9
    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.1132792 schema:issn 1370-4621
    77 1573-773X
    78 schema:name Neural Processing Letters
    79 rdf:type schema:Periodical
    80 sg:person.010245516550.14 schema:affiliation https://www.grid.ac/institutes/grid.43169.39
    81 schema:familyName Hu
    82 schema:givenName Junying
    83 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010245516550.14
    84 rdf:type schema:Person
    85 sg:person.010777237601.50 schema:affiliation https://www.grid.ac/institutes/grid.43169.39
    86 schema:familyName Zhang
    87 schema:givenName Jiangshe
    88 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010777237601.50
    89 rdf:type schema:Person
    90 sg:person.013544124622.38 schema:affiliation https://www.grid.ac/institutes/grid.43169.39
    91 schema:familyName Du
    92 schema:givenName Fang
    93 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013544124622.38
    94 rdf:type schema:Person
    95 sg:person.016101160745.87 schema:affiliation https://www.grid.ac/institutes/grid.440661.1
    96 schema:familyName Ji
    97 schema:givenName Nannan
    98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016101160745.87
    99 rdf:type schema:Person
    100 sg:person.016610531514.07 schema:affiliation https://www.grid.ac/institutes/grid.43169.39
    101 schema:familyName Zhang
    102 schema:givenName Chunxia
    103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016610531514.07
    104 rdf:type schema:Person
    105 sg:pub.10.1007/978-3-319-09333-8_84 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032143737
    106 https://doi.org/10.1007/978-3-319-09333-8_84
    107 rdf:type schema:CreativeWork
    108 sg:pub.10.1007/978-3-642-23783-6_41 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007627921
    109 https://doi.org/10.1007/978-3-642-23783-6_41
    110 rdf:type schema:CreativeWork
    111 sg:pub.10.1007/bf00332918 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044770331
    112 https://doi.org/10.1007/bf00332918
    113 rdf:type schema:CreativeWork
    114 sg:pub.10.1038/323533a0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018367015
    115 https://doi.org/10.1038/323533a0
    116 rdf:type schema:CreativeWork
    117 https://doi.org/10.1016/b978-1-4832-1448-1.50039-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053572681
    118 rdf:type schema:CreativeWork
    119 https://doi.org/10.1016/j.neucom.2005.12.126 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038265102
    120 rdf:type schema:CreativeWork
    121 https://doi.org/10.1016/j.neucom.2015.02.023 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026982403
    122 rdf:type schema:CreativeWork
    123 https://doi.org/10.1016/j.neucom.2015.07.119 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029215156
    124 rdf:type schema:CreativeWork
    125 https://doi.org/10.1016/j.sigpro.2017.05.030 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085967134
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.1109/icaci.2013.6748512 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095794752
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.1109/icassp.2017.7953183 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095991750
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.1109/icpr.2014.607 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095354143
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.1109/tcyb.2014.2361472 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017907727
    134 rdf:type schema:CreativeWork
    135 https://doi.org/10.1109/tnnls.2015.2479223 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061718972
    136 rdf:type schema:CreativeWork
    137 https://doi.org/10.1121/1.395916 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062347208
    138 rdf:type schema:CreativeWork
    139 https://doi.org/10.1145/1273496.1273556 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002982013
    140 rdf:type schema:CreativeWork
    141 https://doi.org/10.1145/1390156.1390294 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034603392
    142 rdf:type schema:CreativeWork
    143 https://doi.org/10.1162/neco.2006.18.7.1527 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004707137
    144 rdf:type schema:CreativeWork
    145 https://www.grid.ac/institutes/grid.43169.39 schema:alternateName Xi'an Jiaotong University
    146 schema:name School of Mathematics and Statistics, Xi’an Jiaotong University, 710049, Xi’an, China
    147 rdf:type schema:Organization
    148 https://www.grid.ac/institutes/grid.440661.1 schema:alternateName Chang'an University
    149 schema:name Department of Mathmatics and Information Science, Chang’an University, 710046, Xi’an, China
    150 rdf:type schema:Organization
     




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


    ...