Simplified neuron model as a principal component analyzer View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

1982-11

AUTHORS

Erkki Oja

ABSTRACT

A simple linear neuron model with constrained Hebbian-type synaptic modification is analyzed and a new class of unconstrained learning rules is derived. It is shown that the model neuron tends to extract the principal component from a stationary input vector sequence.

PAGES

267-273

Journal

TITLE

Journal of Mathematical Biology

ISSUE

3

VOLUME

15

Related Patents

  • Methods And Apparatus For Early Sensory Integration And Robust Acquisition Of Real World Knowledge
  • Self-Organization Of Pattern Data With Dimension Reduction Through Learning Of Non-Linear Variance-Constrained Mapping
  • Method For Recognizing Deviations Of The Surface Shape From A Predetermined Shape By Means Of A Three-Dimensional Measurement Value Acquisition And Subsequent Processing With An Artificial Neural Network
  • Methods And Apparatus For Iterative Nonspecific Distributed Runtime Architecture And Its Application To Cloud Intelligence
  • Method And Apparatus For A Local Competitive Learning Rule That Leads To Sparse Connectivity
  • Methods And Apparatus For Early Sensory Integration And Robust Acquisition Of Real World Knowledge
  • Methods And Apparatus For Autonomous Robotic Control
  • Methods And Apparatus For Autonomous Robotic Control
  • Visualization And Self-Organization Of Multidimensional Data Through Equalized Orthogonal Mapping
  • Methods And Apparatus For Autonomous Robotic Control
  • Graphic Processor Based Accelerator System And Method
  • System And Method For Controller Adaptation
  • Methods And Apparatus For Iterative Nonspecific Distributed Runtime Architecture And Its Application To Cloud Intelligence
  • Adaptive Control System Capable Of Recovering From Unexpected Situations
  • Online, Incremental Real-Time Learning For Tagging And Labeling Data Streams For Deep Neural Networks And Neural Network Applications
  • Methods And Apparatus For Autonomous Robotic Control
  • Method And Apparatus For A Local Competitive Learning Rule That Leads To Sparse Connectivity
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/bf00275687

    DOI

    http://dx.doi.org/10.1007/bf00275687

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1041038550

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/7153672


    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/2008/01", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Mathematical Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/06", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Biological Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Animals", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Mathematics", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Models, Neurological", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Neurons", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Synapses", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Institute of Mathematics, University of Kuopio, 70100, Kuopio 10, Finland", 
              "id": "http://www.grid.ac/institutes/grid.9668.1", 
              "name": [
                "Institute of Mathematics, University of Kuopio, 70100, Kuopio 10, Finland"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Oja", 
            "givenName": "Erkki", 
            "id": "sg:person.01111267524.42", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01111267524.42"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/bf02459570", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026163953", 
              "https://doi.org/10.1007/bf02459570"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00288907", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1020503948", 
              "https://doi.org/10.1007/bf00288907"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf03380115", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1084017657", 
              "https://doi.org/10.1007/bf03380115"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00319777", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026631832", 
              "https://doi.org/10.1007/bf00319777"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf02478259", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028715170", 
              "https://doi.org/10.1007/bf02478259"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00337414", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027306129", 
              "https://doi.org/10.1007/bf00337414"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4684-9352-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019074520", 
              "https://doi.org/10.1007/978-1-4684-9352-8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00337288", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009635558", 
              "https://doi.org/10.1007/bf00337288"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00337432", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1044501062", 
              "https://doi.org/10.1007/bf00337432"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "1982-11", 
        "datePublishedReg": "1982-11-01", 
        "description": "A simple linear neuron model with constrained Hebbian-type synaptic modification is analyzed and a new class of unconstrained learning rules is derived. It is shown that the model neuron tends to extract the principal component from a stationary input vector sequence.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/bf00275687", 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1081642", 
            "issn": [
              "0303-6812", 
              "1432-1416"
            ], 
            "name": "Journal of Mathematical Biology", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "3", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "15"
          }
        ], 
        "keywords": [
          "synaptic modification", 
          "model neurons", 
          "neurons", 
          "neuron model", 
          "new class", 
          "model", 
          "modification", 
          "components", 
          "principal components", 
          "simplified neuron model", 
          "analyzer", 
          "learning rule", 
          "sequence", 
          "class", 
          "vector sequences", 
          "rules", 
          "linear neuron model", 
          "input vector sequence", 
          "principal component analyzers"
        ], 
        "name": "Simplified neuron model as a principal component analyzer", 
        "pagination": "267-273", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1041038550"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/bf00275687"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "7153672"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/bf00275687", 
          "https://app.dimensions.ai/details/publication/pub.1041038550"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-10-01T06:27", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20221001/entities/gbq_results/article/article_166.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/bf00275687"
      }
    ]
     

    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/bf00275687'

    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/bf00275687'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/bf00275687'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/bf00275687'


     

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

    136 TRIPLES      21 PREDICATES      59 URIs      42 LITERALS      12 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/bf00275687 schema:about N0f7095df83644353851b659ef945ed1c
    2 N35fda3eb4b28490b923b2573e75ff050
    3 N5558f3cece0942ef87029281a2f33916
    4 N78591db55bfb4de1bc41adf57e3111c2
    5 Nca8e19565df542cc94cb865d1f06a86d
    6 anzsrc-for:01
    7 anzsrc-for:06
    8 schema:author N366ceace94ba476ab6f2900b0470e377
    9 schema:citation sg:pub.10.1007/978-1-4684-9352-8
    10 sg:pub.10.1007/bf00288907
    11 sg:pub.10.1007/bf00319777
    12 sg:pub.10.1007/bf00337288
    13 sg:pub.10.1007/bf00337414
    14 sg:pub.10.1007/bf00337432
    15 sg:pub.10.1007/bf02459570
    16 sg:pub.10.1007/bf02478259
    17 sg:pub.10.1007/bf03380115
    18 schema:datePublished 1982-11
    19 schema:datePublishedReg 1982-11-01
    20 schema:description A simple linear neuron model with constrained Hebbian-type synaptic modification is analyzed and a new class of unconstrained learning rules is derived. It is shown that the model neuron tends to extract the principal component from a stationary input vector sequence.
    21 schema:genre article
    22 schema:isAccessibleForFree false
    23 schema:isPartOf N9227f05d57be4017a1d46edec61c68bc
    24 Ndecb02f7086c46e2888f36a07dde3e09
    25 sg:journal.1081642
    26 schema:keywords analyzer
    27 class
    28 components
    29 input vector sequence
    30 learning rule
    31 linear neuron model
    32 model
    33 model neurons
    34 modification
    35 neuron model
    36 neurons
    37 new class
    38 principal component analyzers
    39 principal components
    40 rules
    41 sequence
    42 simplified neuron model
    43 synaptic modification
    44 vector sequences
    45 schema:name Simplified neuron model as a principal component analyzer
    46 schema:pagination 267-273
    47 schema:productId N0bab75c592144f42b517c250bd7bcd60
    48 Na514afc33f844e0ca8118fddaa95e952
    49 Nae49f30b257d4dbb9916b68048aad496
    50 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041038550
    51 https://doi.org/10.1007/bf00275687
    52 schema:sdDatePublished 2022-10-01T06:27
    53 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    54 schema:sdPublisher Nd5d3caa208da4332aefa779344945102
    55 schema:url https://doi.org/10.1007/bf00275687
    56 sgo:license sg:explorer/license/
    57 sgo:sdDataset articles
    58 rdf:type schema:ScholarlyArticle
    59 N0bab75c592144f42b517c250bd7bcd60 schema:name doi
    60 schema:value 10.1007/bf00275687
    61 rdf:type schema:PropertyValue
    62 N0f7095df83644353851b659ef945ed1c schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    63 schema:name Neurons
    64 rdf:type schema:DefinedTerm
    65 N35fda3eb4b28490b923b2573e75ff050 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    66 schema:name Models, Neurological
    67 rdf:type schema:DefinedTerm
    68 N366ceace94ba476ab6f2900b0470e377 rdf:first sg:person.01111267524.42
    69 rdf:rest rdf:nil
    70 N5558f3cece0942ef87029281a2f33916 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    71 schema:name Synapses
    72 rdf:type schema:DefinedTerm
    73 N78591db55bfb4de1bc41adf57e3111c2 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    74 schema:name Mathematics
    75 rdf:type schema:DefinedTerm
    76 N9227f05d57be4017a1d46edec61c68bc schema:issueNumber 3
    77 rdf:type schema:PublicationIssue
    78 Na514afc33f844e0ca8118fddaa95e952 schema:name pubmed_id
    79 schema:value 7153672
    80 rdf:type schema:PropertyValue
    81 Nae49f30b257d4dbb9916b68048aad496 schema:name dimensions_id
    82 schema:value pub.1041038550
    83 rdf:type schema:PropertyValue
    84 Nca8e19565df542cc94cb865d1f06a86d schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    85 schema:name Animals
    86 rdf:type schema:DefinedTerm
    87 Nd5d3caa208da4332aefa779344945102 schema:name Springer Nature - SN SciGraph project
    88 rdf:type schema:Organization
    89 Ndecb02f7086c46e2888f36a07dde3e09 schema:volumeNumber 15
    90 rdf:type schema:PublicationVolume
    91 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
    92 schema:name Mathematical Sciences
    93 rdf:type schema:DefinedTerm
    94 anzsrc-for:06 schema:inDefinedTermSet anzsrc-for:
    95 schema:name Biological Sciences
    96 rdf:type schema:DefinedTerm
    97 sg:journal.1081642 schema:issn 0303-6812
    98 1432-1416
    99 schema:name Journal of Mathematical Biology
    100 schema:publisher Springer Nature
    101 rdf:type schema:Periodical
    102 sg:person.01111267524.42 schema:affiliation grid-institutes:grid.9668.1
    103 schema:familyName Oja
    104 schema:givenName Erkki
    105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01111267524.42
    106 rdf:type schema:Person
    107 sg:pub.10.1007/978-1-4684-9352-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019074520
    108 https://doi.org/10.1007/978-1-4684-9352-8
    109 rdf:type schema:CreativeWork
    110 sg:pub.10.1007/bf00288907 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020503948
    111 https://doi.org/10.1007/bf00288907
    112 rdf:type schema:CreativeWork
    113 sg:pub.10.1007/bf00319777 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026631832
    114 https://doi.org/10.1007/bf00319777
    115 rdf:type schema:CreativeWork
    116 sg:pub.10.1007/bf00337288 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009635558
    117 https://doi.org/10.1007/bf00337288
    118 rdf:type schema:CreativeWork
    119 sg:pub.10.1007/bf00337414 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027306129
    120 https://doi.org/10.1007/bf00337414
    121 rdf:type schema:CreativeWork
    122 sg:pub.10.1007/bf00337432 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044501062
    123 https://doi.org/10.1007/bf00337432
    124 rdf:type schema:CreativeWork
    125 sg:pub.10.1007/bf02459570 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026163953
    126 https://doi.org/10.1007/bf02459570
    127 rdf:type schema:CreativeWork
    128 sg:pub.10.1007/bf02478259 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028715170
    129 https://doi.org/10.1007/bf02478259
    130 rdf:type schema:CreativeWork
    131 sg:pub.10.1007/bf03380115 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084017657
    132 https://doi.org/10.1007/bf03380115
    133 rdf:type schema:CreativeWork
    134 grid-institutes:grid.9668.1 schema:alternateName Institute of Mathematics, University of Kuopio, 70100, Kuopio 10, Finland
    135 schema:name Institute of Mathematics, University of Kuopio, 70100, Kuopio 10, Finland
    136 rdf:type schema:Organization
     




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


    ...