Deep bidirectional intelligence: AlphaZero, deep IA-search, deep IA-infer, and TPC causal learning View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2018-12

AUTHORS

Lei Xu

ABSTRACT

This paper starts at a brief review on AlphaGoZero, Q learning, and Monte-Carlo tree search (MCTS), in a comparison with decades ago studies on A* search and CNneim-A that was proposed in 1986 and shares a scouting technique similar to one used in MCTS. Then, we combine the strengths of AlphaGoZero and CNneim-A, resulting in a family named deep IA-search that consists of Deep Scout A*, Deep CNneim-A, Deep Bi-Scout A*, and V-AlphaGoZero, as well as their extensions. Moreover, relation between search and reasoning motivates to extend deep IA-search to Deep IA-Infer for implementing reasoning. Especially, another early study (Xu and Pearl, Structuring causal tree models with continuous variables. In: Proceedings of the 3rd annual conference on uncertainty in artificial intelligence, pp 170–179 1987) on structuring causal tree is developed into a three phase causal learning approach, namely topology identification, parameter reestimation, and causal ρ-tree search on a casual ρ-diagram that is defined by a set of pairwise correlation coefficient ρ. Algorithms are sketched for discovering casual topologies of triplets, stars, and trees, as well as some topologies of casual ρ-Directed Acyclic Graph (DAG), e.g. ones for Yule–Simpson’s paradox, Pearl’s Sprinkler DAG, and Back door DAG. Furthermore, the classic Boolean SAT problem is extended into one ρ-SAT problem, and the roles of four fundamental mechanisms in an intelligent system are elaborated, with insights on integrating these mechanisms to encode not only variables but also how they are organised, as well as on why deep networks are preferred while extra depth is unnecessary. More... »

PAGES

5

References to SciGraph publications

  • 2015-05. Deep learning in NATURE
  • 1993. Causation, Prediction, and Search in NONE
  • 2010-09. Bayesian Ying-Yang system, best harmony learning, and five action circling in FRONTIERS OF ELECTRICAL AND ELECTRONIC ENGINEERING IN CHINA
  • 2016-01. Mastering the game of Go with deep neural networks and tree search in NATURE
  • 2015-02. Human-level control through deep reinforcement learning in NATURE
  • 2011. Rubin Causal Model in INTERNATIONAL ENCYCLOPEDIA OF STATISTICAL SCIENCE
  • 1988-09. Auto-association by multilayer perceptrons and singular value decomposition in BIOLOGICAL CYBERNETICS
  • 2017-10. Mastering the game of Go without human knowledge in NATURE
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1186/s40535-018-0052-y

    DOI

    http://dx.doi.org/10.1186/s40535-018-0052-y

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1107318360


    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": "Chinese University of Hong Kong", 
              "id": "https://www.grid.ac/institutes/grid.10784.3a", 
              "name": [
                "Centre for Cognitive Machines and Computational Health (CMaCH), The School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, SEIEE Building 3, 800 Dongchuan Road, Minhang District, 200240, Shanghai, China", 
                "Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Xu", 
            "givenName": "Lei", 
            "id": "sg:person.0717266740.53", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0717266740.53"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/s0893-6080(05)80107-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001367521"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0893-6080(05)80107-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001367521"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-04898-2_64", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1002716431", 
              "https://doi.org/10.1007/978-3-642-04898-2_64"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/jproc.2015.2455034", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003288846"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11460-010-0108-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1004408225", 
              "https://doi.org/10.1007/s11460-010-0108-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11460-010-0108-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1004408225", 
              "https://doi.org/10.1007/s11460-010-0108-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://app.dimensions.ai/details/publication/pub.1004816646", 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4612-2748-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1004816646", 
              "https://doi.org/10.1007/978-1-4612-2748-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4612-2748-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1004816646", 
              "https://doi.org/10.1007/978-1-4612-2748-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature14539", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1010020120", 
              "https://doi.org/10.1038/nature14539"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2307/1412107", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1012258410"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neunet.2014.09.003", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013219854"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0004-3702(86)90072-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014162908"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0004-3702(86)90072-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014162908"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1037/h0037350", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1015529465"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.artint.2012.06.009", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024987986"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1214/aoms/1177732676", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029004437"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature14236", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1030517994", 
              "https://doi.org/10.1038/nature14236"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature16961", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039427823", 
              "https://doi.org/10.1038/nature16961"
            ], 
            "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/10.2202/1557-4679.1203", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052750172"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/72.238318", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061218377"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tciaig.2012.2186810", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061548895"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.1985.4767624", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742111"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tssc.1968.300136", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061806130"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1177/089443939100900106", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1063873485"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1177/089443939100900106", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1063873485"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2307/1910129", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1069639071"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icpr.1988.28334", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1086198807"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1609/aimag.v31i3.2303", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1090968457"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature24270", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092261951", 
              "https://doi.org/10.1038/nature24270"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature24270", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092261951", 
              "https://doi.org/10.1038/nature24270"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018-12", 
        "datePublishedReg": "2018-12-01", 
        "description": "This paper starts at a brief review on AlphaGoZero, Q learning, and Monte-Carlo tree search (MCTS), in a comparison with decades ago studies on A* search and CNneim-A that was proposed in 1986 and shares a scouting technique similar to one used in MCTS. Then, we combine the strengths of AlphaGoZero and CNneim-A, resulting in a family named deep IA-search that consists of Deep Scout A*, Deep CNneim-A, Deep Bi-Scout A*, and V-AlphaGoZero, as well as their extensions. Moreover, relation between search and reasoning motivates to extend deep IA-search to Deep IA-Infer for implementing reasoning. Especially, another early study (Xu and Pearl, Structuring causal tree models with continuous variables. In: Proceedings of the 3rd annual conference on uncertainty in artificial intelligence, pp 170\u2013179 1987) on structuring causal tree is developed into a three phase causal learning approach, namely topology identification, parameter reestimation, and causal \u03c1-tree search on a casual \u03c1-diagram that is defined by a set of pairwise correlation coefficient \u03c1. Algorithms are sketched for discovering casual topologies of triplets, stars, and trees, as well as some topologies of casual \u03c1-Directed Acyclic Graph (DAG), e.g. ones for Yule\u2013Simpson\u2019s paradox, Pearl\u2019s Sprinkler DAG, and Back door DAG. Furthermore, the classic Boolean SAT problem is extended into one \u03c1-SAT problem, and the roles of four fundamental mechanisms in an intelligent system are elaborated, with insights on integrating these mechanisms to encode not only variables but also how they are organised, as well as on why deep networks are preferred while extra depth is unnecessary.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1186/s40535-018-0052-y", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1053269", 
            "issn": [
              "2196-0089"
            ], 
            "name": "Applied Informatics", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "5"
          }
        ], 
        "name": "Deep bidirectional intelligence: AlphaZero, deep IA-search, deep IA-infer, and TPC causal learning", 
        "pagination": "5", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "ad1ad461f5c8670d5cdf0b2f8f14a811f2b6bf2bddfdf61517f06c33c3235d6d"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1186/s40535-018-0052-y"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1107318360"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1186/s40535-018-0052-y", 
          "https://app.dimensions.ai/details/publication/pub.1107318360"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-10T19:14", 
        "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_8678_00000542.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1186%2Fs40535-018-0052-y"
      }
    ]
     

    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.10.1186/s40535-018-0052-y'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s40535-018-0052-y'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s40535-018-0052-y'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s40535-018-0052-y'


     

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

    146 TRIPLES      21 PREDICATES      53 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1186/s40535-018-0052-y schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N7410d6bf93ad463c9274fb74250e36c2
    4 schema:citation sg:pub.10.1007/978-1-4612-2748-9
    5 sg:pub.10.1007/978-3-642-04898-2_64
    6 sg:pub.10.1007/bf00332918
    7 sg:pub.10.1007/s11460-010-0108-9
    8 sg:pub.10.1038/nature14236
    9 sg:pub.10.1038/nature14539
    10 sg:pub.10.1038/nature16961
    11 sg:pub.10.1038/nature24270
    12 https://app.dimensions.ai/details/publication/pub.1004816646
    13 https://doi.org/10.1016/0004-3702(86)90072-x
    14 https://doi.org/10.1016/j.artint.2012.06.009
    15 https://doi.org/10.1016/j.neunet.2014.09.003
    16 https://doi.org/10.1016/s0893-6080(05)80107-8
    17 https://doi.org/10.1037/h0037350
    18 https://doi.org/10.1109/72.238318
    19 https://doi.org/10.1109/icpr.1988.28334
    20 https://doi.org/10.1109/jproc.2015.2455034
    21 https://doi.org/10.1109/tciaig.2012.2186810
    22 https://doi.org/10.1109/tpami.1985.4767624
    23 https://doi.org/10.1109/tssc.1968.300136
    24 https://doi.org/10.1177/089443939100900106
    25 https://doi.org/10.1214/aoms/1177732676
    26 https://doi.org/10.1609/aimag.v31i3.2303
    27 https://doi.org/10.2202/1557-4679.1203
    28 https://doi.org/10.2307/1412107
    29 https://doi.org/10.2307/1910129
    30 schema:datePublished 2018-12
    31 schema:datePublishedReg 2018-12-01
    32 schema:description This paper starts at a brief review on AlphaGoZero, Q learning, and Monte-Carlo tree search (MCTS), in a comparison with decades ago studies on A* search and CNneim-A that was proposed in 1986 and shares a scouting technique similar to one used in MCTS. Then, we combine the strengths of AlphaGoZero and CNneim-A, resulting in a family named deep IA-search that consists of Deep Scout A*, Deep CNneim-A, Deep Bi-Scout A*, and V-AlphaGoZero, as well as their extensions. Moreover, relation between search and reasoning motivates to extend deep IA-search to Deep IA-Infer for implementing reasoning. Especially, another early study (Xu and Pearl, Structuring causal tree models with continuous variables. In: Proceedings of the 3rd annual conference on uncertainty in artificial intelligence, pp 170–179 1987) on structuring causal tree is developed into a three phase causal learning approach, namely topology identification, parameter reestimation, and causal ρ-tree search on a casual ρ-diagram that is defined by a set of pairwise correlation coefficient ρ. Algorithms are sketched for discovering casual topologies of triplets, stars, and trees, as well as some topologies of casual ρ-Directed Acyclic Graph (DAG), e.g. ones for Yule–Simpson’s paradox, Pearl’s Sprinkler DAG, and Back door DAG. Furthermore, the classic Boolean SAT problem is extended into one ρ-SAT problem, and the roles of four fundamental mechanisms in an intelligent system are elaborated, with insights on integrating these mechanisms to encode not only variables but also how they are organised, as well as on why deep networks are preferred while extra depth is unnecessary.
    33 schema:genre research_article
    34 schema:inLanguage en
    35 schema:isAccessibleForFree false
    36 schema:isPartOf N2b17e24a7c524cb98fb106ac282f5c9d
    37 N8b976dfc1260499ebfdd8ce2c70c0d4d
    38 sg:journal.1053269
    39 schema:name Deep bidirectional intelligence: AlphaZero, deep IA-search, deep IA-infer, and TPC causal learning
    40 schema:pagination 5
    41 schema:productId N475754677c1d4c0880d7786cbdc59c1c
    42 N6ecc344f0f434eafb1667710be1d4f15
    43 Ncf93eb3e28c841d6a4900f899935e2af
    44 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107318360
    45 https://doi.org/10.1186/s40535-018-0052-y
    46 schema:sdDatePublished 2019-04-10T19:14
    47 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    48 schema:sdPublisher N990683bc0e6d4bc6b2e7ec016046bcd2
    49 schema:url https://link.springer.com/10.1186%2Fs40535-018-0052-y
    50 sgo:license sg:explorer/license/
    51 sgo:sdDataset articles
    52 rdf:type schema:ScholarlyArticle
    53 N2b17e24a7c524cb98fb106ac282f5c9d schema:issueNumber 1
    54 rdf:type schema:PublicationIssue
    55 N475754677c1d4c0880d7786cbdc59c1c schema:name doi
    56 schema:value 10.1186/s40535-018-0052-y
    57 rdf:type schema:PropertyValue
    58 N6ecc344f0f434eafb1667710be1d4f15 schema:name dimensions_id
    59 schema:value pub.1107318360
    60 rdf:type schema:PropertyValue
    61 N7410d6bf93ad463c9274fb74250e36c2 rdf:first sg:person.0717266740.53
    62 rdf:rest rdf:nil
    63 N8b976dfc1260499ebfdd8ce2c70c0d4d schema:volumeNumber 5
    64 rdf:type schema:PublicationVolume
    65 N990683bc0e6d4bc6b2e7ec016046bcd2 schema:name Springer Nature - SN SciGraph project
    66 rdf:type schema:Organization
    67 Ncf93eb3e28c841d6a4900f899935e2af schema:name readcube_id
    68 schema:value ad1ad461f5c8670d5cdf0b2f8f14a811f2b6bf2bddfdf61517f06c33c3235d6d
    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.1053269 schema:issn 2196-0089
    77 schema:name Applied Informatics
    78 rdf:type schema:Periodical
    79 sg:person.0717266740.53 schema:affiliation https://www.grid.ac/institutes/grid.10784.3a
    80 schema:familyName Xu
    81 schema:givenName Lei
    82 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0717266740.53
    83 rdf:type schema:Person
    84 sg:pub.10.1007/978-1-4612-2748-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004816646
    85 https://doi.org/10.1007/978-1-4612-2748-9
    86 rdf:type schema:CreativeWork
    87 sg:pub.10.1007/978-3-642-04898-2_64 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002716431
    88 https://doi.org/10.1007/978-3-642-04898-2_64
    89 rdf:type schema:CreativeWork
    90 sg:pub.10.1007/bf00332918 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044770331
    91 https://doi.org/10.1007/bf00332918
    92 rdf:type schema:CreativeWork
    93 sg:pub.10.1007/s11460-010-0108-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004408225
    94 https://doi.org/10.1007/s11460-010-0108-9
    95 rdf:type schema:CreativeWork
    96 sg:pub.10.1038/nature14236 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030517994
    97 https://doi.org/10.1038/nature14236
    98 rdf:type schema:CreativeWork
    99 sg:pub.10.1038/nature14539 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010020120
    100 https://doi.org/10.1038/nature14539
    101 rdf:type schema:CreativeWork
    102 sg:pub.10.1038/nature16961 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039427823
    103 https://doi.org/10.1038/nature16961
    104 rdf:type schema:CreativeWork
    105 sg:pub.10.1038/nature24270 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092261951
    106 https://doi.org/10.1038/nature24270
    107 rdf:type schema:CreativeWork
    108 https://app.dimensions.ai/details/publication/pub.1004816646 schema:CreativeWork
    109 https://doi.org/10.1016/0004-3702(86)90072-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1014162908
    110 rdf:type schema:CreativeWork
    111 https://doi.org/10.1016/j.artint.2012.06.009 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024987986
    112 rdf:type schema:CreativeWork
    113 https://doi.org/10.1016/j.neunet.2014.09.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013219854
    114 rdf:type schema:CreativeWork
    115 https://doi.org/10.1016/s0893-6080(05)80107-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001367521
    116 rdf:type schema:CreativeWork
    117 https://doi.org/10.1037/h0037350 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015529465
    118 rdf:type schema:CreativeWork
    119 https://doi.org/10.1109/72.238318 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061218377
    120 rdf:type schema:CreativeWork
    121 https://doi.org/10.1109/icpr.1988.28334 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086198807
    122 rdf:type schema:CreativeWork
    123 https://doi.org/10.1109/jproc.2015.2455034 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003288846
    124 rdf:type schema:CreativeWork
    125 https://doi.org/10.1109/tciaig.2012.2186810 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061548895
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.1109/tpami.1985.4767624 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742111
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.1109/tssc.1968.300136 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061806130
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.1177/089443939100900106 schema:sameAs https://app.dimensions.ai/details/publication/pub.1063873485
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.1214/aoms/1177732676 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029004437
    134 rdf:type schema:CreativeWork
    135 https://doi.org/10.1609/aimag.v31i3.2303 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090968457
    136 rdf:type schema:CreativeWork
    137 https://doi.org/10.2202/1557-4679.1203 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052750172
    138 rdf:type schema:CreativeWork
    139 https://doi.org/10.2307/1412107 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012258410
    140 rdf:type schema:CreativeWork
    141 https://doi.org/10.2307/1910129 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069639071
    142 rdf:type schema:CreativeWork
    143 https://www.grid.ac/institutes/grid.10784.3a schema:alternateName Chinese University of Hong Kong
    144 schema:name Centre for Cognitive Machines and Computational Health (CMaCH), The School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, SEIEE Building 3, 800 Dongchuan Road, Minhang District, 200240, Shanghai, China
    145 Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China
    146 rdf:type schema:Organization
     




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


    ...