Self-organizing neural network that discovers surfaces in random-dot stereograms View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

1992-01

AUTHORS

S Becker, G E Hinton

ABSTRACT

The standard form of back-propagation learning is implausible as a model of perceptual learning because it requires an external teacher to specify the desired output of the network. We show how the external teacher can be replaced by internally derived teaching signals. These signals are generated by using the assumption that different parts of the perceptual input have common causes in the external world. Small modules that look at separate but related parts of the perceptual input discover these common causes by striving to produce outputs that agree with each other. The modules may look at different modalities (such as vision and touch), or the same modality at different times (for example, the consecutive two-dimensional views of a rotating three-dimensional object), or even spatially adjacent parts of the same image. Our simulations show that when our learning procedure is applied to adjacent patches of two-dimensional images, it allows a neural network that has no prior knowledge of the third dimension to discovery depth in random dot stereograms of curved surfaces. More... »

PAGES

161-163

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1038/355161a0

DOI

http://dx.doi.org/10.1038/355161a0

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1051732355

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/1729650


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": "Artificial Intelligence", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Mathematics", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Neural Networks (Computer)", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Toronto", 
          "id": "https://www.grid.ac/institutes/grid.17063.33", 
          "name": [
            "Department of Computer Science, University of Toronto, Canada."
          ], 
          "type": "Organization"
        }, 
        "familyName": "Becker", 
        "givenName": "S", 
        "id": "sg:person.0713333536.07", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0713333536.07"
        ], 
        "type": "Person"
      }, 
      {
        "familyName": "Hinton", 
        "givenName": "G E", 
        "id": "sg:person.0615147542.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0615147542.17"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1038/323533a0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018367015", 
          "https://doi.org/10.1038/323533a0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1214/ss/1177013604", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052575245"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1523/jneurosci.10-07-02281.1990", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1078743873"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1992-01", 
    "datePublishedReg": "1992-01-01", 
    "description": "The standard form of back-propagation learning is implausible as a model of perceptual learning because it requires an external teacher to specify the desired output of the network. We show how the external teacher can be replaced by internally derived teaching signals. These signals are generated by using the assumption that different parts of the perceptual input have common causes in the external world. Small modules that look at separate but related parts of the perceptual input discover these common causes by striving to produce outputs that agree with each other. The modules may look at different modalities (such as vision and touch), or the same modality at different times (for example, the consecutive two-dimensional views of a rotating three-dimensional object), or even spatially adjacent parts of the same image. Our simulations show that when our learning procedure is applied to adjacent patches of two-dimensional images, it allows a neural network that has no prior knowledge of the third dimension to discovery depth in random dot stereograms of curved surfaces.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1038/355161a0", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1018957", 
        "issn": [
          "0090-0028", 
          "1476-4687"
        ], 
        "name": "Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "6356", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "355"
      }
    ], 
    "name": "Self-organizing neural network that discovers surfaces in random-dot stereograms", 
    "pagination": "161-163", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "f66d164b6b3fe1acaad1b2a07fb48342630fc4b59fdacedccf2f9f3b6ba5389c"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "1729650"
        ]
      }, 
      {
        "name": "nlm_unique_id", 
        "type": "PropertyValue", 
        "value": [
          "0410462"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1038/355161a0"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1051732355"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1038/355161a0", 
      "https://app.dimensions.ai/details/publication/pub.1051732355"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-10T16:29", 
    "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_8669_00000426.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://www.nature.com/articles/355161a0"
  }
]
 

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.10.1038/355161a0'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1038/355161a0'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1038/355161a0'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1038/355161a0'


 

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

97 TRIPLES      21 PREDICATES      35 URIs      24 LITERALS      12 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1038/355161a0 schema:about N35d66c8da9cf42459dcb653c76d99305
2 N9b5882631969454e8eae0f59c58faf03
3 Ndb8c5411b54d4d8f91559e15b830e435
4 anzsrc-for:08
5 anzsrc-for:0801
6 schema:author Nf9ed913e0b654a3f859434611415d531
7 schema:citation sg:pub.10.1038/323533a0
8 https://doi.org/10.1214/ss/1177013604
9 https://doi.org/10.1523/jneurosci.10-07-02281.1990
10 schema:datePublished 1992-01
11 schema:datePublishedReg 1992-01-01
12 schema:description The standard form of back-propagation learning is implausible as a model of perceptual learning because it requires an external teacher to specify the desired output of the network. We show how the external teacher can be replaced by internally derived teaching signals. These signals are generated by using the assumption that different parts of the perceptual input have common causes in the external world. Small modules that look at separate but related parts of the perceptual input discover these common causes by striving to produce outputs that agree with each other. The modules may look at different modalities (such as vision and touch), or the same modality at different times (for example, the consecutive two-dimensional views of a rotating three-dimensional object), or even spatially adjacent parts of the same image. Our simulations show that when our learning procedure is applied to adjacent patches of two-dimensional images, it allows a neural network that has no prior knowledge of the third dimension to discovery depth in random dot stereograms of curved surfaces.
13 schema:genre research_article
14 schema:inLanguage en
15 schema:isAccessibleForFree false
16 schema:isPartOf N1118197696e0460dbe6ca0579377d180
17 N832be885643147fb8f505bb400f3f7ec
18 sg:journal.1018957
19 schema:name Self-organizing neural network that discovers surfaces in random-dot stereograms
20 schema:pagination 161-163
21 schema:productId N4fe2f41008c84ca5b58dcb6a4ef83c71
22 Nb43d4b6f8c964effa4a7f762f71fac92
23 Nbbee61a954df426686e8f892e10ed1fc
24 Nca0dca57568a4bfebef5b2ed06a2bab4
25 Nefe739329f594dd08dc1ab99262d45f4
26 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051732355
27 https://doi.org/10.1038/355161a0
28 schema:sdDatePublished 2019-04-10T16:29
29 schema:sdLicense https://scigraph.springernature.com/explorer/license/
30 schema:sdPublisher N24e18d83c2094597b7912aaac95cbf36
31 schema:url http://www.nature.com/articles/355161a0
32 sgo:license sg:explorer/license/
33 sgo:sdDataset articles
34 rdf:type schema:ScholarlyArticle
35 N1118197696e0460dbe6ca0579377d180 schema:volumeNumber 355
36 rdf:type schema:PublicationVolume
37 N24e18d83c2094597b7912aaac95cbf36 schema:name Springer Nature - SN SciGraph project
38 rdf:type schema:Organization
39 N35d66c8da9cf42459dcb653c76d99305 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
40 schema:name Artificial Intelligence
41 rdf:type schema:DefinedTerm
42 N4fe2f41008c84ca5b58dcb6a4ef83c71 schema:name pubmed_id
43 schema:value 1729650
44 rdf:type schema:PropertyValue
45 N832be885643147fb8f505bb400f3f7ec schema:issueNumber 6356
46 rdf:type schema:PublicationIssue
47 N9b5882631969454e8eae0f59c58faf03 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
48 schema:name Neural Networks (Computer)
49 rdf:type schema:DefinedTerm
50 N9b5ca6634132455db2152e06edfc0a4b rdf:first sg:person.0615147542.17
51 rdf:rest rdf:nil
52 Nb43d4b6f8c964effa4a7f762f71fac92 schema:name readcube_id
53 schema:value f66d164b6b3fe1acaad1b2a07fb48342630fc4b59fdacedccf2f9f3b6ba5389c
54 rdf:type schema:PropertyValue
55 Nbbee61a954df426686e8f892e10ed1fc schema:name nlm_unique_id
56 schema:value 0410462
57 rdf:type schema:PropertyValue
58 Nca0dca57568a4bfebef5b2ed06a2bab4 schema:name dimensions_id
59 schema:value pub.1051732355
60 rdf:type schema:PropertyValue
61 Ndb8c5411b54d4d8f91559e15b830e435 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
62 schema:name Mathematics
63 rdf:type schema:DefinedTerm
64 Nefe739329f594dd08dc1ab99262d45f4 schema:name doi
65 schema:value 10.1038/355161a0
66 rdf:type schema:PropertyValue
67 Nf9ed913e0b654a3f859434611415d531 rdf:first sg:person.0713333536.07
68 rdf:rest N9b5ca6634132455db2152e06edfc0a4b
69 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
70 schema:name Information and Computing Sciences
71 rdf:type schema:DefinedTerm
72 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
73 schema:name Artificial Intelligence and Image Processing
74 rdf:type schema:DefinedTerm
75 sg:journal.1018957 schema:issn 0090-0028
76 1476-4687
77 schema:name Nature
78 rdf:type schema:Periodical
79 sg:person.0615147542.17 schema:familyName Hinton
80 schema:givenName G E
81 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0615147542.17
82 rdf:type schema:Person
83 sg:person.0713333536.07 schema:affiliation https://www.grid.ac/institutes/grid.17063.33
84 schema:familyName Becker
85 schema:givenName S
86 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0713333536.07
87 rdf:type schema:Person
88 sg:pub.10.1038/323533a0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018367015
89 https://doi.org/10.1038/323533a0
90 rdf:type schema:CreativeWork
91 https://doi.org/10.1214/ss/1177013604 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052575245
92 rdf:type schema:CreativeWork
93 https://doi.org/10.1523/jneurosci.10-07-02281.1990 schema:sameAs https://app.dimensions.ai/details/publication/pub.1078743873
94 rdf:type schema:CreativeWork
95 https://www.grid.ac/institutes/grid.17063.33 schema:alternateName University of Toronto
96 schema:name Department of Computer Science, University of Toronto, Canada.
97 rdf:type schema:Organization
 




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


...