Neural-space generalization of a topological transformation View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

1988-09

AUTHORS

G. Josin

ABSTRACT

An investigation is performed to assess the generalization capability found in neural network paradigms to approximate a 2-dimensional coordinate (topological) transformation. A developed strategy uses the example to give a physical meaning to what is meant by generalization. The example shows how to use a neural network paradigm to generalize a two-degree of freedom topological transformation from cartesian end-point coordinates to corresponding joint angle coordinates based only on examples of the mapping. The importance of this example is that it provides a clear understanding of how and what a neural network is actually communications and brings a theoretical idea to a useful understanding. When examples characterize the topology, a collective generalization property begins to emerge and the network learns the topology. If the network is presented with additional examples of the transformation, the network can generate the corresponding joint angles to any unseen position, that is, by generalization. It is also significant that the network's generalization property emerges from the network based on very few training examples! Further, the networks power exists with very few neurons. Results suggest the use of the paradigm's generalization capability to provide solutions to unknown or intractable algorithms for applications. More... »

PAGES

283-290

References to SciGraph publications

  • 1977-12. Self-control in neural nets in BIOLOGICAL CYBERNETICS
  • 1985-07. “Neural” computation of decisions in optimization problems in BIOLOGICAL CYBERNETICS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/bf00332917

    DOI

    http://dx.doi.org/10.1007/bf00332917

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1048697356

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/3196772


    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": "Models, Neurological", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "name": [
                "Neural Systems Incorporated, 2827 West 43rd Avenue, V6N 3H9, Vancouver, British Columbia, Canada"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Josin", 
            "givenName": "G.", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/bf00344139", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017031923", 
              "https://doi.org/10.1007/bf00344139"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00344139", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017031923", 
              "https://doi.org/10.1007/bf00344139"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1073/pnas.79.8.2554", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038762424"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0022-5193(61)90046-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040640000"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00339943", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1080089235", 
              "https://doi.org/10.1007/bf00339943"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "1988-09", 
        "datePublishedReg": "1988-09-01", 
        "description": "An investigation is performed to assess the generalization capability found in neural network paradigms to approximate a 2-dimensional coordinate (topological) transformation. A developed strategy uses the example to give a physical meaning to what is meant by generalization. The example shows how to use a neural network paradigm to generalize a two-degree of freedom topological transformation from cartesian end-point coordinates to corresponding joint angle coordinates based only on examples of the mapping. The importance of this example is that it provides a clear understanding of how and what a neural network is actually communications and brings a theoretical idea to a useful understanding. When examples characterize the topology, a collective generalization property begins to emerge and the network learns the topology. If the network is presented with additional examples of the transformation, the network can generate the corresponding joint angles to any unseen position, that is, by generalization. It is also significant that the network's generalization property emerges from the network based on very few training examples! Further, the networks power exists with very few neurons. Results suggest the use of the paradigm's generalization capability to provide solutions to unknown or intractable algorithms for applications.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/bf00332917", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1081741", 
            "issn": [
              "0340-1200", 
              "1432-0770"
            ], 
            "name": "Biological Cybernetics", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "4-5", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "59"
          }
        ], 
        "name": "Neural-space generalization of a topological transformation", 
        "pagination": "283-290", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/bf00332917"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "e7fc2503b2d2a9f745a65d05cac64a76a67b54572073b006b586444bb1f7d411"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1048697356"
            ]
          }, 
          {
            "name": "nlm_unique_id", 
            "type": "PropertyValue", 
            "value": [
              "7502533"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "3196772"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/bf00332917", 
          "https://app.dimensions.ai/details/publication/pub.1048697356"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-15T08:52", 
        "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/v90/0000000374_0000000374/records_119741_00000001.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "http://link.springer.com/10.1007/BF00332917"
      }
    ]
     

    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/bf00332917'

    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/bf00332917'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/bf00332917'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/bf00332917'


     

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

    89 TRIPLES      21 PREDICATES      35 URIs      23 LITERALS      11 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/bf00332917 schema:about N15132a8060b14a2fbba4d4eb09b4f0cb
    2 N1d56717c1ab443129eb65e27f5fc9a24
    3 anzsrc-for:08
    4 anzsrc-for:0801
    5 schema:author Nd5f79e93919c44c0ab231c36dece8796
    6 schema:citation sg:pub.10.1007/bf00339943
    7 sg:pub.10.1007/bf00344139
    8 https://doi.org/10.1016/0022-5193(61)90046-7
    9 https://doi.org/10.1073/pnas.79.8.2554
    10 schema:datePublished 1988-09
    11 schema:datePublishedReg 1988-09-01
    12 schema:description An investigation is performed to assess the generalization capability found in neural network paradigms to approximate a 2-dimensional coordinate (topological) transformation. A developed strategy uses the example to give a physical meaning to what is meant by generalization. The example shows how to use a neural network paradigm to generalize a two-degree of freedom topological transformation from cartesian end-point coordinates to corresponding joint angle coordinates based only on examples of the mapping. The importance of this example is that it provides a clear understanding of how and what a neural network is actually communications and brings a theoretical idea to a useful understanding. When examples characterize the topology, a collective generalization property begins to emerge and the network learns the topology. If the network is presented with additional examples of the transformation, the network can generate the corresponding joint angles to any unseen position, that is, by generalization. It is also significant that the network's generalization property emerges from the network based on very few training examples! Further, the networks power exists with very few neurons. Results suggest the use of the paradigm's generalization capability to provide solutions to unknown or intractable algorithms for applications.
    13 schema:genre research_article
    14 schema:inLanguage en
    15 schema:isAccessibleForFree false
    16 schema:isPartOf N3024946aa7a64196be631b37c2987322
    17 N7f2e012a663542f297c6b25c9f659bcf
    18 sg:journal.1081741
    19 schema:name Neural-space generalization of a topological transformation
    20 schema:pagination 283-290
    21 schema:productId N4e1f7d03fc8d4201bfae6d7143006760
    22 N5f198883a6e449f39810c40e1b0714da
    23 Nac25e8046cff43b79335dda09ea61ff1
    24 Ncf133c81c2bd46089794d9ad3be8f92f
    25 Nfc63ab3a71f94222addfe0aa20b481c9
    26 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048697356
    27 https://doi.org/10.1007/bf00332917
    28 schema:sdDatePublished 2019-04-15T08:52
    29 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    30 schema:sdPublisher N20f56a1f23714ce89b44487226af41d1
    31 schema:url http://link.springer.com/10.1007/BF00332917
    32 sgo:license sg:explorer/license/
    33 sgo:sdDataset articles
    34 rdf:type schema:ScholarlyArticle
    35 N15132a8060b14a2fbba4d4eb09b4f0cb schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    36 schema:name Artificial Intelligence
    37 rdf:type schema:DefinedTerm
    38 N1d56717c1ab443129eb65e27f5fc9a24 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    39 schema:name Models, Neurological
    40 rdf:type schema:DefinedTerm
    41 N20f56a1f23714ce89b44487226af41d1 schema:name Springer Nature - SN SciGraph project
    42 rdf:type schema:Organization
    43 N3024946aa7a64196be631b37c2987322 schema:volumeNumber 59
    44 rdf:type schema:PublicationVolume
    45 N4e1f7d03fc8d4201bfae6d7143006760 schema:name readcube_id
    46 schema:value e7fc2503b2d2a9f745a65d05cac64a76a67b54572073b006b586444bb1f7d411
    47 rdf:type schema:PropertyValue
    48 N5f198883a6e449f39810c40e1b0714da schema:name doi
    49 schema:value 10.1007/bf00332917
    50 rdf:type schema:PropertyValue
    51 N7f2e012a663542f297c6b25c9f659bcf schema:issueNumber 4-5
    52 rdf:type schema:PublicationIssue
    53 Nac25e8046cff43b79335dda09ea61ff1 schema:name nlm_unique_id
    54 schema:value 7502533
    55 rdf:type schema:PropertyValue
    56 Nbb3dd5ba15d344c1a62a26cc7526889a schema:affiliation Nf1ec99df1c5f4ce682db8d9d56294f87
    57 schema:familyName Josin
    58 schema:givenName G.
    59 rdf:type schema:Person
    60 Ncf133c81c2bd46089794d9ad3be8f92f schema:name pubmed_id
    61 schema:value 3196772
    62 rdf:type schema:PropertyValue
    63 Nd5f79e93919c44c0ab231c36dece8796 rdf:first Nbb3dd5ba15d344c1a62a26cc7526889a
    64 rdf:rest rdf:nil
    65 Nf1ec99df1c5f4ce682db8d9d56294f87 schema:name Neural Systems Incorporated, 2827 West 43rd Avenue, V6N 3H9, Vancouver, British Columbia, Canada
    66 rdf:type schema:Organization
    67 Nfc63ab3a71f94222addfe0aa20b481c9 schema:name dimensions_id
    68 schema:value pub.1048697356
    69 rdf:type schema:PropertyValue
    70 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    71 schema:name Information and Computing Sciences
    72 rdf:type schema:DefinedTerm
    73 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    74 schema:name Artificial Intelligence and Image Processing
    75 rdf:type schema:DefinedTerm
    76 sg:journal.1081741 schema:issn 0340-1200
    77 1432-0770
    78 schema:name Biological Cybernetics
    79 rdf:type schema:Periodical
    80 sg:pub.10.1007/bf00339943 schema:sameAs https://app.dimensions.ai/details/publication/pub.1080089235
    81 https://doi.org/10.1007/bf00339943
    82 rdf:type schema:CreativeWork
    83 sg:pub.10.1007/bf00344139 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017031923
    84 https://doi.org/10.1007/bf00344139
    85 rdf:type schema:CreativeWork
    86 https://doi.org/10.1016/0022-5193(61)90046-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040640000
    87 rdf:type schema:CreativeWork
    88 https://doi.org/10.1073/pnas.79.8.2554 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038762424
    89 rdf:type schema:CreativeWork
     




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


    ...