Using plausible explanations to bias empirical generalization in weak theory domains View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

1991

AUTHORS

Gerhard Widmer

ABSTRACT

The paper argues for the usefulness of plausible explanations not just for analytical learning, but also for empirical generalization. The larger context is an implemented system that learns complex rules (for a musical task) on the basis of a qualitative theory of the domain. It learns by generalizing and compiling plausible explanations, but it can also incrementally modify learned rules in reaction to new evidence. The paper shows how this incremental modification (generalization) becomes more effective if it is based on an analysis of the explanations underlying learned rules; these explanations support a notion of ‘deep’ similarity and can provide substantial bias on the empirical modification of concepts. Several criteria that implement this bias are described, and an extended example illustrates how they lead to intelligent generalization behaviour. More... »

PAGES

33-43

References to SciGraph publications

Book

TITLE

Machine Learning — EWSL-91

ISBN

3-540-53816-X

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/bfb0017002

DOI

http://dx.doi.org/10.1007/bfb0017002

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1052478803


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/2008/1701", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology", 
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Vienna", 
          "id": "https://www.grid.ac/institutes/grid.10420.37", 
          "name": [
            "Department of Medical Cybernetics and Artificial Intelligence, University of Vienna, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Widmer", 
        "givenName": "Gerhard", 
        "id": "sg:person.013641401431.40", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013641401431.40"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1207/s15516709cog1301_1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1008863907"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1207/s15516709cog1301_1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1008863907"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/b978-1-55860-036-2.50008-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014588921"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00116250", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017707493", 
          "https://doi.org/10.1007/bf00116250"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00116250", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017707493", 
          "https://doi.org/10.1007/bf00116250"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/b978-1-55860-036-2.50014-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042007591"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/b978-1-55860-036-2.50007-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050302423"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1991", 
    "datePublishedReg": "1991-01-01", 
    "description": "The paper argues for the usefulness of plausible explanations not just for analytical learning, but also for empirical generalization. The larger context is an implemented system that learns complex rules (for a musical task) on the basis of a qualitative theory of the domain. It learns by generalizing and compiling plausible explanations, but it can also incrementally modify learned rules in reaction to new evidence. The paper shows how this incremental modification (generalization) becomes more effective if it is based on an analysis of the explanations underlying learned rules; these explanations support a notion of \u2018deep\u2019 similarity and can provide substantial bias on the empirical modification of concepts. Several criteria that implement this bias are described, and an extended example illustrates how they lead to intelligent generalization behaviour.", 
    "editor": [
      {
        "familyName": "Kodratoff", 
        "givenName": "Yves", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/bfb0017002", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "3-540-53816-X"
      ], 
      "name": "Machine Learning \u2014 EWSL-91", 
      "type": "Book"
    }, 
    "name": "Using plausible explanations to bias empirical generalization in weak theory domains", 
    "pagination": "33-43", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/bfb0017002"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "f9f97870e651a10ed0ad0e073fc66325326b6dfe5ca11712ebf364ddf7b9e03e"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1052478803"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin/Heidelberg", 
      "name": "Springer-Verlag", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/bfb0017002", 
      "https://app.dimensions.ai/details/publication/pub.1052478803"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T23:42", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8697_00000090.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/BFb0017002"
  }
]
 

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/bfb0017002'

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/bfb0017002'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/bfb0017002'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/bfb0017002'


 

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

80 TRIPLES      23 PREDICATES      32 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/bfb0017002 schema:about anzsrc-for:17
2 anzsrc-for:1701
3 schema:author N7bfd99b3533c4f9792fcd86a1578b3a7
4 schema:citation sg:pub.10.1007/bf00116250
5 https://doi.org/10.1016/b978-1-55860-036-2.50007-2
6 https://doi.org/10.1016/b978-1-55860-036-2.50008-4
7 https://doi.org/10.1016/b978-1-55860-036-2.50014-x
8 https://doi.org/10.1207/s15516709cog1301_1
9 schema:datePublished 1991
10 schema:datePublishedReg 1991-01-01
11 schema:description The paper argues for the usefulness of plausible explanations not just for analytical learning, but also for empirical generalization. The larger context is an implemented system that learns complex rules (for a musical task) on the basis of a qualitative theory of the domain. It learns by generalizing and compiling plausible explanations, but it can also incrementally modify learned rules in reaction to new evidence. The paper shows how this incremental modification (generalization) becomes more effective if it is based on an analysis of the explanations underlying learned rules; these explanations support a notion of ‘deep’ similarity and can provide substantial bias on the empirical modification of concepts. Several criteria that implement this bias are described, and an extended example illustrates how they lead to intelligent generalization behaviour.
12 schema:editor N4f7c65a86aa94f3b9480dc606ffb06c4
13 schema:genre chapter
14 schema:inLanguage en
15 schema:isAccessibleForFree false
16 schema:isPartOf Nc0dab18aa879422bb719f9275bf417d8
17 schema:name Using plausible explanations to bias empirical generalization in weak theory domains
18 schema:pagination 33-43
19 schema:productId N0636d74c281e48498de62f25a229fe9b
20 N348dfe76abec4971a121e4813b2b0c84
21 Nf10879c05c4c4a4bab71fa89b12a7b0c
22 schema:publisher Ndfda23fe3591448e91e3e808c50b5a5b
23 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052478803
24 https://doi.org/10.1007/bfb0017002
25 schema:sdDatePublished 2019-04-15T23:42
26 schema:sdLicense https://scigraph.springernature.com/explorer/license/
27 schema:sdPublisher N774830b7feb04c64a4999b6556cbac92
28 schema:url http://link.springer.com/10.1007/BFb0017002
29 sgo:license sg:explorer/license/
30 sgo:sdDataset chapters
31 rdf:type schema:Chapter
32 N0636d74c281e48498de62f25a229fe9b schema:name doi
33 schema:value 10.1007/bfb0017002
34 rdf:type schema:PropertyValue
35 N348dfe76abec4971a121e4813b2b0c84 schema:name dimensions_id
36 schema:value pub.1052478803
37 rdf:type schema:PropertyValue
38 N4f7c65a86aa94f3b9480dc606ffb06c4 rdf:first N94b339786e32428683519f51a6077f60
39 rdf:rest rdf:nil
40 N774830b7feb04c64a4999b6556cbac92 schema:name Springer Nature - SN SciGraph project
41 rdf:type schema:Organization
42 N7bfd99b3533c4f9792fcd86a1578b3a7 rdf:first sg:person.013641401431.40
43 rdf:rest rdf:nil
44 N94b339786e32428683519f51a6077f60 schema:familyName Kodratoff
45 schema:givenName Yves
46 rdf:type schema:Person
47 Nc0dab18aa879422bb719f9275bf417d8 schema:isbn 3-540-53816-X
48 schema:name Machine Learning — EWSL-91
49 rdf:type schema:Book
50 Ndfda23fe3591448e91e3e808c50b5a5b schema:location Berlin/Heidelberg
51 schema:name Springer-Verlag
52 rdf:type schema:Organisation
53 Nf10879c05c4c4a4bab71fa89b12a7b0c schema:name readcube_id
54 schema:value f9f97870e651a10ed0ad0e073fc66325326b6dfe5ca11712ebf364ddf7b9e03e
55 rdf:type schema:PropertyValue
56 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
57 schema:name Psychology and Cognitive Sciences
58 rdf:type schema:DefinedTerm
59 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
60 schema:name Psychology
61 rdf:type schema:DefinedTerm
62 sg:person.013641401431.40 schema:affiliation https://www.grid.ac/institutes/grid.10420.37
63 schema:familyName Widmer
64 schema:givenName Gerhard
65 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013641401431.40
66 rdf:type schema:Person
67 sg:pub.10.1007/bf00116250 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017707493
68 https://doi.org/10.1007/bf00116250
69 rdf:type schema:CreativeWork
70 https://doi.org/10.1016/b978-1-55860-036-2.50007-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050302423
71 rdf:type schema:CreativeWork
72 https://doi.org/10.1016/b978-1-55860-036-2.50008-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014588921
73 rdf:type schema:CreativeWork
74 https://doi.org/10.1016/b978-1-55860-036-2.50014-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1042007591
75 rdf:type schema:CreativeWork
76 https://doi.org/10.1207/s15516709cog1301_1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008863907
77 rdf:type schema:CreativeWork
78 https://www.grid.ac/institutes/grid.10420.37 schema:alternateName University of Vienna
79 schema:name Department of Medical Cybernetics and Artificial Intelligence, University of Vienna, Austria
80 rdf:type schema:Organization
 




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


...