Learning with Rejection View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2016

AUTHORS

Corinna Cortes , Giulia DeSalvo , Mehryar Mohri

ABSTRACT

We introduce a novel framework for classification with a rejection option that consists of simultaneously learning two functions: a classifier along with a rejection function. We present a full theoretical analysis of this framework including new data-dependent learning bounds in terms of the Rademacher complexities of the classifier and rejection families as well as consistency and calibration results. These theoretical guarantees guide us in designing new algorithms that can exploit different kernel-based hypothesis sets for the classifier and rejection functions. We compare and contrast our general framework with the special case of confidence-based rejection for which we devise alternative loss functions and algorithms as well. We report the results of several experiments showing that our kernel-based algorithms can yield a notable improvement over the best existing confidence-based rejection algorithm. More... »

PAGES

67-82

References to SciGraph publications

  • 2008-12. Combining classifiers for improved classification of proteins from sequence or structure in BMC BIOINFORMATICS
  • 1991. Probability in Banach Spaces, Isoperimetry and Processes in NONE
  • 2000-12-21. Multiple Reject Thresholds for Improving Classification Reliability in ADVANCES IN PATTERN RECOGNITION
  • 2002. Support Vector Machines with Embedded Reject Option in PATTERN RECOGNITION WITH SUPPORT VECTOR MACHINES
  • 2000-12-21. An Optimal Reject Rule for Binary Classifiers in ADVANCES IN PATTERN RECOGNITION
  • 2015. Learning with Deep Cascades in ALGORITHMIC LEARNING THEORY
  • Book

    TITLE

    Algorithmic Learning Theory

    ISBN

    978-3-319-46378-0
    978-3-319-46379-7

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-319-46379-7_5

    DOI

    http://dx.doi.org/10.1007/978-3-319-46379-7_5

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1084846384


    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": {
              "name": [
                "Google Research"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Cortes", 
            "givenName": "Corinna", 
            "id": "sg:person.010042472421.96", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010042472421.96"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Courant Institute of Mathematical Sciences", 
              "id": "https://www.grid.ac/institutes/grid.482020.c", 
              "name": [
                "Courant Institute of Mathematical Sciences"
              ], 
              "type": "Organization"
            }, 
            "familyName": "DeSalvo", 
            "givenName": "Giulia", 
            "id": "sg:person.016621272565.61", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016621272565.61"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Courant Institute of Mathematical Sciences", 
              "id": "https://www.grid.ac/institutes/grid.482020.c", 
              "name": [
                "Google Research", 
                "Courant Institute of Mathematical Sciences"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Mohri", 
            "givenName": "Mehryar", 
            "id": "sg:person.014747403275.19", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014747403275.19"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/0031-3203(93)90097-g", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001523844"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0031-3203(93)90097-g", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001523844"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-24486-0_17", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003100289", 
              "https://doi.org/10.1007/978-3-319-24486-0_17"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://app.dimensions.ai/details/publication/pub.1008285500", 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-20212-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008285500", 
              "https://doi.org/10.1007/978-3-642-20212-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-20212-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008285500", 
              "https://doi.org/10.1007/978-3-642-20212-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patrec.2004.09.042", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009470722"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1002/cjs.5550340410", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017149070"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45665-1_6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022351828", 
              "https://doi.org/10.1007/3-540-45665-1_6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/1471-2105-9-389", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026431996", 
              "https://doi.org/10.1186/1471-2105-9-389"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/1471-2105-9-389", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026431996", 
              "https://doi.org/10.1186/1471-2105-9-389"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patrec.2005.10.015", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1036457308"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patrec.2008.03.010", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040968563"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1102351.1102435", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041436602"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-44522-6_89", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1043083224", 
              "https://doi.org/10.1007/3-540-44522-6_89"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-44522-6_89", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1043083224", 
              "https://doi.org/10.1007/3-540-44522-6_89"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-44522-6_63", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046196849", 
              "https://doi.org/10.1007/3-540-44522-6_63"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-44522-6_63", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046196849", 
              "https://doi.org/10.1007/3-540-44522-6_63"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tec.1957.5222035", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061588079"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tit.1970.1054406", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061646711"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1214/aos/1015362183", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1064405846"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icpr.2010.810", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095328219"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2016", 
        "datePublishedReg": "2016-01-01", 
        "description": "We introduce a novel framework for classification with a rejection option that consists of simultaneously learning two functions: a classifier along with a rejection function. We present a full theoretical analysis of this framework including new data-dependent learning bounds in terms of the Rademacher complexities of the classifier and rejection families as well as consistency and calibration results. These theoretical guarantees guide us in designing new algorithms that can exploit different kernel-based hypothesis sets for the classifier and rejection functions. We compare and contrast our general framework with the special case of confidence-based rejection for which we devise alternative loss functions and algorithms as well. We report the results of several experiments showing that our kernel-based algorithms can yield a notable improvement over the best existing confidence-based rejection algorithm.", 
        "editor": [
          {
            "familyName": "Ortner", 
            "givenName": "Ronald", 
            "type": "Person"
          }, 
          {
            "familyName": "Simon", 
            "givenName": "Hans Ulrich", 
            "type": "Person"
          }, 
          {
            "familyName": "Zilles", 
            "givenName": "Sandra", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-319-46379-7_5", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.3127058", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.4313325", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.3489376", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": {
          "isbn": [
            "978-3-319-46378-0", 
            "978-3-319-46379-7"
          ], 
          "name": "Algorithmic Learning Theory", 
          "type": "Book"
        }, 
        "name": "Learning with Rejection", 
        "pagination": "67-82", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-319-46379-7_5"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "77dcb07fed5f0494db671508731c1af7b1ef31ca9ef5d0b5077ce8b5898744ea"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1084846384"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-319-46379-7_5", 
          "https://app.dimensions.ai/details/publication/pub.1084846384"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T21:05", 
        "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_8690_00000279.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-319-46379-7_5"
      }
    ]
     

    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.10.1007/978-3-319-46379-7_5'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-46379-7_5'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-46379-7_5'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-46379-7_5'


     

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

    154 TRIPLES      23 PREDICATES      44 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-319-46379-7_5 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nbf2679756dbe40c8b35abdd40dddb900
    4 schema:citation sg:pub.10.1007/3-540-44522-6_63
    5 sg:pub.10.1007/3-540-44522-6_89
    6 sg:pub.10.1007/3-540-45665-1_6
    7 sg:pub.10.1007/978-3-319-24486-0_17
    8 sg:pub.10.1007/978-3-642-20212-4
    9 sg:pub.10.1186/1471-2105-9-389
    10 https://app.dimensions.ai/details/publication/pub.1008285500
    11 https://doi.org/10.1002/cjs.5550340410
    12 https://doi.org/10.1016/0031-3203(93)90097-g
    13 https://doi.org/10.1016/j.patrec.2004.09.042
    14 https://doi.org/10.1016/j.patrec.2005.10.015
    15 https://doi.org/10.1016/j.patrec.2008.03.010
    16 https://doi.org/10.1109/icpr.2010.810
    17 https://doi.org/10.1109/tec.1957.5222035
    18 https://doi.org/10.1109/tit.1970.1054406
    19 https://doi.org/10.1145/1102351.1102435
    20 https://doi.org/10.1214/aos/1015362183
    21 schema:datePublished 2016
    22 schema:datePublishedReg 2016-01-01
    23 schema:description We introduce a novel framework for classification with a rejection option that consists of simultaneously learning two functions: a classifier along with a rejection function. We present a full theoretical analysis of this framework including new data-dependent learning bounds in terms of the Rademacher complexities of the classifier and rejection families as well as consistency and calibration results. These theoretical guarantees guide us in designing new algorithms that can exploit different kernel-based hypothesis sets for the classifier and rejection functions. We compare and contrast our general framework with the special case of confidence-based rejection for which we devise alternative loss functions and algorithms as well. We report the results of several experiments showing that our kernel-based algorithms can yield a notable improvement over the best existing confidence-based rejection algorithm.
    24 schema:editor N4a01079da08f4545910355954e7a722c
    25 schema:genre chapter
    26 schema:inLanguage en
    27 schema:isAccessibleForFree false
    28 schema:isPartOf N0f326929ad68418c9d9613d51450e1ba
    29 schema:name Learning with Rejection
    30 schema:pagination 67-82
    31 schema:productId N0a52b4e172c44de98acdd87fa055cdab
    32 N52927bfb248c460ea9449ded711d8f9d
    33 N5bb0e688de4449258121007f39361a8d
    34 schema:publisher Nbe3cff9150db439391f0d7c44d05e667
    35 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084846384
    36 https://doi.org/10.1007/978-3-319-46379-7_5
    37 schema:sdDatePublished 2019-04-15T21:05
    38 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    39 schema:sdPublisher N4a35896468004352aaa5bf2b8097687f
    40 schema:url http://link.springer.com/10.1007/978-3-319-46379-7_5
    41 sgo:license sg:explorer/license/
    42 sgo:sdDataset chapters
    43 rdf:type schema:Chapter
    44 N0a52b4e172c44de98acdd87fa055cdab schema:name doi
    45 schema:value 10.1007/978-3-319-46379-7_5
    46 rdf:type schema:PropertyValue
    47 N0e199193321746f18c6ea52e1ee395df schema:name Google Research
    48 rdf:type schema:Organization
    49 N0f326929ad68418c9d9613d51450e1ba schema:isbn 978-3-319-46378-0
    50 978-3-319-46379-7
    51 schema:name Algorithmic Learning Theory
    52 rdf:type schema:Book
    53 N446190248f5a45baa6223be97878c273 schema:familyName Zilles
    54 schema:givenName Sandra
    55 rdf:type schema:Person
    56 N4a01079da08f4545910355954e7a722c rdf:first N7d2129ed70b34d2b9d99db6e7737faff
    57 rdf:rest Nc0367bdb6c1f4b0a9c3e3de63d7f0736
    58 N4a35896468004352aaa5bf2b8097687f schema:name Springer Nature - SN SciGraph project
    59 rdf:type schema:Organization
    60 N52927bfb248c460ea9449ded711d8f9d schema:name dimensions_id
    61 schema:value pub.1084846384
    62 rdf:type schema:PropertyValue
    63 N5bb0e688de4449258121007f39361a8d schema:name readcube_id
    64 schema:value 77dcb07fed5f0494db671508731c1af7b1ef31ca9ef5d0b5077ce8b5898744ea
    65 rdf:type schema:PropertyValue
    66 N64a1a724fd7246e0a30a58738417d8e5 rdf:first sg:person.014747403275.19
    67 rdf:rest rdf:nil
    68 N7d2129ed70b34d2b9d99db6e7737faff schema:familyName Ortner
    69 schema:givenName Ronald
    70 rdf:type schema:Person
    71 N977b2a199fe14b2f857e32f36b5d3e01 rdf:first sg:person.016621272565.61
    72 rdf:rest N64a1a724fd7246e0a30a58738417d8e5
    73 Nbe3cff9150db439391f0d7c44d05e667 schema:location Cham
    74 schema:name Springer International Publishing
    75 rdf:type schema:Organisation
    76 Nbf2679756dbe40c8b35abdd40dddb900 rdf:first sg:person.010042472421.96
    77 rdf:rest N977b2a199fe14b2f857e32f36b5d3e01
    78 Nc0367bdb6c1f4b0a9c3e3de63d7f0736 rdf:first Nc190388c376442c6a624363f8311f929
    79 rdf:rest Nd23e4a19a49e49d1980dea76f53f36aa
    80 Nc190388c376442c6a624363f8311f929 schema:familyName Simon
    81 schema:givenName Hans Ulrich
    82 rdf:type schema:Person
    83 Nd23e4a19a49e49d1980dea76f53f36aa rdf:first N446190248f5a45baa6223be97878c273
    84 rdf:rest rdf:nil
    85 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    86 schema:name Information and Computing Sciences
    87 rdf:type schema:DefinedTerm
    88 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    89 schema:name Artificial Intelligence and Image Processing
    90 rdf:type schema:DefinedTerm
    91 sg:grant.3127058 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-319-46379-7_5
    92 rdf:type schema:MonetaryGrant
    93 sg:grant.3489376 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-319-46379-7_5
    94 rdf:type schema:MonetaryGrant
    95 sg:grant.4313325 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-319-46379-7_5
    96 rdf:type schema:MonetaryGrant
    97 sg:person.010042472421.96 schema:affiliation N0e199193321746f18c6ea52e1ee395df
    98 schema:familyName Cortes
    99 schema:givenName Corinna
    100 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010042472421.96
    101 rdf:type schema:Person
    102 sg:person.014747403275.19 schema:affiliation https://www.grid.ac/institutes/grid.482020.c
    103 schema:familyName Mohri
    104 schema:givenName Mehryar
    105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014747403275.19
    106 rdf:type schema:Person
    107 sg:person.016621272565.61 schema:affiliation https://www.grid.ac/institutes/grid.482020.c
    108 schema:familyName DeSalvo
    109 schema:givenName Giulia
    110 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016621272565.61
    111 rdf:type schema:Person
    112 sg:pub.10.1007/3-540-44522-6_63 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046196849
    113 https://doi.org/10.1007/3-540-44522-6_63
    114 rdf:type schema:CreativeWork
    115 sg:pub.10.1007/3-540-44522-6_89 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043083224
    116 https://doi.org/10.1007/3-540-44522-6_89
    117 rdf:type schema:CreativeWork
    118 sg:pub.10.1007/3-540-45665-1_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022351828
    119 https://doi.org/10.1007/3-540-45665-1_6
    120 rdf:type schema:CreativeWork
    121 sg:pub.10.1007/978-3-319-24486-0_17 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003100289
    122 https://doi.org/10.1007/978-3-319-24486-0_17
    123 rdf:type schema:CreativeWork
    124 sg:pub.10.1007/978-3-642-20212-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008285500
    125 https://doi.org/10.1007/978-3-642-20212-4
    126 rdf:type schema:CreativeWork
    127 sg:pub.10.1186/1471-2105-9-389 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026431996
    128 https://doi.org/10.1186/1471-2105-9-389
    129 rdf:type schema:CreativeWork
    130 https://app.dimensions.ai/details/publication/pub.1008285500 schema:CreativeWork
    131 https://doi.org/10.1002/cjs.5550340410 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017149070
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.1016/0031-3203(93)90097-g schema:sameAs https://app.dimensions.ai/details/publication/pub.1001523844
    134 rdf:type schema:CreativeWork
    135 https://doi.org/10.1016/j.patrec.2004.09.042 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009470722
    136 rdf:type schema:CreativeWork
    137 https://doi.org/10.1016/j.patrec.2005.10.015 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036457308
    138 rdf:type schema:CreativeWork
    139 https://doi.org/10.1016/j.patrec.2008.03.010 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040968563
    140 rdf:type schema:CreativeWork
    141 https://doi.org/10.1109/icpr.2010.810 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095328219
    142 rdf:type schema:CreativeWork
    143 https://doi.org/10.1109/tec.1957.5222035 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061588079
    144 rdf:type schema:CreativeWork
    145 https://doi.org/10.1109/tit.1970.1054406 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061646711
    146 rdf:type schema:CreativeWork
    147 https://doi.org/10.1145/1102351.1102435 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041436602
    148 rdf:type schema:CreativeWork
    149 https://doi.org/10.1214/aos/1015362183 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064405846
    150 rdf:type schema:CreativeWork
    151 https://www.grid.ac/institutes/grid.482020.c schema:alternateName Courant Institute of Mathematical Sciences
    152 schema:name Courant Institute of Mathematical Sciences
    153 Google Research
    154 rdf:type schema:Organization
     




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


    ...