Neutral Network With Plural Weight Calculation Methods And Variation Of Plural Learning Parameters


Ontology type: sgo:Patent     


Patent Info

DATE

1992-12-01T00:00

AUTHORS

Shigeo Sakaue , Toshiyuki Kohda , Yasuharu Shimeki , Hideyuki Takagi , Hayato Togawa

ABSTRACT

An iterative learning machine uses, as a direction of changing iterative weight, a conjugate gradient direction in place of the conventional steepest descent direction, thereby saving time. Learning rates are set dynamically. Error calculation for plural learning rates, with respect to a certain weight changing direction, are accomplished by storing a product-sum of the input signals and weights in a hidden layer and a product-sum of the input signals and the weight changing direction in the hidden layer. When the learning falls into a non-effective state where further iteration does not effectively reduce an error, the weights are adjusted in order to restart the learning. More... »

Related SciGraph Publications

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": "Shigeo Sakaue", 
        "type": "Person"
      }, 
      {
        "name": "Toshiyuki Kohda", 
        "type": "Person"
      }, 
      {
        "name": "Yasuharu Shimeki", 
        "type": "Person"
      }, 
      {
        "name": "Hideyuki Takagi", 
        "type": "Person"
      }, 
      {
        "name": "Hayato Togawa", 
        "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/10.1016/0893-6080(88)90003-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019288082"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(88)90003-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019288082"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1992-12-01T00:00", 
    "description": "

An iterative learning machine uses, as a direction of changing iterative weight, a conjugate gradient direction in place of the conventional steepest descent direction, thereby saving time. Learning rates are set dynamically. Error calculation for plural learning rates, with respect to a certain weight changing direction, are accomplished by storing a product-sum of the input signals and weights in a hidden layer and a product-sum of the input signals and the weight changing direction in the hidden layer. When the learning falls into a non-effective state where further iteration does not effectively reduce an error, the weights are adjusted in order to restart the learning.

", "id": "sg:patent.US-5168550-A", "keywords": [ "calculation method", "machine", "weight", "conjugate", "descent", "Learning", "calculation", "respect", "product", "input signal", "layer", "state", "error" ], "name": "NEUTRAL NETWORK WITH PLURAL WEIGHT CALCULATION METHODS AND VARIATION OF PLURAL LEARNING PARAMETERS", "recipient": [ { "id": "https://www.grid.ac/institutes/grid.410834.a", "type": "Organization" } ], "sameAs": [ "https://app.dimensions.ai/details/patent/US-5168550-A" ], "sdDataset": "patents", "sdDatePublished": "2019-04-18T10:26", "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_02985.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-5168550-A'

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-5168550-A'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/patent.US-5168550-A'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/patent.US-5168550-A'


 

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

58 TRIPLES      15 PREDICATES      29 URIs      21 LITERALS      2 BLANK NODES

Subject Predicate Object
1 sg:patent.US-5168550-A schema:about anzsrc-for:2746
2 schema:author N98da25edd06043fa9f6ce1333e9de2d4
3 schema:citation sg:pub.10.1038/323533a0
4 https://doi.org/10.1016/0893-6080(88)90003-2
5 schema:datePublished 1992-12-01T00:00
6 schema:description <p>An iterative learning machine uses, as a direction of changing iterative weight, a conjugate gradient direction in place of the conventional steepest descent direction, thereby saving time. Learning rates are set dynamically. Error calculation for plural learning rates, with respect to a certain weight changing direction, are accomplished by storing a product-sum of the input signals and weights in a hidden layer and a product-sum of the input signals and the weight changing direction in the hidden layer. When the learning falls into a non-effective state where further iteration does not effectively reduce an error, the weights are adjusted in order to restart the learning.</p>
7 schema:keywords Learning
8 calculation
9 calculation method
10 conjugate
11 descent
12 error
13 input signal
14 layer
15 machine
16 product
17 respect
18 state
19 weight
20 schema:name NEUTRAL NETWORK WITH PLURAL WEIGHT CALCULATION METHODS AND VARIATION OF PLURAL LEARNING PARAMETERS
21 schema:recipient https://www.grid.ac/institutes/grid.410834.a
22 schema:sameAs https://app.dimensions.ai/details/patent/US-5168550-A
23 schema:sdDatePublished 2019-04-18T10:26
24 schema:sdLicense https://scigraph.springernature.com/explorer/license/
25 schema:sdPublisher Nf52ea8a2c55f4adab6237d6005f11f30
26 sgo:license sg:explorer/license/
27 sgo:sdDataset patents
28 rdf:type sgo:Patent
29 N03c708c916834e8eb4c8783b25f34a56 schema:name Yasuharu Shimeki
30 rdf:type schema:Person
31 N52acb9858be94c00affa07426a403aee schema:name Hideyuki Takagi
32 rdf:type schema:Person
33 N54444095f4bb496398a562306c2460e7 rdf:first Nac7bc6a3e6984c05a165ddccddd68f55
34 rdf:rest rdf:nil
35 N55b580b7de9a4d69bbb1957a0dd58fcf rdf:first N52acb9858be94c00affa07426a403aee
36 rdf:rest N54444095f4bb496398a562306c2460e7
37 N5d76d7d2032e4b9ca9e41dd64ed8dccd schema:name Toshiyuki Kohda
38 rdf:type schema:Person
39 N7e2a94b053224c89a2f0eb025dea508c rdf:first N03c708c916834e8eb4c8783b25f34a56
40 rdf:rest N55b580b7de9a4d69bbb1957a0dd58fcf
41 N926cd1d4242e42d3802233c1c5f4558a schema:name Shigeo Sakaue
42 rdf:type schema:Person
43 N98da25edd06043fa9f6ce1333e9de2d4 rdf:first N926cd1d4242e42d3802233c1c5f4558a
44 rdf:rest Nd87b9e8333854841ba84941a23797391
45 Nac7bc6a3e6984c05a165ddccddd68f55 schema:name Hayato Togawa
46 rdf:type schema:Person
47 Nd87b9e8333854841ba84941a23797391 rdf:first N5d76d7d2032e4b9ca9e41dd64ed8dccd
48 rdf:rest N7e2a94b053224c89a2f0eb025dea508c
49 Nf52ea8a2c55f4adab6237d6005f11f30 schema:name Springer Nature - SN SciGraph project
50 rdf:type schema:Organization
51 anzsrc-for:2746 schema:inDefinedTermSet anzsrc-for:
52 rdf:type schema:DefinedTerm
53 sg:pub.10.1038/323533a0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018367015
54 https://doi.org/10.1038/323533a0
55 rdf:type schema:CreativeWork
56 https://doi.org/10.1016/0893-6080(88)90003-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019288082
57 rdf:type schema:CreativeWork
58 https://www.grid.ac/institutes/grid.410834.a schema:Organization
 




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


...