Meta-learning for Fast Incremental Learning View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2003-06-18

AUTHORS

Takayuki Oohira , Koichiro Yamauchi , Takashi Omori

ABSTRACT

Model based learning systems usually face to a problem of forgetting as a result of the incremental learning of new instances. Normally, the systems have to re-learn past instances to avoid this problem. However, the re-learning process wastes substantial learning time. To reduce learning time, we propose a novel incremental learning system, which consists of two neural networks: a main-learning module and a meta-learning module. The main-learning module approximates a continuous function between input and desired output value, while the meta-learning module predicts an appropriate change in parameters of the main-learning module for incremental learning. The meta-learning module acquires the learning strategy for modifying current parameters not only to adjust the main-learning module’s behavior for new instances but also to avoid forgetting past learned skills. More... »

PAGES

157-164

Book

TITLE

Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003

ISBN

978-3-540-40408-8
978-3-540-44989-8

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/3-540-44989-2_20

DOI

http://dx.doi.org/10.1007/3-540-44989-2_20

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1010032192


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": "Graduate School of Engineering, Hokkaido University, Kita ku, Kita 13 Jyou Nishi 8 Chou, 060-8628, Sapporo, Japan", 
          "id": "http://www.grid.ac/institutes/grid.39158.36", 
          "name": [
            "Graduate School of Engineering, Hokkaido University, Kita ku, Kita 13 Jyou Nishi 8 Chou, 060-8628, Sapporo, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Oohira", 
        "givenName": "Takayuki", 
        "id": "sg:person.011767412664.06", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011767412664.06"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Graduate School of Engineering, Hokkaido University, Kita ku, Kita 13 Jyou Nishi 8 Chou, 060-8628, Sapporo, Japan", 
          "id": "http://www.grid.ac/institutes/grid.39158.36", 
          "name": [
            "Graduate School of Engineering, Hokkaido University, Kita ku, Kita 13 Jyou Nishi 8 Chou, 060-8628, Sapporo, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Yamauchi", 
        "givenName": "Koichiro", 
        "id": "sg:person.07364502315.92", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07364502315.92"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Graduate School of Engineering, Hokkaido University, Kita ku, Kita 13 Jyou Nishi 8 Chou, 060-8628, Sapporo, Japan", 
          "id": "http://www.grid.ac/institutes/grid.39158.36", 
          "name": [
            "Graduate School of Engineering, Hokkaido University, Kita ku, Kita 13 Jyou Nishi 8 Chou, 060-8628, Sapporo, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Omori", 
        "givenName": "Takashi", 
        "id": "sg:person.01263557346.07", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01263557346.07"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2003-06-18", 
    "datePublishedReg": "2003-06-18", 
    "description": "Model based learning systems usually face to a problem of forgetting as a result of the incremental learning of new instances. Normally, the systems have to re-learn past instances to avoid this problem. However, the re-learning process wastes substantial learning time. To reduce learning time, we propose a novel incremental learning system, which consists of two neural networks: a main-learning module and a meta-learning module. The main-learning module approximates a continuous function between input and desired output value, while the meta-learning module predicts an appropriate change in parameters of the main-learning module for incremental learning. The meta-learning module acquires the learning strategy for modifying current parameters not only to adjust the main-learning module\u2019s behavior for new instances but also to avoid forgetting past learned skills.", 
    "editor": [
      {
        "familyName": "Kaynak", 
        "givenName": "Okyay", 
        "type": "Person"
      }, 
      {
        "familyName": "Alpaydin", 
        "givenName": "Ethem", 
        "type": "Person"
      }, 
      {
        "familyName": "Oja", 
        "givenName": "Erkki", 
        "type": "Person"
      }, 
      {
        "familyName": "Xu", 
        "givenName": "Lei", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/3-540-44989-2_20", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-40408-8", 
        "978-3-540-44989-8"
      ], 
      "name": "Artificial Neural Networks and Neural Information Processing \u2014 ICANN/ICONIP 2003", 
      "type": "Book"
    }, 
    "keywords": [
      "incremental learning", 
      "learning system", 
      "new instances", 
      "Fast Incremental Learning", 
      "incremental learning system", 
      "neural network", 
      "learning time", 
      "module behavior", 
      "re-learning process", 
      "module", 
      "learning strategies", 
      "past instances", 
      "learning", 
      "output values", 
      "instances", 
      "system", 
      "network", 
      "input", 
      "continuous functions", 
      "time", 
      "model", 
      "current parameters", 
      "parameters", 
      "appropriate changes", 
      "strategies", 
      "process", 
      "behavior", 
      "results", 
      "skills", 
      "function", 
      "values", 
      "changes", 
      "problem", 
      "re-learn past instances", 
      "substantial learning time", 
      "novel incremental learning system", 
      "main-learning module", 
      "meta-learning module", 
      "main-learning module\u2019s behavior"
    ], 
    "name": "Meta-learning for Fast Incremental Learning", 
    "pagination": "157-164", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1010032192"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/3-540-44989-2_20"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/3-540-44989-2_20", 
      "https://app.dimensions.ai/details/publication/pub.1010032192"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:21", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/chapter/chapter_363.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/3-540-44989-2_20"
  }
]
 

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.10.1007/3-540-44989-2_20'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/3-540-44989-2_20'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/3-540-44989-2_20'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/3-540-44989-2_20'


 

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

128 TRIPLES      23 PREDICATES      64 URIs      57 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/3-540-44989-2_20 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N852c672306034eff9614d1f9082089f7
4 schema:datePublished 2003-06-18
5 schema:datePublishedReg 2003-06-18
6 schema:description Model based learning systems usually face to a problem of forgetting as a result of the incremental learning of new instances. Normally, the systems have to re-learn past instances to avoid this problem. However, the re-learning process wastes substantial learning time. To reduce learning time, we propose a novel incremental learning system, which consists of two neural networks: a main-learning module and a meta-learning module. The main-learning module approximates a continuous function between input and desired output value, while the meta-learning module predicts an appropriate change in parameters of the main-learning module for incremental learning. The meta-learning module acquires the learning strategy for modifying current parameters not only to adjust the main-learning module’s behavior for new instances but also to avoid forgetting past learned skills.
7 schema:editor Nffdbb06d8703413c97a55e0d84c725be
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf N290f614245db4e5d971be1111b9fc79c
12 schema:keywords Fast Incremental Learning
13 appropriate changes
14 behavior
15 changes
16 continuous functions
17 current parameters
18 function
19 incremental learning
20 incremental learning system
21 input
22 instances
23 learning
24 learning strategies
25 learning system
26 learning time
27 main-learning module
28 main-learning module’s behavior
29 meta-learning module
30 model
31 module
32 module behavior
33 network
34 neural network
35 new instances
36 novel incremental learning system
37 output values
38 parameters
39 past instances
40 problem
41 process
42 re-learn past instances
43 re-learning process
44 results
45 skills
46 strategies
47 substantial learning time
48 system
49 time
50 values
51 schema:name Meta-learning for Fast Incremental Learning
52 schema:pagination 157-164
53 schema:productId N40058764fdc04dcda5bb2ce78c92cb01
54 N7e251e8e427a4694a04030c8f62586f3
55 schema:publisher Nb0ee56e1f8f94978a6dc95861ba7d4c8
56 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010032192
57 https://doi.org/10.1007/3-540-44989-2_20
58 schema:sdDatePublished 2022-01-01T19:21
59 schema:sdLicense https://scigraph.springernature.com/explorer/license/
60 schema:sdPublisher N436ad5796c8d4f3e95f51fa74102905e
61 schema:url https://doi.org/10.1007/3-540-44989-2_20
62 sgo:license sg:explorer/license/
63 sgo:sdDataset chapters
64 rdf:type schema:Chapter
65 N143acc2f9dad41218fa5d5ecb6fb8e05 schema:familyName Xu
66 schema:givenName Lei
67 rdf:type schema:Person
68 N1bee7d354eca4552a3c4ecb50dd6e4ae rdf:first N45fdcc1a49b94c3596bcae4b1a093b41
69 rdf:rest N71a1c624928241a9864834d5874924c3
70 N290f614245db4e5d971be1111b9fc79c schema:isbn 978-3-540-40408-8
71 978-3-540-44989-8
72 schema:name Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003
73 rdf:type schema:Book
74 N2f394d44bea543229e39f258af83a5b1 rdf:first sg:person.07364502315.92
75 rdf:rest N35c4b47254fd48c9b9e8725e2d757dd6
76 N33a8970e778649f69df34d7c7443994b rdf:first N143acc2f9dad41218fa5d5ecb6fb8e05
77 rdf:rest rdf:nil
78 N35c4b47254fd48c9b9e8725e2d757dd6 rdf:first sg:person.01263557346.07
79 rdf:rest rdf:nil
80 N40058764fdc04dcda5bb2ce78c92cb01 schema:name doi
81 schema:value 10.1007/3-540-44989-2_20
82 rdf:type schema:PropertyValue
83 N436ad5796c8d4f3e95f51fa74102905e schema:name Springer Nature - SN SciGraph project
84 rdf:type schema:Organization
85 N45fdcc1a49b94c3596bcae4b1a093b41 schema:familyName Alpaydin
86 schema:givenName Ethem
87 rdf:type schema:Person
88 N71a1c624928241a9864834d5874924c3 rdf:first Na10b903788e24c11981da2b517925636
89 rdf:rest N33a8970e778649f69df34d7c7443994b
90 N7e251e8e427a4694a04030c8f62586f3 schema:name dimensions_id
91 schema:value pub.1010032192
92 rdf:type schema:PropertyValue
93 N852c672306034eff9614d1f9082089f7 rdf:first sg:person.011767412664.06
94 rdf:rest N2f394d44bea543229e39f258af83a5b1
95 Na10b903788e24c11981da2b517925636 schema:familyName Oja
96 schema:givenName Erkki
97 rdf:type schema:Person
98 Nb0ee56e1f8f94978a6dc95861ba7d4c8 schema:name Springer Nature
99 rdf:type schema:Organisation
100 Nb7191e97a9ff4799a149dfcf4eded701 schema:familyName Kaynak
101 schema:givenName Okyay
102 rdf:type schema:Person
103 Nffdbb06d8703413c97a55e0d84c725be rdf:first Nb7191e97a9ff4799a149dfcf4eded701
104 rdf:rest N1bee7d354eca4552a3c4ecb50dd6e4ae
105 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
106 schema:name Information and Computing Sciences
107 rdf:type schema:DefinedTerm
108 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
109 schema:name Artificial Intelligence and Image Processing
110 rdf:type schema:DefinedTerm
111 sg:person.011767412664.06 schema:affiliation grid-institutes:grid.39158.36
112 schema:familyName Oohira
113 schema:givenName Takayuki
114 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011767412664.06
115 rdf:type schema:Person
116 sg:person.01263557346.07 schema:affiliation grid-institutes:grid.39158.36
117 schema:familyName Omori
118 schema:givenName Takashi
119 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01263557346.07
120 rdf:type schema:Person
121 sg:person.07364502315.92 schema:affiliation grid-institutes:grid.39158.36
122 schema:familyName Yamauchi
123 schema:givenName Koichiro
124 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07364502315.92
125 rdf:type schema:Person
126 grid-institutes:grid.39158.36 schema:alternateName Graduate School of Engineering, Hokkaido University, Kita ku, Kita 13 Jyou Nishi 8 Chou, 060-8628, Sapporo, Japan
127 schema:name Graduate School of Engineering, Hokkaido University, Kita ku, Kita 13 Jyou Nishi 8 Chou, 060-8628, Sapporo, Japan
128 rdf:type schema:Organization
 




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


...