Mapping symbolic knowledge into locally receptive field networks View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

1995

AUTHORS

Enrico Blanzieri , Attilio Giordana

ABSTRACT

This paper investigates Locally Receptive Field Networks, a broad class of neural networks including Probabilistic Neural Networks and Radial Basis Function Networks, which naturally exhibit symbolic properties. Moreover, specific attention is given to the sub-class of Factorizable Radial Basis Function Networks whose architecture can be directly translated into a prepositional theory and viceversa. Exploiting this characteristics, symbolic and numeric algorithms can be easely integrated for automating network synthesis. Several methods including classification and regression trees, and statistical clustering are evaluated on a classification task in a difficult medical domain. The obtained results show that the considered network class is able to achieve a high accuracy, while conserving a symbolic readability. More... »

PAGES

267-278

Book

TITLE

Topics in Artificial Intelligence

ISBN

978-3-540-60437-2
978-3-540-47468-5

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/3-540-60437-5_27

DOI

http://dx.doi.org/10.1007/3-540-60437-5_27

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1048575190


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/2008/0801", 
        "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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Turin", 
          "id": "https://www.grid.ac/institutes/grid.7605.4", 
          "name": [
            "Centro di Scienza Cognitiva, Universit\u00e0 di Torino, Via Lagrange 3, 10100\u00a0Torino, Italy"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Blanzieri", 
        "givenName": "Enrico", 
        "id": "sg:person.013033541655.32", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013033541655.32"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Turin", 
          "id": "https://www.grid.ac/institutes/grid.7605.4", 
          "name": [
            "Dipartimento di Informatica, Universit\u00e0 di Torino, C.so Svizzera 185, 10149\u00a0Torino, Italy"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Giordana", 
        "givenName": "Attilio", 
        "id": "sg:person.013711540444.49", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013711540444.49"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "1995", 
    "datePublishedReg": "1995-01-01", 
    "description": "This paper investigates Locally Receptive Field Networks, a broad class of neural networks including Probabilistic Neural Networks and Radial Basis Function Networks, which naturally exhibit symbolic properties. Moreover, specific attention is given to the sub-class of Factorizable Radial Basis Function Networks whose architecture can be directly translated into a prepositional theory and viceversa. Exploiting this characteristics, symbolic and numeric algorithms can be easely integrated for automating network synthesis. Several methods including classification and regression trees, and statistical clustering are evaluated on a classification task in a difficult medical domain. The obtained results show that the considered network class is able to achieve a high accuracy, while conserving a symbolic readability.", 
    "editor": [
      {
        "familyName": "Gori", 
        "givenName": "Marco", 
        "type": "Person"
      }, 
      {
        "familyName": "Soda", 
        "givenName": "Giovanni", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/3-540-60437-5_27", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-540-60437-2", 
        "978-3-540-47468-5"
      ], 
      "name": "Topics in Artificial Intelligence", 
      "type": "Book"
    }, 
    "name": "Mapping symbolic knowledge into locally receptive field networks", 
    "pagination": "267-278", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/3-540-60437-5_27"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "e767790ad8725724285f9c33a961a610cdc101d633a03016183d7cf069af40c5"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1048575190"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/3-540-60437-5_27", 
      "https://app.dimensions.ai/details/publication/pub.1048575190"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T15:10", 
    "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_8672_00000083.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/3-540-60437-5_27"
  }
]
 

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.10.1007/3-540-60437-5_27'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/3-540-60437-5_27'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/3-540-60437-5_27'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/3-540-60437-5_27'


 

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

78 TRIPLES      22 PREDICATES      27 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/3-540-60437-5_27 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nc05d4cb2e1044cf8adf49b7f5708582e
4 schema:datePublished 1995
5 schema:datePublishedReg 1995-01-01
6 schema:description This paper investigates Locally Receptive Field Networks, a broad class of neural networks including Probabilistic Neural Networks and Radial Basis Function Networks, which naturally exhibit symbolic properties. Moreover, specific attention is given to the sub-class of Factorizable Radial Basis Function Networks whose architecture can be directly translated into a prepositional theory and viceversa. Exploiting this characteristics, symbolic and numeric algorithms can be easely integrated for automating network synthesis. Several methods including classification and regression trees, and statistical clustering are evaluated on a classification task in a difficult medical domain. The obtained results show that the considered network class is able to achieve a high accuracy, while conserving a symbolic readability.
7 schema:editor N638d41c346504cb78d0150648c3c3833
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf N9a13ec22fa4640bd995ef7696a75fc3f
12 schema:name Mapping symbolic knowledge into locally receptive field networks
13 schema:pagination 267-278
14 schema:productId N0ebfb42ae9284e409266f3cfacf35f55
15 N22baef11a6a84d8180781c3758fe5a6d
16 Nb016815dd79744c484c8252dec3223a2
17 schema:publisher N256a7ff7d9cb44a08bc0c69ed9a2e382
18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048575190
19 https://doi.org/10.1007/3-540-60437-5_27
20 schema:sdDatePublished 2019-04-15T15:10
21 schema:sdLicense https://scigraph.springernature.com/explorer/license/
22 schema:sdPublisher Nb143cc679b8f476aa7860aef2dece31b
23 schema:url http://link.springer.com/10.1007/3-540-60437-5_27
24 sgo:license sg:explorer/license/
25 sgo:sdDataset chapters
26 rdf:type schema:Chapter
27 N0ebfb42ae9284e409266f3cfacf35f55 schema:name dimensions_id
28 schema:value pub.1048575190
29 rdf:type schema:PropertyValue
30 N16d216ef5a63426bae7b69d9ddf82d2b rdf:first sg:person.013711540444.49
31 rdf:rest rdf:nil
32 N22baef11a6a84d8180781c3758fe5a6d schema:name readcube_id
33 schema:value e767790ad8725724285f9c33a961a610cdc101d633a03016183d7cf069af40c5
34 rdf:type schema:PropertyValue
35 N256a7ff7d9cb44a08bc0c69ed9a2e382 schema:location Berlin, Heidelberg
36 schema:name Springer Berlin Heidelberg
37 rdf:type schema:Organisation
38 N50de0cb831fa46f4b01ee72cffd700ba schema:familyName Soda
39 schema:givenName Giovanni
40 rdf:type schema:Person
41 N638d41c346504cb78d0150648c3c3833 rdf:first Nba6f59a7def34d6587300ca713737c06
42 rdf:rest N9d7661c6abb044c2bef7f1d5bd5806ac
43 N9a13ec22fa4640bd995ef7696a75fc3f schema:isbn 978-3-540-47468-5
44 978-3-540-60437-2
45 schema:name Topics in Artificial Intelligence
46 rdf:type schema:Book
47 N9d7661c6abb044c2bef7f1d5bd5806ac rdf:first N50de0cb831fa46f4b01ee72cffd700ba
48 rdf:rest rdf:nil
49 Nb016815dd79744c484c8252dec3223a2 schema:name doi
50 schema:value 10.1007/3-540-60437-5_27
51 rdf:type schema:PropertyValue
52 Nb143cc679b8f476aa7860aef2dece31b schema:name Springer Nature - SN SciGraph project
53 rdf:type schema:Organization
54 Nba6f59a7def34d6587300ca713737c06 schema:familyName Gori
55 schema:givenName Marco
56 rdf:type schema:Person
57 Nc05d4cb2e1044cf8adf49b7f5708582e rdf:first sg:person.013033541655.32
58 rdf:rest N16d216ef5a63426bae7b69d9ddf82d2b
59 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
60 schema:name Information and Computing Sciences
61 rdf:type schema:DefinedTerm
62 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
63 schema:name Artificial Intelligence and Image Processing
64 rdf:type schema:DefinedTerm
65 sg:person.013033541655.32 schema:affiliation https://www.grid.ac/institutes/grid.7605.4
66 schema:familyName Blanzieri
67 schema:givenName Enrico
68 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013033541655.32
69 rdf:type schema:Person
70 sg:person.013711540444.49 schema:affiliation https://www.grid.ac/institutes/grid.7605.4
71 schema:familyName Giordana
72 schema:givenName Attilio
73 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013711540444.49
74 rdf:type schema:Person
75 https://www.grid.ac/institutes/grid.7605.4 schema:alternateName University of Turin
76 schema:name Centro di Scienza Cognitiva, Università di Torino, Via Lagrange 3, 10100 Torino, Italy
77 Dipartimento di Informatica, Università di Torino, C.so Svizzera 185, 10149 Torino, Italy
78 rdf:type schema:Organization
 




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


...