On the Intractability of Loading Neural Networks View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

1994

AUTHORS

Bhaskar DasGupta , Hava T. Siegelmann , Eduardo Sontag

ABSTRACT

Neural networks have been proposed as a tool for machine learning. In this role, a network is trained to recognize complex associations between inputs and outputs that were presented during a supervised training cycle. These associations are incorporated into the weights of the network, which encode a distributed representation of the information that was contained in the patterns. Once trained, the network will compute an input/output mapping which, if the training data was representative enough, will closely match the unknown rule which produced the original data. Massive parallelism of computation, as well as noise and fault tolerance, are often offered as justifications for the use of neural nets as learning paradigms. More... »

PAGES

357-389

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-1-4615-2696-4_10

DOI

http://dx.doi.org/10.1007/978-1-4615-2696-4_10

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1009581238


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/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Dept. of Computer Science, University of Minnesota, 55455-0159, Minneapolis, MN, USA", 
          "id": "http://www.grid.ac/institutes/grid.17635.36", 
          "name": [
            "Dept. of Computer Science, University of Minnesota, 55455-0159, Minneapolis, MN, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "DasGupta", 
        "givenName": "Bhaskar", 
        "id": "sg:person.0763403270.10", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0763403270.10"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dept. of Computer Science, Rutgers University, 08903, New Brunswick, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.430387.b", 
          "name": [
            "Dept. of Computer Science, Rutgers University, 08903, New Brunswick, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Siegelmann", 
        "givenName": "Hava T.", 
        "id": "sg:person.0733202717.86", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0733202717.86"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dept. of Mathematics, Rutgers University, 08903, New Brunswick, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.430387.b", 
          "name": [
            "Dept. of Mathematics, Rutgers University, 08903, New Brunswick, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Sontag", 
        "givenName": "Eduardo", 
        "id": "sg:person.0714217520.83", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0714217520.83"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "1994", 
    "datePublishedReg": "1994-01-01", 
    "description": "Neural networks have been proposed as a tool for machine learning. In this role, a network is trained to recognize complex associations between inputs and outputs that were presented during a supervised training cycle. These associations are incorporated into the weights of the network, which encode a distributed representation of the information that was contained in the patterns. Once trained, the network will compute an input/output mapping which, if the training data was representative enough, will closely match the unknown rule which produced the original data. Massive parallelism of computation, as well as noise and fault tolerance, are often offered as justifications for the use of neural nets as learning paradigms.", 
    "editor": [
      {
        "familyName": "Roychowdhury", 
        "givenName": "Vwani", 
        "type": "Person"
      }, 
      {
        "familyName": "Siu", 
        "givenName": "Kai-Yeung", 
        "type": "Person"
      }, 
      {
        "familyName": "Orlitsky", 
        "givenName": "Alon", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-1-4615-2696-4_10", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-1-4613-6160-2", 
        "978-1-4615-2696-4"
      ], 
      "name": "Theoretical Advances in Neural Computation and Learning", 
      "type": "Book"
    }, 
    "keywords": [
      "neural network", 
      "input/output mapping", 
      "machine learning", 
      "massive parallelism", 
      "training data", 
      "fault tolerance", 
      "neural nets", 
      "unknown rules", 
      "distributed representation", 
      "output mapping", 
      "network", 
      "original data", 
      "training cycle", 
      "parallelism", 
      "computation", 
      "intractability", 
      "learning", 
      "paradigm", 
      "nets", 
      "representation", 
      "information", 
      "rules", 
      "tool", 
      "data", 
      "input", 
      "mapping", 
      "noise", 
      "output", 
      "use", 
      "complex association", 
      "patterns", 
      "justification", 
      "tolerance", 
      "weight", 
      "cycle", 
      "role", 
      "association"
    ], 
    "name": "On the Intractability of Loading Neural Networks", 
    "pagination": "357-389", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1009581238"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-1-4615-2696-4_10"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-1-4615-2696-4_10", 
      "https://app.dimensions.ai/details/publication/pub.1009581238"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-05-20T07:44", 
    "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_235.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-1-4615-2696-4_10"
  }
]
 

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.10.1007/978-1-4615-2696-4_10'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-1-4615-2696-4_10'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-1-4615-2696-4_10'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-1-4615-2696-4_10'


 

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

126 TRIPLES      23 PREDICATES      63 URIs      56 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-1-4615-2696-4_10 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N4b816e437efe49ea94f5b80a819057f7
4 schema:datePublished 1994
5 schema:datePublishedReg 1994-01-01
6 schema:description Neural networks have been proposed as a tool for machine learning. In this role, a network is trained to recognize complex associations between inputs and outputs that were presented during a supervised training cycle. These associations are incorporated into the weights of the network, which encode a distributed representation of the information that was contained in the patterns. Once trained, the network will compute an input/output mapping which, if the training data was representative enough, will closely match the unknown rule which produced the original data. Massive parallelism of computation, as well as noise and fault tolerance, are often offered as justifications for the use of neural nets as learning paradigms.
7 schema:editor N692a149db867485dacebc700cc49d9dd
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf Nce7bc52f9cdb41a687a094b3d19c4e9a
12 schema:keywords association
13 complex association
14 computation
15 cycle
16 data
17 distributed representation
18 fault tolerance
19 information
20 input
21 input/output mapping
22 intractability
23 justification
24 learning
25 machine learning
26 mapping
27 massive parallelism
28 nets
29 network
30 neural nets
31 neural network
32 noise
33 original data
34 output
35 output mapping
36 paradigm
37 parallelism
38 patterns
39 representation
40 role
41 rules
42 tolerance
43 tool
44 training cycle
45 training data
46 unknown rules
47 use
48 weight
49 schema:name On the Intractability of Loading Neural Networks
50 schema:pagination 357-389
51 schema:productId N9797be3dc7a843278f5d76e535d74c40
52 Nbe59afc87b504cc0a121d156f394581c
53 schema:publisher N02bc5e0cc3d54dbcacf94de4158c8f03
54 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009581238
55 https://doi.org/10.1007/978-1-4615-2696-4_10
56 schema:sdDatePublished 2022-05-20T07:44
57 schema:sdLicense https://scigraph.springernature.com/explorer/license/
58 schema:sdPublisher N086a0d48c0e44565825f49d417a40b2f
59 schema:url https://doi.org/10.1007/978-1-4615-2696-4_10
60 sgo:license sg:explorer/license/
61 sgo:sdDataset chapters
62 rdf:type schema:Chapter
63 N00615c7d70fb4157926ea60c1f893997 rdf:first sg:person.0714217520.83
64 rdf:rest rdf:nil
65 N02bc5e0cc3d54dbcacf94de4158c8f03 schema:name Springer Nature
66 rdf:type schema:Organisation
67 N086a0d48c0e44565825f49d417a40b2f schema:name Springer Nature - SN SciGraph project
68 rdf:type schema:Organization
69 N0a2de693d73c44ff97c3c9f92e8a55e1 rdf:first N6aee33660f3c493381d26749dcb5a7f2
70 rdf:rest rdf:nil
71 N3780216be48447f1b7d03540eb260c73 schema:familyName Siu
72 schema:givenName Kai-Yeung
73 rdf:type schema:Person
74 N4b816e437efe49ea94f5b80a819057f7 rdf:first sg:person.0763403270.10
75 rdf:rest N8c8943a6b0924e29b17e3b265110fccb
76 N692a149db867485dacebc700cc49d9dd rdf:first N9155255f8144481f8f510c0d5bf47ef2
77 rdf:rest N7ead3053879d4fd7bec4af87e7dc0e49
78 N6aee33660f3c493381d26749dcb5a7f2 schema:familyName Orlitsky
79 schema:givenName Alon
80 rdf:type schema:Person
81 N7ead3053879d4fd7bec4af87e7dc0e49 rdf:first N3780216be48447f1b7d03540eb260c73
82 rdf:rest N0a2de693d73c44ff97c3c9f92e8a55e1
83 N8c8943a6b0924e29b17e3b265110fccb rdf:first sg:person.0733202717.86
84 rdf:rest N00615c7d70fb4157926ea60c1f893997
85 N9155255f8144481f8f510c0d5bf47ef2 schema:familyName Roychowdhury
86 schema:givenName Vwani
87 rdf:type schema:Person
88 N9797be3dc7a843278f5d76e535d74c40 schema:name doi
89 schema:value 10.1007/978-1-4615-2696-4_10
90 rdf:type schema:PropertyValue
91 Nbe59afc87b504cc0a121d156f394581c schema:name dimensions_id
92 schema:value pub.1009581238
93 rdf:type schema:PropertyValue
94 Nce7bc52f9cdb41a687a094b3d19c4e9a schema:isbn 978-1-4613-6160-2
95 978-1-4615-2696-4
96 schema:name Theoretical Advances in Neural Computation and Learning
97 rdf:type schema:Book
98 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
99 schema:name Information and Computing Sciences
100 rdf:type schema:DefinedTerm
101 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
102 schema:name Artificial Intelligence and Image Processing
103 rdf:type schema:DefinedTerm
104 sg:person.0714217520.83 schema:affiliation grid-institutes:grid.430387.b
105 schema:familyName Sontag
106 schema:givenName Eduardo
107 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0714217520.83
108 rdf:type schema:Person
109 sg:person.0733202717.86 schema:affiliation grid-institutes:grid.430387.b
110 schema:familyName Siegelmann
111 schema:givenName Hava T.
112 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0733202717.86
113 rdf:type schema:Person
114 sg:person.0763403270.10 schema:affiliation grid-institutes:grid.17635.36
115 schema:familyName DasGupta
116 schema:givenName Bhaskar
117 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0763403270.10
118 rdf:type schema:Person
119 grid-institutes:grid.17635.36 schema:alternateName Dept. of Computer Science, University of Minnesota, 55455-0159, Minneapolis, MN, USA
120 schema:name Dept. of Computer Science, University of Minnesota, 55455-0159, Minneapolis, MN, USA
121 rdf:type schema:Organization
122 grid-institutes:grid.430387.b schema:alternateName Dept. of Computer Science, Rutgers University, 08903, New Brunswick, NJ, USA
123 Dept. of Mathematics, Rutgers University, 08903, New Brunswick, NJ, USA
124 schema:name Dept. of Computer Science, Rutgers University, 08903, New Brunswick, NJ, USA
125 Dept. of Mathematics, Rutgers University, 08903, New Brunswick, NJ, USA
126 rdf:type schema:Organization
 




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


...