Learning machine with a hierarchial structure without mutual connections within levels thereof


Ontology type: sgo:Patent     


Patent Info

DATE

1994-03-15T00:00

AUTHORS

Toshiyuki Koda , Yasuharu Shimeki , Shigeo Sakaue , Hiroshi Yamamoto

ABSTRACT

A learning machine has plural multiple-input single-output signal processing circuits connected in a hierarchical structure. The learning machine sets a threshold value, which is a evaluation standard for change in weight coefficients, high during the early part of the learning process and enables rough learning to progress without changing the weight coefficients for those multiple-input single-output signal processing circuits for which errors are sufficiently small. On the other hand, the learning machine gradually reduces the threshold value as learning progresses and advances learning by a non-linear optimization method (including a conjugate gradient method, a linear search method, or a combination of conjugate gradient and linear search methods) during the later part of the learning process, and thereby improves the learning speed. 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/2008/2358", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "name": "Toshiyuki Koda", 
        "type": "Person"
      }, 
      {
        "name": "Yasuharu Shimeki", 
        "type": "Person"
      }, 
      {
        "name": "Shigeo Sakaue", 
        "type": "Person"
      }, 
      {
        "name": "Hiroshi Yamamoto", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/bf00332914", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043901229", 
          "https://doi.org/10.1007/bf00332914"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00332914", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043901229", 
          "https://doi.org/10.1007/bf00332914"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/21.44018", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061122179"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/29.60090", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061144715"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/37.55125", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061163222"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1994-03-15T00:00", 
    "description": "

A learning machine has plural multiple-input single-output signal processing circuits connected in a hierarchical structure. The learning machine sets a threshold value, which is a evaluation standard for change in weight coefficients, high during the early part of the learning process and enables rough learning to progress without changing the weight coefficients for those multiple-input single-output signal processing circuits for which errors are sufficiently small. On the other hand, the learning machine gradually reduces the threshold value as learning progresses and advances learning by a non-linear optimization method (including a conjugate gradient method, a linear search method, or a combination of conjugate gradient and linear search methods) during the later part of the learning process, and thereby improves the learning speed.

", "id": "sg:patent.US-5295228-A", "keywords": [ "machine", "connection", "signal processing", "hierarchical structure", "threshold value", "Evaluation Study as Topic", "coefficient", "early part", "progress", "error", "optimization method", "conjugate gradient method", "search method", "conjugate", "late part" ], "name": "Learning machine with a hierarchial structure without mutual connections within levels thereof", "recipient": [ { "id": "https://www.grid.ac/institutes/grid.410834.a", "type": "Organization" } ], "sameAs": [ "https://app.dimensions.ai/details/patent/US-5295228-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_02998.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-5295228-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-5295228-A'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/patent.US-5295228-A'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/patent.US-5295228-A'


 

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

62 TRIPLES      15 PREDICATES      33 URIs      23 LITERALS      2 BLANK NODES

Subject Predicate Object
1 sg:patent.US-5295228-A schema:about anzsrc-for:2358
2 schema:author N7c5c77de939d48539b0ce93b29c7a929
3 schema:citation sg:pub.10.1007/bf00332914
4 https://doi.org/10.1109/21.44018
5 https://doi.org/10.1109/29.60090
6 https://doi.org/10.1109/37.55125
7 schema:datePublished 1994-03-15T00:00
8 schema:description <p>A learning machine has plural multiple-input single-output signal processing circuits connected in a hierarchical structure. The learning machine sets a threshold value, which is a evaluation standard for change in weight coefficients, high during the early part of the learning process and enables rough learning to progress without changing the weight coefficients for those multiple-input single-output signal processing circuits for which errors are sufficiently small. On the other hand, the learning machine gradually reduces the threshold value as learning progresses and advances learning by a non-linear optimization method (including a conjugate gradient method, a linear search method, or a combination of conjugate gradient and linear search methods) during the later part of the learning process, and thereby improves the learning speed.</p>
9 schema:keywords Evaluation Study as Topic
10 coefficient
11 conjugate
12 conjugate gradient method
13 connection
14 early part
15 error
16 hierarchical structure
17 late part
18 machine
19 optimization method
20 progress
21 search method
22 signal processing
23 threshold value
24 schema:name Learning machine with a hierarchial structure without mutual connections within levels thereof
25 schema:recipient https://www.grid.ac/institutes/grid.410834.a
26 schema:sameAs https://app.dimensions.ai/details/patent/US-5295228-A
27 schema:sdDatePublished 2019-04-18T10:26
28 schema:sdLicense https://scigraph.springernature.com/explorer/license/
29 schema:sdPublisher N1f08f6c0ab74438c89ffecd42b378427
30 sgo:license sg:explorer/license/
31 sgo:sdDataset patents
32 rdf:type sgo:Patent
33 N0a734164751b4702b2d121613b0d13c3 schema:name Yasuharu Shimeki
34 rdf:type schema:Person
35 N1b4b1b92e01d484f95a6a11bdd80d5e6 rdf:first N344c325ee4074169866440581dab40d0
36 rdf:rest N453e69f83cc24055a6711380467d907d
37 N1f08f6c0ab74438c89ffecd42b378427 schema:name Springer Nature - SN SciGraph project
38 rdf:type schema:Organization
39 N2734a8d5f610459ea74e74614638124d rdf:first N0a734164751b4702b2d121613b0d13c3
40 rdf:rest N1b4b1b92e01d484f95a6a11bdd80d5e6
41 N344c325ee4074169866440581dab40d0 schema:name Shigeo Sakaue
42 rdf:type schema:Person
43 N453e69f83cc24055a6711380467d907d rdf:first Na2526e61fd9745439d41ed53134ca107
44 rdf:rest rdf:nil
45 N7c5c77de939d48539b0ce93b29c7a929 rdf:first N90ae962099e74d7ab59abe755d4857d7
46 rdf:rest N2734a8d5f610459ea74e74614638124d
47 N90ae962099e74d7ab59abe755d4857d7 schema:name Toshiyuki Koda
48 rdf:type schema:Person
49 Na2526e61fd9745439d41ed53134ca107 schema:name Hiroshi Yamamoto
50 rdf:type schema:Person
51 anzsrc-for:2358 schema:inDefinedTermSet anzsrc-for:
52 rdf:type schema:DefinedTerm
53 sg:pub.10.1007/bf00332914 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043901229
54 https://doi.org/10.1007/bf00332914
55 rdf:type schema:CreativeWork
56 https://doi.org/10.1109/21.44018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061122179
57 rdf:type schema:CreativeWork
58 https://doi.org/10.1109/29.60090 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061144715
59 rdf:type schema:CreativeWork
60 https://doi.org/10.1109/37.55125 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061163222
61 rdf:type schema:CreativeWork
62 https://www.grid.ac/institutes/grid.410834.a schema:Organization
 




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


...