Double-Layered Cortical Learning Algorithm for Time-Series Prediction View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2021

AUTHORS

Takeru Aoki , Keiki Takadama , Hiroyuki Sato

ABSTRACT

This work proposes a double-layered cortical learning algorithm. The cortical learning algorithm is a time-series prediction methodology inspired from the human neuro-cortex. The human neuro-cortex has a multi-layer structure, while the conventional cortical learning algorithm has a single layer structure. This work introduces a double-layered structure into the cortical learning algorithm. The first layer represents the input data and its context every time-step. The input data context presentation in the first layer is transferred to the second layer, and it is represented in the second layer as an abstract representation. Also, the abstract prediction in the second layer is reflected to the first layer to modify and enhance the prediction in the first layer. The experimental results show that the proposed double-layered cortical learning algorithm achieves higher prediction accuracy than the conventional single-layered cortical learning algorithms and the recurrent neural networks with the long short-term memory on several artificial time-series data. More... »

PAGES

33-44

Book

TITLE

Bio-Inspired Information and Communications Technologies

ISBN

978-3-030-92162-0
978-3-030-92163-7

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-030-92163-7_4

DOI

http://dx.doi.org/10.1007/978-3-030-92163-7_4

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1143570240


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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "The University of Electro-Communications, 1-5-1 Chofugaoka, 182-8585, Chofu, Tokyo, Japan", 
          "id": "http://www.grid.ac/institutes/grid.266298.1", 
          "name": [
            "The University of Electro-Communications, 1-5-1 Chofugaoka, 182-8585, Chofu, Tokyo, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Aoki", 
        "givenName": "Takeru", 
        "id": "sg:person.015162262761.13", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015162262761.13"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "The University of Electro-Communications, 1-5-1 Chofugaoka, 182-8585, Chofu, Tokyo, Japan", 
          "id": "http://www.grid.ac/institutes/grid.266298.1", 
          "name": [
            "The University of Electro-Communications, 1-5-1 Chofugaoka, 182-8585, Chofu, Tokyo, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Takadama", 
        "givenName": "Keiki", 
        "id": "sg:person.012774267611.99", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012774267611.99"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "The University of Electro-Communications, 1-5-1 Chofugaoka, 182-8585, Chofu, Tokyo, Japan", 
          "id": "http://www.grid.ac/institutes/grid.266298.1", 
          "name": [
            "The University of Electro-Communications, 1-5-1 Chofugaoka, 182-8585, Chofu, Tokyo, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Sato", 
        "givenName": "Hiroyuki", 
        "id": "sg:person.07750750604.05", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07750750604.05"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2021", 
    "datePublishedReg": "2021-01-01", 
    "description": "This work proposes a double-layered cortical learning algorithm. The cortical learning algorithm is a time-series prediction methodology inspired from the human neuro-cortex. The human neuro-cortex has a multi-layer structure, while the conventional cortical learning algorithm has a single layer structure. This work introduces a double-layered structure into the cortical learning algorithm. The first layer represents the input data and its context every time-step. The input data context presentation in the first layer is transferred to the second layer, and it is represented in the second layer as an abstract representation. Also, the abstract prediction in the second layer is reflected to the first layer to modify and enhance the prediction in the first layer. The experimental results show that the proposed double-layered cortical learning algorithm achieves higher prediction accuracy than the conventional single-layered cortical learning algorithms and the recurrent neural networks with the long short-term memory on several artificial time-series data.", 
    "editor": [
      {
        "familyName": "Nakano", 
        "givenName": "Tadashi", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-030-92163-7_4", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-030-92162-0", 
        "978-3-030-92163-7"
      ], 
      "name": "Bio-Inspired Information and Communications Technologies", 
      "type": "Book"
    }, 
    "keywords": [
      "cortical learning algorithm", 
      "learning algorithm", 
      "long short-term memory", 
      "artificial time-series data", 
      "recurrent neural network", 
      "time series prediction", 
      "conventional cortical learning algorithm", 
      "first layer", 
      "high prediction accuracy", 
      "neural network", 
      "second layer", 
      "short-term memory", 
      "abstract representation", 
      "time series data", 
      "input data", 
      "algorithm", 
      "prediction accuracy", 
      "context presentation", 
      "experimental results", 
      "prediction methodology", 
      "Abstract Prediction", 
      "network", 
      "multi-layer structure", 
      "prediction", 
      "accuracy", 
      "representation", 
      "work", 
      "data", 
      "memory", 
      "methodology", 
      "single-layer structure", 
      "context", 
      "layer", 
      "structure", 
      "results", 
      "presentation", 
      "layer structure", 
      "double-layered structure"
    ], 
    "name": "Double-Layered Cortical Learning Algorithm for Time-Series Prediction", 
    "pagination": "33-44", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1143570240"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-030-92163-7_4"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-030-92163-7_4", 
      "https://app.dimensions.ai/details/publication/pub.1143570240"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-05-20T07:44", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220519/entities/gbq_results/chapter/chapter_259.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-030-92163-7_4"
  }
]
 

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.10.1007/978-3-030-92163-7_4'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-92163-7_4'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-92163-7_4'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-92163-7_4'


 

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

112 TRIPLES      23 PREDICATES      64 URIs      57 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-030-92163-7_4 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nb4dbe7bddb73470b99c9ab2edf9a7d89
4 schema:datePublished 2021
5 schema:datePublishedReg 2021-01-01
6 schema:description This work proposes a double-layered cortical learning algorithm. The cortical learning algorithm is a time-series prediction methodology inspired from the human neuro-cortex. The human neuro-cortex has a multi-layer structure, while the conventional cortical learning algorithm has a single layer structure. This work introduces a double-layered structure into the cortical learning algorithm. The first layer represents the input data and its context every time-step. The input data context presentation in the first layer is transferred to the second layer, and it is represented in the second layer as an abstract representation. Also, the abstract prediction in the second layer is reflected to the first layer to modify and enhance the prediction in the first layer. The experimental results show that the proposed double-layered cortical learning algorithm achieves higher prediction accuracy than the conventional single-layered cortical learning algorithms and the recurrent neural networks with the long short-term memory on several artificial time-series data.
7 schema:editor N513641ced32c49b79b361b7c7c34e769
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf N5738762a2bcd405d89219215ff3b402f
12 schema:keywords Abstract Prediction
13 abstract representation
14 accuracy
15 algorithm
16 artificial time-series data
17 context
18 context presentation
19 conventional cortical learning algorithm
20 cortical learning algorithm
21 data
22 double-layered structure
23 experimental results
24 first layer
25 high prediction accuracy
26 input data
27 layer
28 layer structure
29 learning algorithm
30 long short-term memory
31 memory
32 methodology
33 multi-layer structure
34 network
35 neural network
36 prediction
37 prediction accuracy
38 prediction methodology
39 presentation
40 recurrent neural network
41 representation
42 results
43 second layer
44 short-term memory
45 single-layer structure
46 structure
47 time series data
48 time series prediction
49 work
50 schema:name Double-Layered Cortical Learning Algorithm for Time-Series Prediction
51 schema:pagination 33-44
52 schema:productId Ncd458d64ff014983b0ecf52f70b1a2fc
53 Nda581dc7b2a546eb8ae904c3592cee2d
54 schema:publisher Nba1612c7723f403e9f19b4af57510f99
55 schema:sameAs https://app.dimensions.ai/details/publication/pub.1143570240
56 https://doi.org/10.1007/978-3-030-92163-7_4
57 schema:sdDatePublished 2022-05-20T07:44
58 schema:sdLicense https://scigraph.springernature.com/explorer/license/
59 schema:sdPublisher N307567896b83423989f1ab3a10a91da2
60 schema:url https://doi.org/10.1007/978-3-030-92163-7_4
61 sgo:license sg:explorer/license/
62 sgo:sdDataset chapters
63 rdf:type schema:Chapter
64 N307567896b83423989f1ab3a10a91da2 schema:name Springer Nature - SN SciGraph project
65 rdf:type schema:Organization
66 N513641ced32c49b79b361b7c7c34e769 rdf:first Ncee6416deba94229bf9f1aae130f4bdf
67 rdf:rest rdf:nil
68 N5738762a2bcd405d89219215ff3b402f schema:isbn 978-3-030-92162-0
69 978-3-030-92163-7
70 schema:name Bio-Inspired Information and Communications Technologies
71 rdf:type schema:Book
72 Nb4dbe7bddb73470b99c9ab2edf9a7d89 rdf:first sg:person.015162262761.13
73 rdf:rest Ne84d8df5d30d44c7a096af2d3f213fce
74 Nba1612c7723f403e9f19b4af57510f99 schema:name Springer Nature
75 rdf:type schema:Organisation
76 Ncd458d64ff014983b0ecf52f70b1a2fc schema:name dimensions_id
77 schema:value pub.1143570240
78 rdf:type schema:PropertyValue
79 Ncee6416deba94229bf9f1aae130f4bdf schema:familyName Nakano
80 schema:givenName Tadashi
81 rdf:type schema:Person
82 Nda581dc7b2a546eb8ae904c3592cee2d schema:name doi
83 schema:value 10.1007/978-3-030-92163-7_4
84 rdf:type schema:PropertyValue
85 Ne437f75448814d988422cec55feae76d rdf:first sg:person.07750750604.05
86 rdf:rest rdf:nil
87 Ne84d8df5d30d44c7a096af2d3f213fce rdf:first sg:person.012774267611.99
88 rdf:rest Ne437f75448814d988422cec55feae76d
89 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
90 schema:name Information and Computing Sciences
91 rdf:type schema:DefinedTerm
92 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
93 schema:name Artificial Intelligence and Image Processing
94 rdf:type schema:DefinedTerm
95 sg:person.012774267611.99 schema:affiliation grid-institutes:grid.266298.1
96 schema:familyName Takadama
97 schema:givenName Keiki
98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012774267611.99
99 rdf:type schema:Person
100 sg:person.015162262761.13 schema:affiliation grid-institutes:grid.266298.1
101 schema:familyName Aoki
102 schema:givenName Takeru
103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015162262761.13
104 rdf:type schema:Person
105 sg:person.07750750604.05 schema:affiliation grid-institutes:grid.266298.1
106 schema:familyName Sato
107 schema:givenName Hiroyuki
108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07750750604.05
109 rdf:type schema:Person
110 grid-institutes:grid.266298.1 schema:alternateName The University of Electro-Communications, 1-5-1 Chofugaoka, 182-8585, Chofu, Tokyo, Japan
111 schema:name The University of Electro-Communications, 1-5-1 Chofugaoka, 182-8585, Chofu, Tokyo, Japan
112 rdf:type schema:Organization
 




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


...