Approximation by superpositions of a sigmoidal function View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

1989-12

AUTHORS

G. Cybenko

ABSTRACT

In this paper we demonstrate that finite linear combinations of compositions of a fixed, univariate function and a set of affine functionals can uniformly approximate any continuous function ofn real variables with support in the unit hypercube; only mild conditions are imposed on the univariate function. Our results settle an open question about representability in the class of single hidden layer neural networks. In particular, we show that arbitrary decision regions can be arbitrarily well approximated by continuous feedforward neural networks with only a single internal, hidden layer and any continuous sigmoidal nonlinearity. The paper discusses approximation properties of other possible types of nonlinearities that might be implemented by artificial neural networks. More... »

PAGES

303-314

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/bf02551274

DOI

http://dx.doi.org/10.1007/bf02551274

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1023250347


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 Illinois at Urbana Champaign", 
          "id": "https://www.grid.ac/institutes/grid.35403.31", 
          "name": [
            "Center for Supercomputing Research and Development and Department of Electrical and Computer Engineering, University of Illinois, 61801, Urbana, Illinois, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Cybenko", 
        "givenName": "G.", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1145/12130.12158", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035113948"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1968.1972", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038881641"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00336857", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040529426", 
          "https://doi.org/10.1007/bf00336857"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/neco.1989.1.1.151", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053187839"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/massp.1987.1165576", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061385413"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1137/0905013", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062855657"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1214/aos/1176349519", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1064408863"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5802/aif.474", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1073139110"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1090/pspum/028.2/0507425", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1089196220"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1989-12", 
    "datePublishedReg": "1989-12-01", 
    "description": "In this paper we demonstrate that finite linear combinations of compositions of a fixed, univariate function and a set of affine functionals can uniformly approximate any continuous function ofn real variables with support in the unit hypercube; only mild conditions are imposed on the univariate function. Our results settle an open question about representability in the class of single hidden layer neural networks. In particular, we show that arbitrary decision regions can be arbitrarily well approximated by continuous feedforward neural networks with only a single internal, hidden layer and any continuous sigmoidal nonlinearity. The paper discusses approximation properties of other possible types of nonlinearities that might be implemented by artificial neural networks.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/bf02551274", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1135855", 
        "issn": [
          "0932-4194", 
          "1435-568X"
        ], 
        "name": "Mathematics of Control, Signals, and Systems", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "4", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "2"
      }
    ], 
    "name": "Approximation by superpositions of a sigmoidal function", 
    "pagination": "303-314", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "6ec50f3efbbebec5568b7267a4e99fd3a7e16d8c5407c89042161fc53f36bfff"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/bf02551274"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1023250347"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/bf02551274", 
      "https://app.dimensions.ai/details/publication/pub.1023250347"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T13:35", 
    "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/v90/0000000370_0000000370/records_46775_00000001.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1007%2FBF02551274"
  }
]
 

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/bf02551274'

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/bf02551274'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/bf02551274'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/bf02551274'


 

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

88 TRIPLES      21 PREDICATES      36 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/bf02551274 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N14ebad5b2a05438da0663dec07483e5a
4 schema:citation sg:pub.10.1007/bf00336857
5 https://doi.org/10.1090/pspum/028.2/0507425
6 https://doi.org/10.1109/massp.1987.1165576
7 https://doi.org/10.1137/0905013
8 https://doi.org/10.1145/12130.12158
9 https://doi.org/10.1145/1968.1972
10 https://doi.org/10.1162/neco.1989.1.1.151
11 https://doi.org/10.1214/aos/1176349519
12 https://doi.org/10.5802/aif.474
13 schema:datePublished 1989-12
14 schema:datePublishedReg 1989-12-01
15 schema:description In this paper we demonstrate that finite linear combinations of compositions of a fixed, univariate function and a set of affine functionals can uniformly approximate any continuous function ofn real variables with support in the unit hypercube; only mild conditions are imposed on the univariate function. Our results settle an open question about representability in the class of single hidden layer neural networks. In particular, we show that arbitrary decision regions can be arbitrarily well approximated by continuous feedforward neural networks with only a single internal, hidden layer and any continuous sigmoidal nonlinearity. The paper discusses approximation properties of other possible types of nonlinearities that might be implemented by artificial neural networks.
16 schema:genre research_article
17 schema:inLanguage en
18 schema:isAccessibleForFree false
19 schema:isPartOf N59a605d8c364474b8ccc0ad6a1c85c6d
20 Nf8f0b102a8e14e3d87b69721fb4a664e
21 sg:journal.1135855
22 schema:name Approximation by superpositions of a sigmoidal function
23 schema:pagination 303-314
24 schema:productId N0a71b3bd492046a6a7fa68b5e54b3ece
25 N8eb43072d8d84f35b872500b951f623c
26 Nc87ff28b0c3044e78919a9569b1b787e
27 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023250347
28 https://doi.org/10.1007/bf02551274
29 schema:sdDatePublished 2019-04-11T13:35
30 schema:sdLicense https://scigraph.springernature.com/explorer/license/
31 schema:sdPublisher Ne72a63ebe5534a17b68cc9c496fc4103
32 schema:url http://link.springer.com/10.1007%2FBF02551274
33 sgo:license sg:explorer/license/
34 sgo:sdDataset articles
35 rdf:type schema:ScholarlyArticle
36 N0a71b3bd492046a6a7fa68b5e54b3ece schema:name doi
37 schema:value 10.1007/bf02551274
38 rdf:type schema:PropertyValue
39 N14ebad5b2a05438da0663dec07483e5a rdf:first Nc0d326bbb9b14b75aeb09edba64adbb1
40 rdf:rest rdf:nil
41 N59a605d8c364474b8ccc0ad6a1c85c6d schema:issueNumber 4
42 rdf:type schema:PublicationIssue
43 N8eb43072d8d84f35b872500b951f623c schema:name dimensions_id
44 schema:value pub.1023250347
45 rdf:type schema:PropertyValue
46 Nc0d326bbb9b14b75aeb09edba64adbb1 schema:affiliation https://www.grid.ac/institutes/grid.35403.31
47 schema:familyName Cybenko
48 schema:givenName G.
49 rdf:type schema:Person
50 Nc87ff28b0c3044e78919a9569b1b787e schema:name readcube_id
51 schema:value 6ec50f3efbbebec5568b7267a4e99fd3a7e16d8c5407c89042161fc53f36bfff
52 rdf:type schema:PropertyValue
53 Ne72a63ebe5534a17b68cc9c496fc4103 schema:name Springer Nature - SN SciGraph project
54 rdf:type schema:Organization
55 Nf8f0b102a8e14e3d87b69721fb4a664e schema:volumeNumber 2
56 rdf:type schema:PublicationVolume
57 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
58 schema:name Information and Computing Sciences
59 rdf:type schema:DefinedTerm
60 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
61 schema:name Artificial Intelligence and Image Processing
62 rdf:type schema:DefinedTerm
63 sg:journal.1135855 schema:issn 0932-4194
64 1435-568X
65 schema:name Mathematics of Control, Signals, and Systems
66 rdf:type schema:Periodical
67 sg:pub.10.1007/bf00336857 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040529426
68 https://doi.org/10.1007/bf00336857
69 rdf:type schema:CreativeWork
70 https://doi.org/10.1090/pspum/028.2/0507425 schema:sameAs https://app.dimensions.ai/details/publication/pub.1089196220
71 rdf:type schema:CreativeWork
72 https://doi.org/10.1109/massp.1987.1165576 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061385413
73 rdf:type schema:CreativeWork
74 https://doi.org/10.1137/0905013 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062855657
75 rdf:type schema:CreativeWork
76 https://doi.org/10.1145/12130.12158 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035113948
77 rdf:type schema:CreativeWork
78 https://doi.org/10.1145/1968.1972 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038881641
79 rdf:type schema:CreativeWork
80 https://doi.org/10.1162/neco.1989.1.1.151 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053187839
81 rdf:type schema:CreativeWork
82 https://doi.org/10.1214/aos/1176349519 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064408863
83 rdf:type schema:CreativeWork
84 https://doi.org/10.5802/aif.474 schema:sameAs https://app.dimensions.ai/details/publication/pub.1073139110
85 rdf:type schema:CreativeWork
86 https://www.grid.ac/institutes/grid.35403.31 schema:alternateName University of Illinois at Urbana Champaign
87 schema:name Center for Supercomputing Research and Development and Department of Electrical and Computer Engineering, University of Illinois, 61801, Urbana, Illinois, USA
88 rdf:type schema:Organization
 




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


...