Resonant spatiotemporal learning in large random recurrent networks View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2002-09

AUTHORS

Emmanuel Daucé, Mathias Quoy, Bernard Doyon

ABSTRACT

Taking a global analogy with the structure of perceptual biological systems, we present a system composed of two layers of real-valued sigmoidal neurons. The primary layer receives stimulating spatiotemporal signals, and the secondary layer is a fully connected random recurrent network. This secondary layer spontaneously displays complex chaotic dynamics. All connections have a constant time delay. We use for our experiments a Hebbian (covariance) learning rule. This rule slowly modifies the weights under the influence of a periodic stimulus. The effect of learning is twofold: (i) it simplifies the secondary-layer dynamics, which eventually stabilizes to a periodic orbit; and (ii) it connects the secondary layer to the primary layer, and realizes a feedback from the secondary to the primary layer. This feedback signal is added to the incoming signal, and matches it (i.e., the secondary layer performs a one-step prediction of the forthcoming stimulus). After learning, a resonant behavior can be observed: the system resonates with familiar stimuli, which activates a feedback signal. In particular, this resonance allows the recognition and retrieval of partial signals, and dynamic maintenance of the memory of past stimuli. This resonance is highly sensitive to the temporal relationships and to the periodicity of the presented stimuli. When we present stimuli which do not match in time or space, the feedback remains silent. The number of different stimuli for which resonant behavior can be learned is analyzed. As with Hopfield networks, the capacity is proportional to the size of the second, recurrent layer. Moreover, the high capacity displayed allows the implementation of our model on real-time systems interacting with their environment. Such an implementation is reported in the case of a simple behavior-based recognition task on a mobile robot. Finally, we present some functional analogies with biological systems in terms of autonomy and dynamic binding, and present some hypotheses on the computational role of feedback connections. More... »

PAGES

185-198

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00422-002-0315-4

DOI

http://dx.doi.org/10.1007/s00422-002-0315-4

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1019555197

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/12200614


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"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Brain", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Conditioning (Psychology)", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Feedback, Physiological", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Motor Neurons", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Neural Networks (Computer)", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Neurons, Afferent", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Perception", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Psychomotor Performance", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Recognition (Psychology)", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Robotics", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Aix-Marseille University", 
          "id": "https://www.grid.ac/institutes/grid.5399.6", 
          "name": [
            "Movement and Perception (UMR6559), Faculty of Sport Science, University of the Mediterranean, 163, avenue de Luminy, CP 910, 13288 Marseille cedex 9, France, FR"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Dauc\u00e9", 
        "givenName": "Emmanuel", 
        "id": "sg:person.0644732057.19", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0644732057.19"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Information Processing and System Research Lab", 
          "id": "https://www.grid.ac/institutes/grid.463844.9", 
          "name": [
            "Neurocybernetics team, ETIS, UCP-ENSEA, 6, avenue du Ponceau, 95014 Cergy-Pontoise cedex, France, FR"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Quoy", 
        "givenName": "Mathias", 
        "id": "sg:person.010556353111.37", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010556353111.37"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Unit\u00e9 INSERM U455, Service de Neurologie-CHU Purpan, 31059 Toulouse cedex, France, FR"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Doyon", 
        "givenName": "Bernard", 
        "id": "sg:person.01264237031.67", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01264237031.67"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2002-09", 
    "datePublishedReg": "2002-09-01", 
    "description": "Taking a global analogy with the structure of perceptual biological systems, we present a system composed of two layers of real-valued sigmoidal neurons. The primary layer receives stimulating spatiotemporal signals, and the secondary layer is a fully connected random recurrent network. This secondary layer spontaneously displays complex chaotic dynamics. All connections have a constant time delay. We use for our experiments a Hebbian (covariance) learning rule. This rule slowly modifies the weights under the influence of a periodic stimulus. The effect of learning is twofold: (i) it simplifies the secondary-layer dynamics, which eventually stabilizes to a periodic orbit; and (ii) it connects the secondary layer to the primary layer, and realizes a feedback from the secondary to the primary layer. This feedback signal is added to the incoming signal, and matches it (i.e., the secondary layer performs a one-step prediction of the forthcoming stimulus). After learning, a resonant behavior can be observed: the system resonates with familiar stimuli, which activates a feedback signal. In particular, this resonance allows the recognition and retrieval of partial signals, and dynamic maintenance of the memory of past stimuli. This resonance is highly sensitive to the temporal relationships and to the periodicity of the presented stimuli. When we present stimuli which do not match in time or space, the feedback remains silent. The number of different stimuli for which resonant behavior can be learned is analyzed. As with Hopfield networks, the capacity is proportional to the size of the second, recurrent layer. Moreover, the high capacity displayed allows the implementation of our model on real-time systems interacting with their environment. Such an implementation is reported in the case of a simple behavior-based recognition task on a mobile robot. Finally, we present some functional analogies with biological systems in terms of autonomy and dynamic binding, and present some hypotheses on the computational role of feedback connections.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s00422-002-0315-4", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1081741", 
        "issn": [
          "0340-1200", 
          "1432-0770"
        ], 
        "name": "Biological Cybernetics", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "3", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "87"
      }
    ], 
    "name": "Resonant spatiotemporal learning in large random recurrent networks", 
    "pagination": "185-198", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "5d2c79e9d421580ae126b86cf80d820816283efca39265f84c5a7f03cbc6ecc6"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "12200614"
        ]
      }, 
      {
        "name": "nlm_unique_id", 
        "type": "PropertyValue", 
        "value": [
          "7502533"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00422-002-0315-4"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1019555197"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00422-002-0315-4", 
      "https://app.dimensions.ai/details/publication/pub.1019555197"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T01:00", 
    "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_8697_00000481.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1007/s00422-002-0315-4"
  }
]
 

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/s00422-002-0315-4'

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/s00422-002-0315-4'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00422-002-0315-4'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00422-002-0315-4'


 

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

128 TRIPLES      20 PREDICATES      39 URIs      31 LITERALS      19 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00422-002-0315-4 schema:about N0820eb75c5db43419d38a217ae296252
2 N140e831551ba484793d192477f731312
3 N18b876d367ae44b6ba1e37528233974e
4 N1ca4f1b4a8034e5f9a34a5cf37837d14
5 N48b1e480422d4b5e81493662c381d423
6 N6c4b1ee0d46543e0993246500805f198
7 Nb31395a3dab74d54958d01f5e800b526
8 Nbb0ce3b7b66347608ab88bfa8e419ef4
9 Nc981a41c051e4b738262b11a5b5a93bc
10 Nd38c921073b040cc96e591e1eb56f3ab
11 anzsrc-for:08
12 anzsrc-for:0801
13 schema:author Nfc5b3425334849bca0c9b4d4b4711553
14 schema:datePublished 2002-09
15 schema:datePublishedReg 2002-09-01
16 schema:description Taking a global analogy with the structure of perceptual biological systems, we present a system composed of two layers of real-valued sigmoidal neurons. The primary layer receives stimulating spatiotemporal signals, and the secondary layer is a fully connected random recurrent network. This secondary layer spontaneously displays complex chaotic dynamics. All connections have a constant time delay. We use for our experiments a Hebbian (covariance) learning rule. This rule slowly modifies the weights under the influence of a periodic stimulus. The effect of learning is twofold: (i) it simplifies the secondary-layer dynamics, which eventually stabilizes to a periodic orbit; and (ii) it connects the secondary layer to the primary layer, and realizes a feedback from the secondary to the primary layer. This feedback signal is added to the incoming signal, and matches it (i.e., the secondary layer performs a one-step prediction of the forthcoming stimulus). After learning, a resonant behavior can be observed: the system resonates with familiar stimuli, which activates a feedback signal. In particular, this resonance allows the recognition and retrieval of partial signals, and dynamic maintenance of the memory of past stimuli. This resonance is highly sensitive to the temporal relationships and to the periodicity of the presented stimuli. When we present stimuli which do not match in time or space, the feedback remains silent. The number of different stimuli for which resonant behavior can be learned is analyzed. As with Hopfield networks, the capacity is proportional to the size of the second, recurrent layer. Moreover, the high capacity displayed allows the implementation of our model on real-time systems interacting with their environment. Such an implementation is reported in the case of a simple behavior-based recognition task on a mobile robot. Finally, we present some functional analogies with biological systems in terms of autonomy and dynamic binding, and present some hypotheses on the computational role of feedback connections.
17 schema:genre research_article
18 schema:inLanguage en
19 schema:isAccessibleForFree false
20 schema:isPartOf N9d80c84442524b6faadbe26a24dd8d52
21 Nb5297e7534bd449fb9bccb23937a1035
22 sg:journal.1081741
23 schema:name Resonant spatiotemporal learning in large random recurrent networks
24 schema:pagination 185-198
25 schema:productId N8553d3171c3e40ba92d876635715b86f
26 N8735398b01ba49f09ec415693360791c
27 N879db04f39c84516b69c7d70bd917309
28 Ne2fb3c8df10e481fa7f2bfe2187e189d
29 Nec3a23903a1b4bca82cd2bf0b04b1400
30 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019555197
31 https://doi.org/10.1007/s00422-002-0315-4
32 schema:sdDatePublished 2019-04-11T01:00
33 schema:sdLicense https://scigraph.springernature.com/explorer/license/
34 schema:sdPublisher N35f24c75b4454ec7a252cac0a6b8c81c
35 schema:url http://link.springer.com/10.1007/s00422-002-0315-4
36 sgo:license sg:explorer/license/
37 sgo:sdDataset articles
38 rdf:type schema:ScholarlyArticle
39 N0820eb75c5db43419d38a217ae296252 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
40 schema:name Recognition (Psychology)
41 rdf:type schema:DefinedTerm
42 N140e831551ba484793d192477f731312 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
43 schema:name Neurons, Afferent
44 rdf:type schema:DefinedTerm
45 N18b876d367ae44b6ba1e37528233974e schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
46 schema:name Neural Networks (Computer)
47 rdf:type schema:DefinedTerm
48 N1ca4f1b4a8034e5f9a34a5cf37837d14 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
49 schema:name Robotics
50 rdf:type schema:DefinedTerm
51 N35f24c75b4454ec7a252cac0a6b8c81c schema:name Springer Nature - SN SciGraph project
52 rdf:type schema:Organization
53 N48b1e480422d4b5e81493662c381d423 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
54 schema:name Conditioning (Psychology)
55 rdf:type schema:DefinedTerm
56 N6c4b1ee0d46543e0993246500805f198 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
57 schema:name Motor Neurons
58 rdf:type schema:DefinedTerm
59 N8553d3171c3e40ba92d876635715b86f schema:name doi
60 schema:value 10.1007/s00422-002-0315-4
61 rdf:type schema:PropertyValue
62 N8735398b01ba49f09ec415693360791c schema:name dimensions_id
63 schema:value pub.1019555197
64 rdf:type schema:PropertyValue
65 N879db04f39c84516b69c7d70bd917309 schema:name pubmed_id
66 schema:value 12200614
67 rdf:type schema:PropertyValue
68 N9d80c84442524b6faadbe26a24dd8d52 schema:issueNumber 3
69 rdf:type schema:PublicationIssue
70 Nb31395a3dab74d54958d01f5e800b526 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
71 schema:name Psychomotor Performance
72 rdf:type schema:DefinedTerm
73 Nb5297e7534bd449fb9bccb23937a1035 schema:volumeNumber 87
74 rdf:type schema:PublicationVolume
75 Nbb0ce3b7b66347608ab88bfa8e419ef4 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
76 schema:name Feedback, Physiological
77 rdf:type schema:DefinedTerm
78 Nbdeb87d08a424fde9478c641454f325d rdf:first sg:person.010556353111.37
79 rdf:rest Ned770481571f40428d2e88f07d5093e9
80 Nc981a41c051e4b738262b11a5b5a93bc schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
81 schema:name Brain
82 rdf:type schema:DefinedTerm
83 Nd38c921073b040cc96e591e1eb56f3ab schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
84 schema:name Perception
85 rdf:type schema:DefinedTerm
86 Ne2fb3c8df10e481fa7f2bfe2187e189d schema:name nlm_unique_id
87 schema:value 7502533
88 rdf:type schema:PropertyValue
89 Nec3a23903a1b4bca82cd2bf0b04b1400 schema:name readcube_id
90 schema:value 5d2c79e9d421580ae126b86cf80d820816283efca39265f84c5a7f03cbc6ecc6
91 rdf:type schema:PropertyValue
92 Ned770481571f40428d2e88f07d5093e9 rdf:first sg:person.01264237031.67
93 rdf:rest rdf:nil
94 Nf32603212d0e445c8f893793cae9c130 schema:name Unité INSERM U455, Service de Neurologie-CHU Purpan, 31059 Toulouse cedex, France, FR
95 rdf:type schema:Organization
96 Nfc5b3425334849bca0c9b4d4b4711553 rdf:first sg:person.0644732057.19
97 rdf:rest Nbdeb87d08a424fde9478c641454f325d
98 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
99 schema:name Information and Computing Sciences
100 rdf:type schema:DefinedTerm
101 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
102 schema:name Artificial Intelligence and Image Processing
103 rdf:type schema:DefinedTerm
104 sg:journal.1081741 schema:issn 0340-1200
105 1432-0770
106 schema:name Biological Cybernetics
107 rdf:type schema:Periodical
108 sg:person.010556353111.37 schema:affiliation https://www.grid.ac/institutes/grid.463844.9
109 schema:familyName Quoy
110 schema:givenName Mathias
111 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010556353111.37
112 rdf:type schema:Person
113 sg:person.01264237031.67 schema:affiliation Nf32603212d0e445c8f893793cae9c130
114 schema:familyName Doyon
115 schema:givenName Bernard
116 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01264237031.67
117 rdf:type schema:Person
118 sg:person.0644732057.19 schema:affiliation https://www.grid.ac/institutes/grid.5399.6
119 schema:familyName Daucé
120 schema:givenName Emmanuel
121 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0644732057.19
122 rdf:type schema:Person
123 https://www.grid.ac/institutes/grid.463844.9 schema:alternateName Information Processing and System Research Lab
124 schema:name Neurocybernetics team, ETIS, UCP-ENSEA, 6, avenue du Ponceau, 95014 Cergy-Pontoise cedex, France, FR
125 rdf:type schema:Organization
126 https://www.grid.ac/institutes/grid.5399.6 schema:alternateName Aix-Marseille University
127 schema:name Movement and Perception (UMR6559), Faculty of Sport Science, University of the Mediterranean, 163, avenue de Luminy, CP 910, 13288 Marseille cedex 9, France, FR
128 rdf:type schema:Organization
 




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


...