Knowledge Reusing Neural Learning System for Immediate Adaptation in Navigation Tasks View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2004

AUTHORS

Akitoshi Ogawa , Takashi Omori

ABSTRACT

A characteristic feature of conventional intelligent agents is the amount of trials that are required for them to learn. Since the tasks they encounter change depending on the environment, it is difficult for a learning system to compress the learning time using a priori knowledge. In the real world, however, agents confront a whole range of new tasks one by one, and have to solve them one by one without consuming learning time. A serious problem for the real-world agent is the amount of learning time needed. We suppose that one reason for a long learning time is the nonuse of prior knowledge. It is natural to expect that a kind of fast adaptation to tasks would be possible when we reuse knowledge that is acquired from similar past experiences. For this problem, we propose a neural-network based learning system that can immediately or quickly solve new tasks by reusing knowledge already acquired. We adopt a navigation task as an example and show the effectiveness of our method in variations on the task by comparing its performance with other methods. More... »

PAGES

409-415

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-540-30499-9_62

DOI

http://dx.doi.org/10.1007/978-3-540-30499-9_62

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1000979818


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/2008/17", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology and Cognitive 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"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1701", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Graduate School of Information Science and Technology, Hokkaido University, Kita 14 Nishi 9, Sapporo, Japan", 
          "id": "http://www.grid.ac/institutes/grid.39158.36", 
          "name": [
            "Graduate School of Information Science and Technology, Hokkaido University, Kita 14 Nishi 9, Sapporo, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ogawa", 
        "givenName": "Akitoshi", 
        "id": "sg:person.016531377655.12", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016531377655.12"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Graduate School of Information Science and Technology, Hokkaido University, Kita 14 Nishi 9, Sapporo, Japan", 
          "id": "http://www.grid.ac/institutes/grid.39158.36", 
          "name": [
            "Graduate School of Information Science and Technology, Hokkaido University, Kita 14 Nishi 9, 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": "2004", 
    "datePublishedReg": "2004-01-01", 
    "description": "A characteristic feature of conventional intelligent agents is the amount of trials that are required for them to learn. Since the tasks they encounter change depending on the environment, it is difficult for a learning system to compress the learning time using a priori knowledge. In the real world, however, agents confront a whole range of new tasks one by one, and have to solve them one by one without consuming learning time. A serious problem for the real-world agent is the amount of learning time needed. We suppose that one reason for a long learning time is the nonuse of prior knowledge. It is natural to expect that a kind of fast adaptation to tasks would be possible when we reuse knowledge that is acquired from similar past experiences. For this problem, we propose a neural-network based learning system that can immediately or quickly solve new tasks by reusing knowledge already acquired. We adopt a navigation task as an example and show the effectiveness of our method in variations on the task by comparing its performance with other methods.", 
    "editor": [
      {
        "familyName": "Pal", 
        "givenName": "Nikhil Ranjan", 
        "type": "Person"
      }, 
      {
        "familyName": "Kasabov", 
        "givenName": "Nik", 
        "type": "Person"
      }, 
      {
        "familyName": "Mudi", 
        "givenName": "Rajani K.", 
        "type": "Person"
      }, 
      {
        "familyName": "Pal", 
        "givenName": "Srimanta", 
        "type": "Person"
      }, 
      {
        "familyName": "Parui", 
        "givenName": "Swapan Kumar", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-540-30499-9_62", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-23931-4", 
        "978-3-540-30499-9"
      ], 
      "name": "Neural Information Processing", 
      "type": "Book"
    }, 
    "keywords": [
      "learning system", 
      "learning time", 
      "navigation task", 
      "long learning time", 
      "neural learning systems", 
      "real-world agents", 
      "intelligent agents", 
      "amount of trial", 
      "real world", 
      "new tasks", 
      "similar past experiences", 
      "prior knowledge", 
      "task", 
      "task one", 
      "fast adaptation", 
      "system", 
      "past experience", 
      "immediate adaptation", 
      "knowledge", 
      "serious problem", 
      "environment", 
      "method", 
      "performance", 
      "effectiveness", 
      "time", 
      "features", 
      "adaptation", 
      "kind", 
      "example", 
      "amount", 
      "world", 
      "agents", 
      "one", 
      "experience", 
      "reasons", 
      "characteristic features", 
      "whole range", 
      "problem", 
      "nonuse", 
      "range", 
      "trials", 
      "variation", 
      "changes"
    ], 
    "name": "Knowledge Reusing Neural Learning System for Immediate Adaptation in Navigation Tasks", 
    "pagination": "409-415", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1000979818"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-540-30499-9_62"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-540-30499-9_62", 
      "https://app.dimensions.ai/details/publication/pub.1000979818"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-05-20T07:42", 
    "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_168.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-540-30499-9_62"
  }
]
 

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.10.1007/978-3-540-30499-9_62'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-30499-9_62'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-30499-9_62'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-30499-9_62'


 

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

138 TRIPLES      23 PREDICATES      71 URIs      62 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-540-30499-9_62 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 anzsrc-for:17
4 anzsrc-for:1701
5 schema:author Ncc03896893584854a19c3c26244e0349
6 schema:datePublished 2004
7 schema:datePublishedReg 2004-01-01
8 schema:description A characteristic feature of conventional intelligent agents is the amount of trials that are required for them to learn. Since the tasks they encounter change depending on the environment, it is difficult for a learning system to compress the learning time using a priori knowledge. In the real world, however, agents confront a whole range of new tasks one by one, and have to solve them one by one without consuming learning time. A serious problem for the real-world agent is the amount of learning time needed. We suppose that one reason for a long learning time is the nonuse of prior knowledge. It is natural to expect that a kind of fast adaptation to tasks would be possible when we reuse knowledge that is acquired from similar past experiences. For this problem, we propose a neural-network based learning system that can immediately or quickly solve new tasks by reusing knowledge already acquired. We adopt a navigation task as an example and show the effectiveness of our method in variations on the task by comparing its performance with other methods.
9 schema:editor N7a727a4440554aa99df825e97fdda267
10 schema:genre chapter
11 schema:inLanguage en
12 schema:isAccessibleForFree false
13 schema:isPartOf N7d3f666453164228836b0467686d468f
14 schema:keywords adaptation
15 agents
16 amount
17 amount of trial
18 changes
19 characteristic features
20 effectiveness
21 environment
22 example
23 experience
24 fast adaptation
25 features
26 immediate adaptation
27 intelligent agents
28 kind
29 knowledge
30 learning system
31 learning time
32 long learning time
33 method
34 navigation task
35 neural learning systems
36 new tasks
37 nonuse
38 one
39 past experience
40 performance
41 prior knowledge
42 problem
43 range
44 real world
45 real-world agents
46 reasons
47 serious problem
48 similar past experiences
49 system
50 task
51 task one
52 time
53 trials
54 variation
55 whole range
56 world
57 schema:name Knowledge Reusing Neural Learning System for Immediate Adaptation in Navigation Tasks
58 schema:pagination 409-415
59 schema:productId N23b9161c9f6d44a997aa4f89b242e5d4
60 N4c38edd66e764fb7a44739b891f0f21e
61 schema:publisher N9069dcc085614e36ba1fcfd8f0028030
62 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000979818
63 https://doi.org/10.1007/978-3-540-30499-9_62
64 schema:sdDatePublished 2022-05-20T07:42
65 schema:sdLicense https://scigraph.springernature.com/explorer/license/
66 schema:sdPublisher N8847b47b7d2e49f294959a6b1b5046d0
67 schema:url https://doi.org/10.1007/978-3-540-30499-9_62
68 sgo:license sg:explorer/license/
69 sgo:sdDataset chapters
70 rdf:type schema:Chapter
71 N23b9161c9f6d44a997aa4f89b242e5d4 schema:name doi
72 schema:value 10.1007/978-3-540-30499-9_62
73 rdf:type schema:PropertyValue
74 N3f23010c8a584b7e83263faca89ec3e9 schema:familyName Mudi
75 schema:givenName Rajani K.
76 rdf:type schema:Person
77 N4c38edd66e764fb7a44739b891f0f21e schema:name dimensions_id
78 schema:value pub.1000979818
79 rdf:type schema:PropertyValue
80 N585ffcfe03fa4d7ba6a8e381552745e6 rdf:first Na13bd3e329434fed9080b375c543f634
81 rdf:rest Ne311a827e6714f858aea0807456eaf5f
82 N652aaf8d393f4a69afddf4cbd1d231db schema:familyName Pal
83 schema:givenName Nikhil Ranjan
84 rdf:type schema:Person
85 N67adc37e3c1041669bd25a605e9eb29b rdf:first Nf347379c280340bc883fd227ea76159e
86 rdf:rest Nb5b6bcf474db47dfa884b04394cdc08d
87 N7a727a4440554aa99df825e97fdda267 rdf:first N652aaf8d393f4a69afddf4cbd1d231db
88 rdf:rest N585ffcfe03fa4d7ba6a8e381552745e6
89 N7d3f666453164228836b0467686d468f schema:isbn 978-3-540-23931-4
90 978-3-540-30499-9
91 schema:name Neural Information Processing
92 rdf:type schema:Book
93 N8847b47b7d2e49f294959a6b1b5046d0 schema:name Springer Nature - SN SciGraph project
94 rdf:type schema:Organization
95 N8f37802999754939a5db045d0bff61ec rdf:first sg:person.01263557346.07
96 rdf:rest rdf:nil
97 N9069dcc085614e36ba1fcfd8f0028030 schema:name Springer Nature
98 rdf:type schema:Organisation
99 Na13bd3e329434fed9080b375c543f634 schema:familyName Kasabov
100 schema:givenName Nik
101 rdf:type schema:Person
102 Nb5b6bcf474db47dfa884b04394cdc08d rdf:first Ne1539b96da4e41d38d470d4fa66704f7
103 rdf:rest rdf:nil
104 Ncc03896893584854a19c3c26244e0349 rdf:first sg:person.016531377655.12
105 rdf:rest N8f37802999754939a5db045d0bff61ec
106 Ne1539b96da4e41d38d470d4fa66704f7 schema:familyName Parui
107 schema:givenName Swapan Kumar
108 rdf:type schema:Person
109 Ne311a827e6714f858aea0807456eaf5f rdf:first N3f23010c8a584b7e83263faca89ec3e9
110 rdf:rest N67adc37e3c1041669bd25a605e9eb29b
111 Nf347379c280340bc883fd227ea76159e schema:familyName Pal
112 schema:givenName Srimanta
113 rdf:type schema:Person
114 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
115 schema:name Information and Computing Sciences
116 rdf:type schema:DefinedTerm
117 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
118 schema:name Artificial Intelligence and Image Processing
119 rdf:type schema:DefinedTerm
120 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
121 schema:name Psychology and Cognitive Sciences
122 rdf:type schema:DefinedTerm
123 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
124 schema:name Psychology
125 rdf:type schema:DefinedTerm
126 sg:person.01263557346.07 schema:affiliation grid-institutes:grid.39158.36
127 schema:familyName Omori
128 schema:givenName Takashi
129 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01263557346.07
130 rdf:type schema:Person
131 sg:person.016531377655.12 schema:affiliation grid-institutes:grid.39158.36
132 schema:familyName Ogawa
133 schema:givenName Akitoshi
134 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016531377655.12
135 rdf:type schema:Person
136 grid-institutes:grid.39158.36 schema:alternateName Graduate School of Information Science and Technology, Hokkaido University, Kita 14 Nishi 9, Sapporo, Japan
137 schema:name Graduate School of Information Science and Technology, Hokkaido University, Kita 14 Nishi 9, Sapporo, Japan
138 rdf:type schema:Organization
 




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


...