Spontaneous Dynamics and Associative Learning in an Assymetric Recurrent Random Neural Network View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

1997

AUTHORS

M. Samuelides , B. Doyon , B. Cessac , M. Quoy

ABSTRACT

Freeman’s investigations on the olfactory bulb of the rabbit showed that its dynamics was chaotic, and that recognition of a learned pattern is linked to a dimension reduction of the dynamics on a much simpler attractor (near limit cycle). We adress here the question wether this behaviour is specific of this particular architecture or if this kind of behaviour observed is an important property of chaotic neural network using a Hebb- like learning rule. In this paper, we use a mean-field theoretical statement to determine the spontaneous dynamics of an assymetric recurrent neural network. In particular we determine the range of random weight matrix for which the network is chaotic. We are able to explain the various changes observed in the dynamical regime when sending static random patterns. We propose a Hebb-like learning rule to store a pattern as a limit cycle or strange attractor. We numerically show the dynamics reduction of a finite-size chaotic network during learning and recognition of a pattern. Though associative learning is actually performed the low storage capacity of the system leads to the consideration of more realistic architecture. More... »

PAGES

312-317

Book

TITLE

Mathematics of Neural Networks

ISBN

978-1-4613-7794-8
978-1-4615-6099-9

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-1-4615-6099-9_54

DOI

http://dx.doi.org/10.1007/978-1-4615-6099-9_54

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1009081313


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": [
            "Centre d\u2019Etudes et de Recherches de Toulouse, BP 4025, 2 avenue Edouard Belin, 31055, Toulouse Cedex, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Samuelides", 
        "givenName": "M.", 
        "id": "sg:person.01142047104.10", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01142047104.10"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Service de Neurologie, CHU Purpan, Unit\u00e9 INSERM 230, 31059, Toulouse C\u00e9dex, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Doyon", 
        "givenName": "B.", 
        "id": "sg:person.01264237031.67", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01264237031.67"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of New Mexico", 
          "id": "https://www.grid.ac/institutes/grid.266832.b", 
          "name": [
            "Department of Electrical and Computer Engineering, University of New-Mexico, 87131, Albuquerque, NM, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Cessac", 
        "givenName": "B.", 
        "id": "sg:person.01074735442.62", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01074735442.62"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Bielefeld University", 
          "id": "https://www.grid.ac/institutes/grid.7491.b", 
          "name": [
            "Universit\u00e4t Bielefeld, BiBos, Postfach 100131, 33501, Bielefeld, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Quoy", 
        "givenName": "M.", 
        "id": "sg:person.010556353111.37", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010556353111.37"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/0893-6080(90)90086-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000752823"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(90)90086-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000752823"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/338334a0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017767690", 
          "https://doi.org/10.1038/338334a0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-2789(94)90024-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027652688"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-2789(94)90024-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027652688"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1017/s0140525x00047336", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032543255"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1017/s0140525x00047336", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032543255"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1017/s0140525x00047336", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032543255"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00202899", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043727259", 
          "https://doi.org/10.1007/bf00202899"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00202899", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043727259", 
          "https://doi.org/10.1007/bf00202899"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0375-9601(85)90444-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047359424"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0375-9601(85)90444-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047359424"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(89)90018-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050194804"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(89)90018-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050194804"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1051/jp1:1995135", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1056974241"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1103/physrevlett.61.259", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1060797987"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1103/physrevlett.61.259", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1060797987"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsmc.1972.4309193", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061792650"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsmc.1972.4309193", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061792650"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1142/s0218127493000222", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062957885"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1997", 
    "datePublishedReg": "1997-01-01", 
    "description": "Freeman\u2019s investigations on the olfactory bulb of the rabbit showed that its dynamics was chaotic, and that recognition of a learned pattern is linked to a dimension reduction of the dynamics on a much simpler attractor (near limit cycle). We adress here the question wether this behaviour is specific of this particular architecture or if this kind of behaviour observed is an important property of chaotic neural network using a Hebb- like learning rule. In this paper, we use a mean-field theoretical statement to determine the spontaneous dynamics of an assymetric recurrent neural network. In particular we determine the range of random weight matrix for which the network is chaotic. We are able to explain the various changes observed in the dynamical regime when sending static random patterns. We propose a Hebb-like learning rule to store a pattern as a limit cycle or strange attractor. We numerically show the dynamics reduction of a finite-size chaotic network during learning and recognition of a pattern. Though associative learning is actually performed the low storage capacity of the system leads to the consideration of more realistic architecture.", 
    "editor": [
      {
        "familyName": "Ellacott", 
        "givenName": "Stephen W.", 
        "type": "Person"
      }, 
      {
        "familyName": "Mason", 
        "givenName": "John C.", 
        "type": "Person"
      }, 
      {
        "familyName": "Anderson", 
        "givenName": "Iain J.", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-1-4615-6099-9_54", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-1-4613-7794-8", 
        "978-1-4615-6099-9"
      ], 
      "name": "Mathematics of Neural Networks", 
      "type": "Book"
    }, 
    "name": "Spontaneous Dynamics and Associative Learning in an Assymetric Recurrent Random Neural Network", 
    "pagination": "312-317", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1009081313"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-1-4615-6099-9_54"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "2b43cae7f751f01f04ba0d1ca79a343d2968d8ff19edcf72d0c116438834e335"
        ]
      }
    ], 
    "publisher": {
      "location": "Boston, MA", 
      "name": "Springer US", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-1-4615-6099-9_54", 
      "https://app.dimensions.ai/details/publication/pub.1009081313"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T09:09", 
    "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/v90/0000000371_0000000371/records_130793_00000000.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F978-1-4615-6099-9_54"
  }
]
 

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.10.1007/978-1-4615-6099-9_54'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-1-4615-6099-9_54'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-1-4615-6099-9_54'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-1-4615-6099-9_54'


 

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

138 TRIPLES      23 PREDICATES      38 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-1-4615-6099-9_54 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N821d48f68a314bc0a79854a3e2bbfb58
4 schema:citation sg:pub.10.1007/bf00202899
5 sg:pub.10.1038/338334a0
6 https://doi.org/10.1016/0167-2789(94)90024-8
7 https://doi.org/10.1016/0375-9601(85)90444-x
8 https://doi.org/10.1016/0893-6080(89)90018-x
9 https://doi.org/10.1016/0893-6080(90)90086-z
10 https://doi.org/10.1017/s0140525x00047336
11 https://doi.org/10.1051/jp1:1995135
12 https://doi.org/10.1103/physrevlett.61.259
13 https://doi.org/10.1109/tsmc.1972.4309193
14 https://doi.org/10.1142/s0218127493000222
15 schema:datePublished 1997
16 schema:datePublishedReg 1997-01-01
17 schema:description Freeman’s investigations on the olfactory bulb of the rabbit showed that its dynamics was chaotic, and that recognition of a learned pattern is linked to a dimension reduction of the dynamics on a much simpler attractor (near limit cycle). We adress here the question wether this behaviour is specific of this particular architecture or if this kind of behaviour observed is an important property of chaotic neural network using a Hebb- like learning rule. In this paper, we use a mean-field theoretical statement to determine the spontaneous dynamics of an assymetric recurrent neural network. In particular we determine the range of random weight matrix for which the network is chaotic. We are able to explain the various changes observed in the dynamical regime when sending static random patterns. We propose a Hebb-like learning rule to store a pattern as a limit cycle or strange attractor. We numerically show the dynamics reduction of a finite-size chaotic network during learning and recognition of a pattern. Though associative learning is actually performed the low storage capacity of the system leads to the consideration of more realistic architecture.
18 schema:editor N306d44b9bbdc4c4f944f7336868b5b3d
19 schema:genre chapter
20 schema:inLanguage en
21 schema:isAccessibleForFree false
22 schema:isPartOf N1cba992334774531b2807c465bae6c4f
23 schema:name Spontaneous Dynamics and Associative Learning in an Assymetric Recurrent Random Neural Network
24 schema:pagination 312-317
25 schema:productId N949d819f036a412f9e3679ab18e8264b
26 Nce6d7a3f7cf74ce596963d3ffd312c3c
27 Ne8dd6da2f69f4208b5734eca831e647a
28 schema:publisher N42e7096c71004895a7fd8db161315f92
29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009081313
30 https://doi.org/10.1007/978-1-4615-6099-9_54
31 schema:sdDatePublished 2019-04-16T09:09
32 schema:sdLicense https://scigraph.springernature.com/explorer/license/
33 schema:sdPublisher Ncb71da87c46349ddb620027828d4d2c8
34 schema:url https://link.springer.com/10.1007%2F978-1-4615-6099-9_54
35 sgo:license sg:explorer/license/
36 sgo:sdDataset chapters
37 rdf:type schema:Chapter
38 N083f4b38ffce46af9c6067b8220d562f rdf:first sg:person.01264237031.67
39 rdf:rest Nd800957ae32641a0978cc798998a25dc
40 N1cba992334774531b2807c465bae6c4f schema:isbn 978-1-4613-7794-8
41 978-1-4615-6099-9
42 schema:name Mathematics of Neural Networks
43 rdf:type schema:Book
44 N306d44b9bbdc4c4f944f7336868b5b3d rdf:first N5d3c60cf048846ce80058b85e12c6f6b
45 rdf:rest Nf302d92d52044fb1833e1295085ced6b
46 N42e7096c71004895a7fd8db161315f92 schema:location Boston, MA
47 schema:name Springer US
48 rdf:type schema:Organisation
49 N484d35014b6c490c828e01e93375d4ed rdf:first sg:person.010556353111.37
50 rdf:rest rdf:nil
51 N5d3c60cf048846ce80058b85e12c6f6b schema:familyName Ellacott
52 schema:givenName Stephen W.
53 rdf:type schema:Person
54 N60f0a4ade39544c1b473f5e58e2d264a schema:name Centre d’Etudes et de Recherches de Toulouse, BP 4025, 2 avenue Edouard Belin, 31055, Toulouse Cedex, France
55 rdf:type schema:Organization
56 N61229906fd5049189bbeabf5983d6ba1 schema:familyName Mason
57 schema:givenName John C.
58 rdf:type schema:Person
59 N740197cecc8d4160acfc61c18bfff265 schema:name Service de Neurologie, CHU Purpan, Unité INSERM 230, 31059, Toulouse Cédex, France
60 rdf:type schema:Organization
61 N821d48f68a314bc0a79854a3e2bbfb58 rdf:first sg:person.01142047104.10
62 rdf:rest N083f4b38ffce46af9c6067b8220d562f
63 N949d819f036a412f9e3679ab18e8264b schema:name doi
64 schema:value 10.1007/978-1-4615-6099-9_54
65 rdf:type schema:PropertyValue
66 Nb705218c2e8c468f9c54f319d8ce7d46 rdf:first Nb86d45f96a6140f6a895803699efb4f8
67 rdf:rest rdf:nil
68 Nb86d45f96a6140f6a895803699efb4f8 schema:familyName Anderson
69 schema:givenName Iain J.
70 rdf:type schema:Person
71 Ncb71da87c46349ddb620027828d4d2c8 schema:name Springer Nature - SN SciGraph project
72 rdf:type schema:Organization
73 Nce6d7a3f7cf74ce596963d3ffd312c3c schema:name readcube_id
74 schema:value 2b43cae7f751f01f04ba0d1ca79a343d2968d8ff19edcf72d0c116438834e335
75 rdf:type schema:PropertyValue
76 Nd800957ae32641a0978cc798998a25dc rdf:first sg:person.01074735442.62
77 rdf:rest N484d35014b6c490c828e01e93375d4ed
78 Ne8dd6da2f69f4208b5734eca831e647a schema:name dimensions_id
79 schema:value pub.1009081313
80 rdf:type schema:PropertyValue
81 Nf302d92d52044fb1833e1295085ced6b rdf:first N61229906fd5049189bbeabf5983d6ba1
82 rdf:rest Nb705218c2e8c468f9c54f319d8ce7d46
83 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
84 schema:name Information and Computing Sciences
85 rdf:type schema:DefinedTerm
86 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
87 schema:name Artificial Intelligence and Image Processing
88 rdf:type schema:DefinedTerm
89 sg:person.010556353111.37 schema:affiliation https://www.grid.ac/institutes/grid.7491.b
90 schema:familyName Quoy
91 schema:givenName M.
92 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010556353111.37
93 rdf:type schema:Person
94 sg:person.01074735442.62 schema:affiliation https://www.grid.ac/institutes/grid.266832.b
95 schema:familyName Cessac
96 schema:givenName B.
97 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01074735442.62
98 rdf:type schema:Person
99 sg:person.01142047104.10 schema:affiliation N60f0a4ade39544c1b473f5e58e2d264a
100 schema:familyName Samuelides
101 schema:givenName M.
102 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01142047104.10
103 rdf:type schema:Person
104 sg:person.01264237031.67 schema:affiliation N740197cecc8d4160acfc61c18bfff265
105 schema:familyName Doyon
106 schema:givenName B.
107 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01264237031.67
108 rdf:type schema:Person
109 sg:pub.10.1007/bf00202899 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043727259
110 https://doi.org/10.1007/bf00202899
111 rdf:type schema:CreativeWork
112 sg:pub.10.1038/338334a0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017767690
113 https://doi.org/10.1038/338334a0
114 rdf:type schema:CreativeWork
115 https://doi.org/10.1016/0167-2789(94)90024-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027652688
116 rdf:type schema:CreativeWork
117 https://doi.org/10.1016/0375-9601(85)90444-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1047359424
118 rdf:type schema:CreativeWork
119 https://doi.org/10.1016/0893-6080(89)90018-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1050194804
120 rdf:type schema:CreativeWork
121 https://doi.org/10.1016/0893-6080(90)90086-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1000752823
122 rdf:type schema:CreativeWork
123 https://doi.org/10.1017/s0140525x00047336 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032543255
124 rdf:type schema:CreativeWork
125 https://doi.org/10.1051/jp1:1995135 schema:sameAs https://app.dimensions.ai/details/publication/pub.1056974241
126 rdf:type schema:CreativeWork
127 https://doi.org/10.1103/physrevlett.61.259 schema:sameAs https://app.dimensions.ai/details/publication/pub.1060797987
128 rdf:type schema:CreativeWork
129 https://doi.org/10.1109/tsmc.1972.4309193 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061792650
130 rdf:type schema:CreativeWork
131 https://doi.org/10.1142/s0218127493000222 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062957885
132 rdf:type schema:CreativeWork
133 https://www.grid.ac/institutes/grid.266832.b schema:alternateName University of New Mexico
134 schema:name Department of Electrical and Computer Engineering, University of New-Mexico, 87131, Albuquerque, NM, USA
135 rdf:type schema:Organization
136 https://www.grid.ac/institutes/grid.7491.b schema:alternateName Bielefeld University
137 schema:name Universität Bielefeld, BiBos, Postfach 100131, 33501, Bielefeld, Germany
138 rdf:type schema:Organization
 




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


...