Toward a Theory of Embodied Statistical Learning View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2008

AUTHORS

Daniel Burfoot , Max Lungarella , Yasuo Kuniyoshi

ABSTRACT

The purpose of this paper is to outline a new formulation of statistical learning that will be more useful and relevant to the field of robotics. The primary motivation for this new perspective is the mismatch between the form of data assumed by current statistical learning algorithms, and the form of data that is actually generated by robotic systems. Specifically, robotic systems generate a vast unlabeled data stream, while most current algorithms are designed to handle limited numbers of discrete, labeled, independent and identically distributed samples. We argue that there is only one meaningful unsupervised learning process that can be applied to a vast data stream: adaptive compression. The compression rate can be used to compare different techniques, and statistical models obtained through adaptive compression should also be useful for other tasks. More... »

PAGES

270-279

References to SciGraph publications

  • 2004. The Autotelic Principle in EMBODIED ARTIFICIAL INTELLIGENCE
  • Book

    TITLE

    From Animals to Animats 10

    ISBN

    978-3-540-69133-4
    978-3-540-69134-1

    Author Affiliations

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-540-69134-1_27

    DOI

    http://dx.doi.org/10.1007/978-3-540-69134-1_27

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1007126851


    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": "University of Tokyo", 
              "id": "https://www.grid.ac/institutes/grid.26999.3d", 
              "name": [
                "The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo\u00a0113-8656, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Burfoot", 
            "givenName": "Daniel", 
            "id": "sg:person.015642422414.16", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015642422414.16"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Artificial Intelligence Laboratory, Andreasstrasse 15, 8050\u00a0Zurich, Switzerland"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Lungarella", 
            "givenName": "Max", 
            "id": "sg:person.015501514105.63", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015501514105.63"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "University of Tokyo", 
              "id": "https://www.grid.ac/institutes/grid.26999.3d", 
              "name": [
                "The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo\u00a0113-8656, Japan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kuniyoshi", 
            "givenName": "Yasuo", 
            "id": "sg:person.013372311431.62", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013372311431.62"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/s0921-8890(05)80025-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001522338"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.ics.2005.12.080", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003429936"
            ], 
            "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": "https://doi.org/10.1098/rstb.1992.0106", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007614297"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0005-1098(78)90005-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018373874"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0005-1098(78)90005-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018373874"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-27833-7_17", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022711395", 
              "https://doi.org/10.1007/978-3-540-27833-7_17"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1006/csla.1996.0011", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029750983"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0079-6123(07)64023-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1036754672"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0004-3702(91)90053-m", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041894242"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0004-3702(91)90053-m", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041894242"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0893-6080(99)00060-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1043895272"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1126/science.1145803", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1053745766"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tnn.1998.712192", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061716400"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/devlrn.2005.1490938", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095226549"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2008", 
        "datePublishedReg": "2008-01-01", 
        "description": "The purpose of this paper is to outline a new formulation of statistical learning that will be more useful and relevant to the field of robotics. The primary motivation for this new perspective is the mismatch between the form of data assumed by current statistical learning algorithms, and the form of data that is actually generated by robotic systems. Specifically, robotic systems generate a vast unlabeled data stream, while most current algorithms are designed to handle limited numbers of discrete, labeled, independent and identically distributed samples. We argue that there is only one meaningful unsupervised learning process that can be applied to a vast data stream: adaptive compression. The compression rate can be used to compare different techniques, and statistical models obtained through adaptive compression should also be useful for other tasks.", 
        "editor": [
          {
            "familyName": "Asada", 
            "givenName": "Minoru", 
            "type": "Person"
          }, 
          {
            "familyName": "Hallam", 
            "givenName": "John C. T.", 
            "type": "Person"
          }, 
          {
            "familyName": "Meyer", 
            "givenName": "Jean-Arcady", 
            "type": "Person"
          }, 
          {
            "familyName": "Tani", 
            "givenName": "Jun", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-540-69134-1_27", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-540-69133-4", 
            "978-3-540-69134-1"
          ], 
          "name": "From Animals to Animats 10", 
          "type": "Book"
        }, 
        "name": "Toward a Theory of Embodied Statistical Learning", 
        "pagination": "270-279", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-540-69134-1_27"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "21f2cc2405dd6370037062d5682b2a6f99b4cc5465a950c6d1f5ae8da3df4227"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1007126851"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-540-69134-1_27", 
          "https://app.dimensions.ai/details/publication/pub.1007126851"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T10:31", 
        "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_8659_00000247.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-540-69134-1_27"
      }
    ]
     

    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.10.1007/978-3-540-69134-1_27'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-69134-1_27'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-69134-1_27'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-69134-1_27'


     

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

    136 TRIPLES      23 PREDICATES      40 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-540-69134-1_27 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nbda69fb4885a4d70b8597d8dddfeac6b
    4 schema:citation sg:pub.10.1007/978-3-540-27833-7_17
    5 https://doi.org/10.1006/csla.1996.0011
    6 https://doi.org/10.1016/0004-3702(91)90053-m
    7 https://doi.org/10.1016/0005-1098(78)90005-5
    8 https://doi.org/10.1016/j.ics.2005.12.080
    9 https://doi.org/10.1016/s0079-6123(07)64023-0
    10 https://doi.org/10.1016/s0893-6080(99)00060-x
    11 https://doi.org/10.1016/s0921-8890(05)80025-9
    12 https://doi.org/10.1098/rstb.1992.0106
    13 https://doi.org/10.1109/devlrn.2005.1490938
    14 https://doi.org/10.1109/tnn.1998.712192
    15 https://doi.org/10.1126/science.1145803
    16 https://doi.org/10.1162/neco.2006.18.7.1527
    17 schema:datePublished 2008
    18 schema:datePublishedReg 2008-01-01
    19 schema:description The purpose of this paper is to outline a new formulation of statistical learning that will be more useful and relevant to the field of robotics. The primary motivation for this new perspective is the mismatch between the form of data assumed by current statistical learning algorithms, and the form of data that is actually generated by robotic systems. Specifically, robotic systems generate a vast unlabeled data stream, while most current algorithms are designed to handle limited numbers of discrete, labeled, independent and identically distributed samples. We argue that there is only one meaningful unsupervised learning process that can be applied to a vast data stream: adaptive compression. The compression rate can be used to compare different techniques, and statistical models obtained through adaptive compression should also be useful for other tasks.
    20 schema:editor Na3052d94868a457faeeefdaaf602a25d
    21 schema:genre chapter
    22 schema:inLanguage en
    23 schema:isAccessibleForFree false
    24 schema:isPartOf Ne41ed87fa3e2466d95db5fe703424341
    25 schema:name Toward a Theory of Embodied Statistical Learning
    26 schema:pagination 270-279
    27 schema:productId N1644737e357345a7abbaf96989dfe3e6
    28 N2266e2ffc6114a719d52f83d762c4eb3
    29 N32f4e0c11be143b191e97df7f5d8bf1f
    30 schema:publisher N21f8ca0cdc434beabed9195f70e8bb9c
    31 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007126851
    32 https://doi.org/10.1007/978-3-540-69134-1_27
    33 schema:sdDatePublished 2019-04-15T10:31
    34 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    35 schema:sdPublisher N0618a6e7dc194d77bc58369622bfd6b3
    36 schema:url http://link.springer.com/10.1007/978-3-540-69134-1_27
    37 sgo:license sg:explorer/license/
    38 sgo:sdDataset chapters
    39 rdf:type schema:Chapter
    40 N0618a6e7dc194d77bc58369622bfd6b3 schema:name Springer Nature - SN SciGraph project
    41 rdf:type schema:Organization
    42 N131c2850e23f43f5a8fc1719870f35e6 rdf:first Nb571b34fc7e24cc8ac45ae0b8d5dff5d
    43 rdf:rest rdf:nil
    44 N1644737e357345a7abbaf96989dfe3e6 schema:name readcube_id
    45 schema:value 21f2cc2405dd6370037062d5682b2a6f99b4cc5465a950c6d1f5ae8da3df4227
    46 rdf:type schema:PropertyValue
    47 N21f8ca0cdc434beabed9195f70e8bb9c schema:location Berlin, Heidelberg
    48 schema:name Springer Berlin Heidelberg
    49 rdf:type schema:Organisation
    50 N2266e2ffc6114a719d52f83d762c4eb3 schema:name doi
    51 schema:value 10.1007/978-3-540-69134-1_27
    52 rdf:type schema:PropertyValue
    53 N2c13f8c0d621441cbd7bc44fb99bab0d schema:familyName Asada
    54 schema:givenName Minoru
    55 rdf:type schema:Person
    56 N32f4e0c11be143b191e97df7f5d8bf1f schema:name dimensions_id
    57 schema:value pub.1007126851
    58 rdf:type schema:PropertyValue
    59 N536498e773e8414ab04354ea3a415df5 schema:familyName Hallam
    60 schema:givenName John C. T.
    61 rdf:type schema:Person
    62 N86a1d14380774fd98f9d391430f7be7d schema:name Artificial Intelligence Laboratory, Andreasstrasse 15, 8050 Zurich, Switzerland
    63 rdf:type schema:Organization
    64 N995b889935164c74b097d6dd53e55970 rdf:first sg:person.015501514105.63
    65 rdf:rest N9bc227e1d57d42369f4bd37cc1ee8936
    66 N9bc227e1d57d42369f4bd37cc1ee8936 rdf:first sg:person.013372311431.62
    67 rdf:rest rdf:nil
    68 Na3052d94868a457faeeefdaaf602a25d rdf:first N2c13f8c0d621441cbd7bc44fb99bab0d
    69 rdf:rest Nc7f3157cce894ffe9d24ad3b844890f5
    70 Naf5ddf163ceb49a689fe169b6661907a rdf:first Nce609d4a921f4f8e97c8dc49cd3765c4
    71 rdf:rest N131c2850e23f43f5a8fc1719870f35e6
    72 Nb571b34fc7e24cc8ac45ae0b8d5dff5d schema:familyName Tani
    73 schema:givenName Jun
    74 rdf:type schema:Person
    75 Nbda69fb4885a4d70b8597d8dddfeac6b rdf:first sg:person.015642422414.16
    76 rdf:rest N995b889935164c74b097d6dd53e55970
    77 Nc7f3157cce894ffe9d24ad3b844890f5 rdf:first N536498e773e8414ab04354ea3a415df5
    78 rdf:rest Naf5ddf163ceb49a689fe169b6661907a
    79 Nce609d4a921f4f8e97c8dc49cd3765c4 schema:familyName Meyer
    80 schema:givenName Jean-Arcady
    81 rdf:type schema:Person
    82 Ne41ed87fa3e2466d95db5fe703424341 schema:isbn 978-3-540-69133-4
    83 978-3-540-69134-1
    84 schema:name From Animals to Animats 10
    85 rdf:type schema:Book
    86 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    87 schema:name Information and Computing Sciences
    88 rdf:type schema:DefinedTerm
    89 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    90 schema:name Artificial Intelligence and Image Processing
    91 rdf:type schema:DefinedTerm
    92 sg:person.013372311431.62 schema:affiliation https://www.grid.ac/institutes/grid.26999.3d
    93 schema:familyName Kuniyoshi
    94 schema:givenName Yasuo
    95 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013372311431.62
    96 rdf:type schema:Person
    97 sg:person.015501514105.63 schema:affiliation N86a1d14380774fd98f9d391430f7be7d
    98 schema:familyName Lungarella
    99 schema:givenName Max
    100 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015501514105.63
    101 rdf:type schema:Person
    102 sg:person.015642422414.16 schema:affiliation https://www.grid.ac/institutes/grid.26999.3d
    103 schema:familyName Burfoot
    104 schema:givenName Daniel
    105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015642422414.16
    106 rdf:type schema:Person
    107 sg:pub.10.1007/978-3-540-27833-7_17 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022711395
    108 https://doi.org/10.1007/978-3-540-27833-7_17
    109 rdf:type schema:CreativeWork
    110 https://doi.org/10.1006/csla.1996.0011 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029750983
    111 rdf:type schema:CreativeWork
    112 https://doi.org/10.1016/0004-3702(91)90053-m schema:sameAs https://app.dimensions.ai/details/publication/pub.1041894242
    113 rdf:type schema:CreativeWork
    114 https://doi.org/10.1016/0005-1098(78)90005-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018373874
    115 rdf:type schema:CreativeWork
    116 https://doi.org/10.1016/j.ics.2005.12.080 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003429936
    117 rdf:type schema:CreativeWork
    118 https://doi.org/10.1016/s0079-6123(07)64023-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036754672
    119 rdf:type schema:CreativeWork
    120 https://doi.org/10.1016/s0893-6080(99)00060-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1043895272
    121 rdf:type schema:CreativeWork
    122 https://doi.org/10.1016/s0921-8890(05)80025-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001522338
    123 rdf:type schema:CreativeWork
    124 https://doi.org/10.1098/rstb.1992.0106 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007614297
    125 rdf:type schema:CreativeWork
    126 https://doi.org/10.1109/devlrn.2005.1490938 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095226549
    127 rdf:type schema:CreativeWork
    128 https://doi.org/10.1109/tnn.1998.712192 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061716400
    129 rdf:type schema:CreativeWork
    130 https://doi.org/10.1126/science.1145803 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053745766
    131 rdf:type schema:CreativeWork
    132 https://doi.org/10.1162/neco.2006.18.7.1527 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004707137
    133 rdf:type schema:CreativeWork
    134 https://www.grid.ac/institutes/grid.26999.3d schema:alternateName University of Tokyo
    135 schema:name The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan
    136 rdf:type schema:Organization
     




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


    ...