Soft Randomized Machine Learning View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2018-11

AUTHORS

Yu. S. Popkov

ABSTRACT

A new method for entropy-randomized machine learning is proposed based on empirical risk minimization instead of the exact fulfillment of empirical balance conditions. The corresponding machine learning algorithm is shown to generate a family of exponential distributions, and their structure is found.

PAGES

646-647

References to SciGraph publications

  • 2008-09. Community cleverness required in NATURE
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1134/s1064562418070293

    DOI

    http://dx.doi.org/10.1134/s1064562418070293

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1111224426


    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": {
              "alternateName": "University of Haifa", 
              "id": "https://www.grid.ac/institutes/grid.18098.38", 
              "name": [
                "Institute for Systems Analysis, Federal Research Center \u201cComputer Science and Control,\u201d, Russian Academy of Sciences, 117312, Moscow, Russia", 
                "Haifa University, Karmiel, Israel", 
                "Yugorsk Research Institute of Information Technologies, Khanty-Mansiysk, Tyumen oblast, Russia"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Popkov", 
            "givenName": "Yu. S.", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1038/455001a", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1004258035", 
              "https://doi.org/10.1038/455001a"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/is.2016.7737456", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095777184"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018-11", 
        "datePublishedReg": "2018-11-01", 
        "description": "A new method for entropy-randomized machine learning is proposed based on empirical risk minimization instead of the exact fulfillment of empirical balance conditions. The corresponding machine learning algorithm is shown to generate a family of exponential distributions, and their structure is found.", 
        "genre": "non_research_article", 
        "id": "sg:pub.10.1134/s1064562418070293", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1136704", 
            "issn": [
              "1064-5624", 
              "1531-8362"
            ], 
            "name": "Doklady Mathematics", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "3", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "98"
          }
        ], 
        "name": "Soft Randomized Machine Learning", 
        "pagination": "646-647", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "9f2ae4853ed11aa0d5b53e77e7fb1d6b90ad164256488283abd0860ef3ce7660"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1134/s1064562418070293"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1111224426"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1134/s1064562418070293", 
          "https://app.dimensions.ai/details/publication/pub.1111224426"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T08:36", 
        "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/v90/0000000314_0000000314/records_55829_00000000.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1134%2FS1064562418070293"
      }
    ]
     

    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.10.1134/s1064562418070293'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1134/s1064562418070293'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1134/s1064562418070293'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1134/s1064562418070293'


     

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

    69 TRIPLES      21 PREDICATES      29 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1134/s1064562418070293 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Ndeb0780fa5884590aa9534754b596e1a
    4 schema:citation sg:pub.10.1038/455001a
    5 https://doi.org/10.1109/is.2016.7737456
    6 schema:datePublished 2018-11
    7 schema:datePublishedReg 2018-11-01
    8 schema:description A new method for entropy-randomized machine learning is proposed based on empirical risk minimization instead of the exact fulfillment of empirical balance conditions. The corresponding machine learning algorithm is shown to generate a family of exponential distributions, and their structure is found.
    9 schema:genre non_research_article
    10 schema:inLanguage en
    11 schema:isAccessibleForFree false
    12 schema:isPartOf N00245f905e184f0eb78f0e464bcd140f
    13 N9dcb973d28164b9e821dee74331c3578
    14 sg:journal.1136704
    15 schema:name Soft Randomized Machine Learning
    16 schema:pagination 646-647
    17 schema:productId N5a2d27dd5376464f8f43a38cd3048c94
    18 Nd3dd3b1388124b6aa5e4adb4ae5730a4
    19 Nfa9472a131dc41098ea70a2c62cda36d
    20 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111224426
    21 https://doi.org/10.1134/s1064562418070293
    22 schema:sdDatePublished 2019-04-11T08:36
    23 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    24 schema:sdPublisher Nea407470330b4038bbe97746ddc20d19
    25 schema:url https://link.springer.com/10.1134%2FS1064562418070293
    26 sgo:license sg:explorer/license/
    27 sgo:sdDataset articles
    28 rdf:type schema:ScholarlyArticle
    29 N00245f905e184f0eb78f0e464bcd140f schema:issueNumber 3
    30 rdf:type schema:PublicationIssue
    31 N5a2d27dd5376464f8f43a38cd3048c94 schema:name readcube_id
    32 schema:value 9f2ae4853ed11aa0d5b53e77e7fb1d6b90ad164256488283abd0860ef3ce7660
    33 rdf:type schema:PropertyValue
    34 N9205a6c3cdd74704be42c1cdf33dfa88 schema:affiliation https://www.grid.ac/institutes/grid.18098.38
    35 schema:familyName Popkov
    36 schema:givenName Yu. S.
    37 rdf:type schema:Person
    38 N9dcb973d28164b9e821dee74331c3578 schema:volumeNumber 98
    39 rdf:type schema:PublicationVolume
    40 Nd3dd3b1388124b6aa5e4adb4ae5730a4 schema:name doi
    41 schema:value 10.1134/s1064562418070293
    42 rdf:type schema:PropertyValue
    43 Ndeb0780fa5884590aa9534754b596e1a rdf:first N9205a6c3cdd74704be42c1cdf33dfa88
    44 rdf:rest rdf:nil
    45 Nea407470330b4038bbe97746ddc20d19 schema:name Springer Nature - SN SciGraph project
    46 rdf:type schema:Organization
    47 Nfa9472a131dc41098ea70a2c62cda36d schema:name dimensions_id
    48 schema:value pub.1111224426
    49 rdf:type schema:PropertyValue
    50 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    51 schema:name Information and Computing Sciences
    52 rdf:type schema:DefinedTerm
    53 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    54 schema:name Artificial Intelligence and Image Processing
    55 rdf:type schema:DefinedTerm
    56 sg:journal.1136704 schema:issn 1064-5624
    57 1531-8362
    58 schema:name Doklady Mathematics
    59 rdf:type schema:Periodical
    60 sg:pub.10.1038/455001a schema:sameAs https://app.dimensions.ai/details/publication/pub.1004258035
    61 https://doi.org/10.1038/455001a
    62 rdf:type schema:CreativeWork
    63 https://doi.org/10.1109/is.2016.7737456 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095777184
    64 rdf:type schema:CreativeWork
    65 https://www.grid.ac/institutes/grid.18098.38 schema:alternateName University of Haifa
    66 schema:name Haifa University, Karmiel, Israel
    67 Institute for Systems Analysis, Federal Research Center “Computer Science and Control,”, Russian Academy of Sciences, 117312, Moscow, Russia
    68 Yugorsk Research Institute of Information Technologies, Khanty-Mansiysk, Tyumen oblast, Russia
    69 rdf:type schema:Organization
     




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


    ...