Machine learning heterogeneous edge device, method, and system


Ontology type: sgo:Patent     


Patent Info

DATE

2018-06-05T00:00

AUTHORS

Daisuke Okanohara , Justin B. Clayton , Toru Nishikawa , Shohei Hido , Nobuyuki Kubota , Nobuyuki Ota , Seiya Tokui

ABSTRACT

A machine learning heterogeneous edge device, method, and system are disclosed. In an example embodiment, an edge device includes a communication module, a data collection device, a memory, a machine learning module, a group determination module, and a leader election module. The edge device analyzes collected data with a model, outputs a result, and updates the model to create a local model. The edge device communicates with other edge devices in a heterogeneous group. The edge device determines group membership and determines a leader edge device. The edge device receives a request for the local model, transmits the local model to the leader edge device, receives a mixed model created by the leader edge device performing a mix operation of the local model and a different local model, and replaces the local model with the mixed model. More... »

Related SciGraph Publications

  • 1999-04. MDL Principle for Robust Vector Quantisation in PATTERN ANALYSIS AND APPLICATIONS
  • 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/2008/2746", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "name": "Daisuke Okanohara", 
            "type": "Person"
          }, 
          {
            "name": "Justin B. Clayton", 
            "type": "Person"
          }, 
          {
            "name": "Toru Nishikawa", 
            "type": "Person"
          }, 
          {
            "name": "Shohei Hido", 
            "type": "Person"
          }, 
          {
            "name": "Nobuyuki Kubota", 
            "type": "Person"
          }, 
          {
            "name": "Nobuyuki Ota", 
            "type": "Person"
          }, 
          {
            "name": "Seiya Tokui", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1006/jcss.1997.1504", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1004338842"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/279227.279229", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008966950"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1037/h0042519", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1030890551"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s100440050015", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1036925934", 
              "https://doi.org/10.1007/s100440050015"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tsmc.1986.289288", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061793830"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018-06-05T00:00", 
        "description": "

    A machine learning heterogeneous edge device, method, and system are disclosed. In an example embodiment, an edge device includes a communication module, a data collection device, a memory, a machine learning module, a group determination module, and a leader election module. The edge device analyzes collected data with a model, outputs a result, and updates the model to create a local model. The edge device communicates with other edge devices in a heterogeneous group. The edge device determines group membership and determines a leader edge device. The edge device receives a request for the local model, transmits the local model to the leader edge device, receives a mixed model created by the leader edge device performing a mix operation of the local model and a different local model, and replaces the local model with the mixed model.

    ", "id": "sg:patent.US-9990587-B2", "keywords": [ "machine", "edge device", "method", "embodiment", "communication", "Data Collection", "memory", "module", "determination", "election", "collected data", "output", "update", "local model", "heterogeneous group", "group membership", "request", "mixed model", "operation" ], "name": "Machine learning heterogeneous edge device, method, and system", "sameAs": [ "https://app.dimensions.ai/details/patent/US-9990587-B2" ], "sdDataset": "patents", "sdDatePublished": "2019-04-18T10:22", "sdLicense": "https://scigraph.springernature.com/explorer/license/", "sdPublisher": { "name": "Springer Nature - SN SciGraph project", "type": "Organization" }, "sdSource": "s3://com-uberresearch-data-patents-target-20190320-rc/data/sn-export/402f166718b70575fb5d4ffe01f064d1/0000100128-0000352499/json_export_01762.jsonl", "type": "Patent" } ]
     

    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/patent.US-9990587-B2'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/patent.US-9990587-B2'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/patent.US-9990587-B2'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/patent.US-9990587-B2'


     

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

    79 TRIPLES      14 PREDICATES      37 URIs      27 LITERALS      2 BLANK NODES

    Subject Predicate Object
    1 sg:patent.US-9990587-B2 schema:about anzsrc-for:2746
    2 schema:author N0c6e743b721c4e25b87a307238fbba42
    3 schema:citation sg:pub.10.1007/s100440050015
    4 https://doi.org/10.1006/jcss.1997.1504
    5 https://doi.org/10.1037/h0042519
    6 https://doi.org/10.1109/tsmc.1986.289288
    7 https://doi.org/10.1145/279227.279229
    8 schema:datePublished 2018-06-05T00:00
    9 schema:description <p id="p-0001" num="0000">A machine learning heterogeneous edge device, method, and system are disclosed. In an example embodiment, an edge device includes a communication module, a data collection device, a memory, a machine learning module, a group determination module, and a leader election module. The edge device analyzes collected data with a model, outputs a result, and updates the model to create a local model. The edge device communicates with other edge devices in a heterogeneous group. The edge device determines group membership and determines a leader edge device. The edge device receives a request for the local model, transmits the local model to the leader edge device, receives a mixed model created by the leader edge device performing a mix operation of the local model and a different local model, and replaces the local model with the mixed model.</p>
    10 schema:keywords Data Collection
    11 collected data
    12 communication
    13 determination
    14 edge device
    15 election
    16 embodiment
    17 group membership
    18 heterogeneous group
    19 local model
    20 machine
    21 memory
    22 method
    23 mixed model
    24 module
    25 operation
    26 output
    27 request
    28 update
    29 schema:name Machine learning heterogeneous edge device, method, and system
    30 schema:sameAs https://app.dimensions.ai/details/patent/US-9990587-B2
    31 schema:sdDatePublished 2019-04-18T10:22
    32 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    33 schema:sdPublisher N031da6070a3d4610ba017e58b57e0c25
    34 sgo:license sg:explorer/license/
    35 sgo:sdDataset patents
    36 rdf:type sgo:Patent
    37 N031da6070a3d4610ba017e58b57e0c25 schema:name Springer Nature - SN SciGraph project
    38 rdf:type schema:Organization
    39 N0aa1220c39b144429f8e0666fa1af4d4 schema:name Justin B. Clayton
    40 rdf:type schema:Person
    41 N0c6e743b721c4e25b87a307238fbba42 rdf:first N47e6cdda3ce84cc385634d8ceccc7d2c
    42 rdf:rest Nf7cb0b90cac645d390f325e187829e63
    43 N34abc1fd29704e0590da67e77d603004 schema:name Shohei Hido
    44 rdf:type schema:Person
    45 N36451599d56f46a98be2f82bea2b5596 schema:name Toru Nishikawa
    46 rdf:type schema:Person
    47 N44f2427dbe8f4fb384fccb0f3830e25c rdf:first N36451599d56f46a98be2f82bea2b5596
    48 rdf:rest N890807f1042e4991aa0f60a9c7112582
    49 N47e6cdda3ce84cc385634d8ceccc7d2c schema:name Daisuke Okanohara
    50 rdf:type schema:Person
    51 N52788311fd5a42e6a8503f56d1ee6433 schema:name Seiya Tokui
    52 rdf:type schema:Person
    53 N550db313688541669150784c9c119b37 schema:name Nobuyuki Ota
    54 rdf:type schema:Person
    55 N67994dc9ee294f04bfee0e7fc3a86e24 rdf:first N550db313688541669150784c9c119b37
    56 rdf:rest Nbbe6e27ee94044a781c91335e6dc1bf7
    57 N8125a7c01bda42b2802e8dfab8e24e2a rdf:first N88b542de8255472bb0a7fe3553995ec0
    58 rdf:rest N67994dc9ee294f04bfee0e7fc3a86e24
    59 N88b542de8255472bb0a7fe3553995ec0 schema:name Nobuyuki Kubota
    60 rdf:type schema:Person
    61 N890807f1042e4991aa0f60a9c7112582 rdf:first N34abc1fd29704e0590da67e77d603004
    62 rdf:rest N8125a7c01bda42b2802e8dfab8e24e2a
    63 Nbbe6e27ee94044a781c91335e6dc1bf7 rdf:first N52788311fd5a42e6a8503f56d1ee6433
    64 rdf:rest rdf:nil
    65 Nf7cb0b90cac645d390f325e187829e63 rdf:first N0aa1220c39b144429f8e0666fa1af4d4
    66 rdf:rest N44f2427dbe8f4fb384fccb0f3830e25c
    67 anzsrc-for:2746 schema:inDefinedTermSet anzsrc-for:
    68 rdf:type schema:DefinedTerm
    69 sg:pub.10.1007/s100440050015 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036925934
    70 https://doi.org/10.1007/s100440050015
    71 rdf:type schema:CreativeWork
    72 https://doi.org/10.1006/jcss.1997.1504 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004338842
    73 rdf:type schema:CreativeWork
    74 https://doi.org/10.1037/h0042519 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030890551
    75 rdf:type schema:CreativeWork
    76 https://doi.org/10.1109/tsmc.1986.289288 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061793830
    77 rdf:type schema:CreativeWork
    78 https://doi.org/10.1145/279227.279229 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008966950
    79 rdf:type schema:CreativeWork
     




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


    ...