Continuity of Approximation by Neural Networks in Lp Spaces View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2001-01

AUTHORS

Paul C. Kainen, Věra Kůrková, Andrew Vogt

ABSTRACT

Devices such as neural networks typically approximate the elements of some function space X by elements of a nontrivial finite union M of finite-dimensional spaces. It is shown that if X=Lp(Ω) (1‖f−M‖+Γ for some f in X. Thus, no continuous finite neural network approximation can be within any positive constant of a best approximation in the Lp-norm. More... »

PAGES

143-147

Identifiers

URI

http://scigraph.springernature.com/pub.10.1023/a:1010916406274

DOI

http://dx.doi.org/10.1023/a:1010916406274

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1028487750


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/2008/0103", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Numerical and Computational Mathematics", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Georgetown University", 
          "id": "https://www.grid.ac/institutes/grid.213910.8", 
          "name": [
            "Department of Mathematics, Georgetown University, 20057, Washington, DC, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kainen", 
        "givenName": "Paul C.", 
        "id": "sg:person.013607306243.38", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013607306243.38"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Institute of Computer Science", 
          "id": "https://www.grid.ac/institutes/grid.448092.3", 
          "name": [
            "Institute of Computer Science, Academy of Sciences of the Czech Republic, P.O. Box 5, 182 07 Prague 8, Czech Republic"
          ], 
          "type": "Organization"
        }, 
        "familyName": "K\u016frkov\u00e1", 
        "givenName": "V\u011bra", 
        "id": "sg:person.0627676237.51", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0627676237.51"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Georgetown University", 
          "id": "https://www.grid.ac/institutes/grid.213910.8", 
          "name": [
            "Department of Mathematics, Georgetown University, 20057, Washington, DC, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Vogt", 
        "givenName": "Andrew", 
        "id": "sg:person.011266447107.50", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011266447107.50"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1006/jath.2000.3467", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010569842"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0925-2312(99)00111-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025764884"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf01171759", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036571198", 
          "https://doi.org/10.1007/bf01171759"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf01171759", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036571198", 
          "https://doi.org/10.1007/bf01171759"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1006/jath.1996.3018", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045342432"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2001-01", 
    "datePublishedReg": "2001-01-01", 
    "description": "Devices such as neural networks typically approximate the elements of some function space X by elements of a nontrivial finite union M of finite-dimensional spaces. It is shown that if X=Lp(\u03a9) (1\u2016f\u2212M\u2016+\u0393 for some f in X. Thus, no continuous finite neural network approximation can be within any positive constant of a best approximation in the Lp-norm.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1023/a:1010916406274", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1048429", 
        "issn": [
          "0254-5330", 
          "1572-9338"
        ], 
        "name": "Annals of Operations Research", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1-4", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "101"
      }
    ], 
    "name": "Continuity of Approximation by Neural Networks in Lp Spaces", 
    "pagination": "143-147", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "87b535c379551373ae6d30be245d8474e336fab34fbaade9956b2a0e641c9f29"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1023/a:1010916406274"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1028487750"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1023/a:1010916406274", 
      "https://app.dimensions.ai/details/publication/pub.1028487750"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-10T20:44", 
    "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_8684_00000500.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1023/A:1010916406274"
  }
]
 

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.10.1023/a:1010916406274'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1023/a:1010916406274'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1023/a:1010916406274'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1023/a:1010916406274'


 

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

91 TRIPLES      21 PREDICATES      31 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1023/a:1010916406274 schema:about anzsrc-for:01
2 anzsrc-for:0103
3 schema:author N0ff8439b7e414c4c8a960a6cde8eaf0d
4 schema:citation sg:pub.10.1007/bf01171759
5 https://doi.org/10.1006/jath.1996.3018
6 https://doi.org/10.1006/jath.2000.3467
7 https://doi.org/10.1016/s0925-2312(99)00111-3
8 schema:datePublished 2001-01
9 schema:datePublishedReg 2001-01-01
10 schema:description Devices such as neural networks typically approximate the elements of some function space X by elements of a nontrivial finite union M of finite-dimensional spaces. It is shown that if X=Lp(Ω) (1<p<∞ and Ω⊂Rd), then for any positive constant Γ and any continuous function φ from X to M, ‖f−φ(f)‖>‖f−M‖+Γ for some f in X. Thus, no continuous finite neural network approximation can be within any positive constant of a best approximation in the Lp-norm.
11 schema:genre research_article
12 schema:inLanguage en
13 schema:isAccessibleForFree false
14 schema:isPartOf N04bc908e79c240b7beb25dc897652669
15 Ncdb5e43d6ec84ba98915bb4a6f517fe4
16 sg:journal.1048429
17 schema:name Continuity of Approximation by Neural Networks in Lp Spaces
18 schema:pagination 143-147
19 schema:productId N0e9e22a95c33465f9c7e2caf48ec1592
20 N814899269552420cb9ed364f87ed8cc9
21 Nb41036eee7d04b5fb406b6de46b9b7be
22 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028487750
23 https://doi.org/10.1023/a:1010916406274
24 schema:sdDatePublished 2019-04-10T20:44
25 schema:sdLicense https://scigraph.springernature.com/explorer/license/
26 schema:sdPublisher N83038af054f9435ebbd3f3c9e84444a4
27 schema:url http://link.springer.com/10.1023/A:1010916406274
28 sgo:license sg:explorer/license/
29 sgo:sdDataset articles
30 rdf:type schema:ScholarlyArticle
31 N04bc908e79c240b7beb25dc897652669 schema:volumeNumber 101
32 rdf:type schema:PublicationVolume
33 N0e9e22a95c33465f9c7e2caf48ec1592 schema:name dimensions_id
34 schema:value pub.1028487750
35 rdf:type schema:PropertyValue
36 N0ff8439b7e414c4c8a960a6cde8eaf0d rdf:first sg:person.013607306243.38
37 rdf:rest Ndf9e3a1773a7475191c8619bc70ef727
38 N814899269552420cb9ed364f87ed8cc9 schema:name doi
39 schema:value 10.1023/a:1010916406274
40 rdf:type schema:PropertyValue
41 N83038af054f9435ebbd3f3c9e84444a4 schema:name Springer Nature - SN SciGraph project
42 rdf:type schema:Organization
43 Nad124f19c9344f25ad356997668f299d rdf:first sg:person.011266447107.50
44 rdf:rest rdf:nil
45 Nb41036eee7d04b5fb406b6de46b9b7be schema:name readcube_id
46 schema:value 87b535c379551373ae6d30be245d8474e336fab34fbaade9956b2a0e641c9f29
47 rdf:type schema:PropertyValue
48 Ncdb5e43d6ec84ba98915bb4a6f517fe4 schema:issueNumber 1-4
49 rdf:type schema:PublicationIssue
50 Ndf9e3a1773a7475191c8619bc70ef727 rdf:first sg:person.0627676237.51
51 rdf:rest Nad124f19c9344f25ad356997668f299d
52 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
53 schema:name Mathematical Sciences
54 rdf:type schema:DefinedTerm
55 anzsrc-for:0103 schema:inDefinedTermSet anzsrc-for:
56 schema:name Numerical and Computational Mathematics
57 rdf:type schema:DefinedTerm
58 sg:journal.1048429 schema:issn 0254-5330
59 1572-9338
60 schema:name Annals of Operations Research
61 rdf:type schema:Periodical
62 sg:person.011266447107.50 schema:affiliation https://www.grid.ac/institutes/grid.213910.8
63 schema:familyName Vogt
64 schema:givenName Andrew
65 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011266447107.50
66 rdf:type schema:Person
67 sg:person.013607306243.38 schema:affiliation https://www.grid.ac/institutes/grid.213910.8
68 schema:familyName Kainen
69 schema:givenName Paul C.
70 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013607306243.38
71 rdf:type schema:Person
72 sg:person.0627676237.51 schema:affiliation https://www.grid.ac/institutes/grid.448092.3
73 schema:familyName Kůrková
74 schema:givenName Věra
75 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0627676237.51
76 rdf:type schema:Person
77 sg:pub.10.1007/bf01171759 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036571198
78 https://doi.org/10.1007/bf01171759
79 rdf:type schema:CreativeWork
80 https://doi.org/10.1006/jath.1996.3018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045342432
81 rdf:type schema:CreativeWork
82 https://doi.org/10.1006/jath.2000.3467 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010569842
83 rdf:type schema:CreativeWork
84 https://doi.org/10.1016/s0925-2312(99)00111-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025764884
85 rdf:type schema:CreativeWork
86 https://www.grid.ac/institutes/grid.213910.8 schema:alternateName Georgetown University
87 schema:name Department of Mathematics, Georgetown University, 20057, Washington, DC, USA
88 rdf:type schema:Organization
89 https://www.grid.ac/institutes/grid.448092.3 schema:alternateName Institute of Computer Science
90 schema:name Institute of Computer Science, Academy of Sciences of the Czech Republic, P.O. Box 5, 182 07 Prague 8, Czech Republic
91 rdf:type schema:Organization
 




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


...