The Role of Internal Oscillators for the One-Shot Learning of Complex Temporal Sequences View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2007

AUTHORS

Matthieu Lagarde , Pierre Andry , Philippe Gaussier

ABSTRACT

We present an artificial neural network used to learn online complex temporal sequences of gestures to a robot. The system is based on a simple temporal sequences learning architecture, neurobiological inspired model using some of the properties of the cerebellum and the hippocampus, plus a diversity generator composed of CTRNN oscillators. The use of oscillators allows to remove the ambiguity of complex sequences. The associations with oscillators allow to build an internal state to disambiguate the observable state. To understand the effect of this learning mechanism, we compare the performance of (i) our model with (ii) simple sequence learning model and with (iii) the simple sequence learning model plus a competitive mechanism between inputs and oscillators. Finally, we present an experiment showing a AIBO robot, which learns and reproduces a sequence of gestures. More... »

PAGES

934-943

References to SciGraph publications

Book

TITLE

Artificial Neural Networks – ICANN 2007

ISBN

978-3-540-74689-8
978-3-540-74690-4

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-540-74690-4_95

DOI

http://dx.doi.org/10.1007/978-3-540-74690-4_95

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1009776103


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": "Information Processing and System Research Lab", 
          "id": "https://www.grid.ac/institutes/grid.463844.9", 
          "name": [
            "ETIS, Neurocybernetic Team, UMR CNRS 8051, 2, avenue Adolphe-Chauvin, University of Cergy-Pontoise, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lagarde", 
        "givenName": "Matthieu", 
        "id": "sg:person.014114521627.31", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014114521627.31"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Information Processing and System Research Lab", 
          "id": "https://www.grid.ac/institutes/grid.463844.9", 
          "name": [
            "ETIS, Neurocybernetic Team, UMR CNRS 8051, 2, avenue Adolphe-Chauvin, University of Cergy-Pontoise, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Andry", 
        "givenName": "Pierre", 
        "id": "sg:person.012152621257.16", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012152621257.16"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Information Processing and System Research Lab", 
          "id": "https://www.grid.ac/institutes/grid.463844.9", 
          "name": [
            "ETIS, Neurocybernetic Team, UMR CNRS 8051, 2, avenue Adolphe-Chauvin, University of Cergy-Pontoise, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Gaussier", 
        "givenName": "Philippe", 
        "id": "sg:person.01041272554.05", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01041272554.05"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1017/cbo9780511489808.012", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1001044091"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/105971230401200203", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004786902"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/105971230401200203", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004786902"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/088395198117596", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009321480"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00422-002-0364-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026775886", 
          "https://doi.org/10.1007/s00422-002-0364-8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1037/0033-295x.95.1.49", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1029502400"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/105971239400200301", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051690783"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/105971239400200301", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051690783"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(94)90092-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052031775"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(94)90092-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052031775"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/ijcnn.2005.1555949", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094521781"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2007", 
    "datePublishedReg": "2007-01-01", 
    "description": "We present an artificial neural network used to learn online complex temporal sequences of gestures to a robot. The system is based on a simple temporal sequences learning architecture, neurobiological inspired model using some of the properties of the cerebellum and the hippocampus, plus a diversity generator composed of CTRNN oscillators. The use of oscillators allows to remove the ambiguity of complex sequences. The associations with oscillators allow to build an internal state to disambiguate the observable state. To understand the effect of this learning mechanism, we compare the performance of (i) our model with (ii) simple sequence learning model and with (iii) the simple sequence learning model plus a competitive mechanism between inputs and oscillators. Finally, we present an experiment showing a AIBO robot, which learns and reproduces a sequence of gestures.", 
    "editor": [
      {
        "familyName": "de S\u00e1", 
        "givenName": "Joaquim Marques", 
        "type": "Person"
      }, 
      {
        "familyName": "Alexandre", 
        "givenName": "Lu\u00eds A.", 
        "type": "Person"
      }, 
      {
        "familyName": "Duch", 
        "givenName": "W\u0142odzis\u0142aw", 
        "type": "Person"
      }, 
      {
        "familyName": "Mandic", 
        "givenName": "Danilo", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-540-74690-4_95", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-74689-8", 
        "978-3-540-74690-4"
      ], 
      "name": "Artificial Neural Networks \u2013 ICANN 2007", 
      "type": "Book"
    }, 
    "name": "The Role of Internal Oscillators for the One-Shot Learning of Complex Temporal Sequences", 
    "pagination": "934-943", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-540-74690-4_95"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "2e92a287071c1c7ed6d05eb72b17d54c35a8dbdabbd00cdb30638348bfe89b22"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1009776103"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-540-74690-4_95", 
      "https://app.dimensions.ai/details/publication/pub.1009776103"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T05:33", 
    "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/v90/0000000346_0000000346/records_99818_00000000.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F978-3-540-74690-4_95"
  }
]
 

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.10.1007/978-3-540-74690-4_95'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74690-4_95'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74690-4_95'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-74690-4_95'


 

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

119 TRIPLES      23 PREDICATES      35 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-540-74690-4_95 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Ne7ab5a22ac764c7fb19da44205afdb86
4 schema:citation sg:pub.10.1007/s00422-002-0364-8
5 https://doi.org/10.1016/0893-6080(94)90092-2
6 https://doi.org/10.1017/cbo9780511489808.012
7 https://doi.org/10.1037/0033-295x.95.1.49
8 https://doi.org/10.1080/088395198117596
9 https://doi.org/10.1109/ijcnn.2005.1555949
10 https://doi.org/10.1177/105971230401200203
11 https://doi.org/10.1177/105971239400200301
12 schema:datePublished 2007
13 schema:datePublishedReg 2007-01-01
14 schema:description We present an artificial neural network used to learn online complex temporal sequences of gestures to a robot. The system is based on a simple temporal sequences learning architecture, neurobiological inspired model using some of the properties of the cerebellum and the hippocampus, plus a diversity generator composed of CTRNN oscillators. The use of oscillators allows to remove the ambiguity of complex sequences. The associations with oscillators allow to build an internal state to disambiguate the observable state. To understand the effect of this learning mechanism, we compare the performance of (i) our model with (ii) simple sequence learning model and with (iii) the simple sequence learning model plus a competitive mechanism between inputs and oscillators. Finally, we present an experiment showing a AIBO robot, which learns and reproduces a sequence of gestures.
15 schema:editor N1ea8cc7a24594c3da3560cab011b32cc
16 schema:genre chapter
17 schema:inLanguage en
18 schema:isAccessibleForFree false
19 schema:isPartOf Nfeb760c0cf374878a0754af97c5eda49
20 schema:name The Role of Internal Oscillators for the One-Shot Learning of Complex Temporal Sequences
21 schema:pagination 934-943
22 schema:productId N77f180fdd74f420d8e8b2653229d42d1
23 Nbc33805c51fa4e01be337d079460a68a
24 Neafb90228d7042a39d7a350f5e76831b
25 schema:publisher N7e37646ce33646eb8b46401c1d228ad4
26 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009776103
27 https://doi.org/10.1007/978-3-540-74690-4_95
28 schema:sdDatePublished 2019-04-16T05:33
29 schema:sdLicense https://scigraph.springernature.com/explorer/license/
30 schema:sdPublisher Nd377089f910a4d6cb1e1a7df16bd8268
31 schema:url https://link.springer.com/10.1007%2F978-3-540-74690-4_95
32 sgo:license sg:explorer/license/
33 sgo:sdDataset chapters
34 rdf:type schema:Chapter
35 N066ef0f88a7343d986649e28a72191f8 rdf:first sg:person.01041272554.05
36 rdf:rest rdf:nil
37 N102c33a4ed4548b9a2baefbda61a6f92 rdf:first sg:person.012152621257.16
38 rdf:rest N066ef0f88a7343d986649e28a72191f8
39 N1c8fb729ab004cfba3dffd3c344e1879 rdf:first Nebeb853402dd48f5b42a854b085c422b
40 rdf:rest Na963281ba1be4833803a6838f096aa54
41 N1ea8cc7a24594c3da3560cab011b32cc rdf:first N3295feb1cb76447d97c736404756a470
42 rdf:rest N1c8fb729ab004cfba3dffd3c344e1879
43 N3295feb1cb76447d97c736404756a470 schema:familyName de Sá
44 schema:givenName Joaquim Marques
45 rdf:type schema:Person
46 N6ff5163252f14e53889811f6b21531a5 rdf:first Nf0fa53eaedb94305be8579502e76cc78
47 rdf:rest rdf:nil
48 N77f180fdd74f420d8e8b2653229d42d1 schema:name doi
49 schema:value 10.1007/978-3-540-74690-4_95
50 rdf:type schema:PropertyValue
51 N7e37646ce33646eb8b46401c1d228ad4 schema:location Berlin, Heidelberg
52 schema:name Springer Berlin Heidelberg
53 rdf:type schema:Organisation
54 Na963281ba1be4833803a6838f096aa54 rdf:first Ne4ff33432fbb45c5a2eacbf1bbcc01c8
55 rdf:rest N6ff5163252f14e53889811f6b21531a5
56 Nbc33805c51fa4e01be337d079460a68a schema:name readcube_id
57 schema:value 2e92a287071c1c7ed6d05eb72b17d54c35a8dbdabbd00cdb30638348bfe89b22
58 rdf:type schema:PropertyValue
59 Nd377089f910a4d6cb1e1a7df16bd8268 schema:name Springer Nature - SN SciGraph project
60 rdf:type schema:Organization
61 Ne4ff33432fbb45c5a2eacbf1bbcc01c8 schema:familyName Duch
62 schema:givenName Włodzisław
63 rdf:type schema:Person
64 Ne7ab5a22ac764c7fb19da44205afdb86 rdf:first sg:person.014114521627.31
65 rdf:rest N102c33a4ed4548b9a2baefbda61a6f92
66 Neafb90228d7042a39d7a350f5e76831b schema:name dimensions_id
67 schema:value pub.1009776103
68 rdf:type schema:PropertyValue
69 Nebeb853402dd48f5b42a854b085c422b schema:familyName Alexandre
70 schema:givenName Luís A.
71 rdf:type schema:Person
72 Nf0fa53eaedb94305be8579502e76cc78 schema:familyName Mandic
73 schema:givenName Danilo
74 rdf:type schema:Person
75 Nfeb760c0cf374878a0754af97c5eda49 schema:isbn 978-3-540-74689-8
76 978-3-540-74690-4
77 schema:name Artificial Neural Networks – ICANN 2007
78 rdf:type schema:Book
79 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
80 schema:name Information and Computing Sciences
81 rdf:type schema:DefinedTerm
82 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
83 schema:name Artificial Intelligence and Image Processing
84 rdf:type schema:DefinedTerm
85 sg:person.01041272554.05 schema:affiliation https://www.grid.ac/institutes/grid.463844.9
86 schema:familyName Gaussier
87 schema:givenName Philippe
88 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01041272554.05
89 rdf:type schema:Person
90 sg:person.012152621257.16 schema:affiliation https://www.grid.ac/institutes/grid.463844.9
91 schema:familyName Andry
92 schema:givenName Pierre
93 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012152621257.16
94 rdf:type schema:Person
95 sg:person.014114521627.31 schema:affiliation https://www.grid.ac/institutes/grid.463844.9
96 schema:familyName Lagarde
97 schema:givenName Matthieu
98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014114521627.31
99 rdf:type schema:Person
100 sg:pub.10.1007/s00422-002-0364-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026775886
101 https://doi.org/10.1007/s00422-002-0364-8
102 rdf:type schema:CreativeWork
103 https://doi.org/10.1016/0893-6080(94)90092-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052031775
104 rdf:type schema:CreativeWork
105 https://doi.org/10.1017/cbo9780511489808.012 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001044091
106 rdf:type schema:CreativeWork
107 https://doi.org/10.1037/0033-295x.95.1.49 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029502400
108 rdf:type schema:CreativeWork
109 https://doi.org/10.1080/088395198117596 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009321480
110 rdf:type schema:CreativeWork
111 https://doi.org/10.1109/ijcnn.2005.1555949 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094521781
112 rdf:type schema:CreativeWork
113 https://doi.org/10.1177/105971230401200203 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004786902
114 rdf:type schema:CreativeWork
115 https://doi.org/10.1177/105971239400200301 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051690783
116 rdf:type schema:CreativeWork
117 https://www.grid.ac/institutes/grid.463844.9 schema:alternateName Information Processing and System Research Lab
118 schema:name ETIS, Neurocybernetic Team, UMR CNRS 8051, 2, avenue Adolphe-Chauvin, University of Cergy-Pontoise, France
119 rdf:type schema:Organization
 




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


...