Dynamics of On-Line Learning in Radial Basis Function Neural Networks View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

1999

AUTHORS

Maria Marinaro , Silvia Scarpetta

ABSTRACT

We present a method for analyzing the behavior of RBFs in an on-line scenario which provides a description of the learning dynamics without invoking the thermodynamic limit. Our analysis is based on a master equation that describes the dynamics of the weight space probability density for any value of the input space dimension. Because the transition probability appearing in the master equation cannot be written in closed form, some approximate form of the dynamics is developed. We assume a arbitrary small learning rate (small noise) and we derive in this limit the dynamic evolution of the means and the variances of the net weights. The analytic results are then confirmed by simulations. More... »

PAGES

139-144

Book

TITLE

Neural Nets WIRN Vietri-99

ISBN

978-1-4471-1226-6
978-1-4471-0877-1

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-1-4471-0877-1_11

DOI

http://dx.doi.org/10.1007/978-1-4471-0877-1_11

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1007516235


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/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "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": "University of Salerno", 
          "id": "https://www.grid.ac/institutes/grid.11780.3f", 
          "name": [
            "INFM, Unita\u2019 di Salerno, Salerno, Italia", 
            "Dipartimento di Fisica Teorica \u2018E.R.Caianiello\u201d, Universita\u2019 di Salerno, Via S. Allende, 84081, Baronissi (SA), Italia", 
            "International Institute for Advanced Science Studies, Via G. Pellegrino 19, 84019, Vietri sul Mare, Salerno, Italia"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Marinaro", 
        "givenName": "Maria", 
        "id": "sg:person.01027564003.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01027564003.17"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Salerno", 
          "id": "https://www.grid.ac/institutes/grid.11780.3f", 
          "name": [
            "INFM, Unita\u2019 di Salerno, Salerno, Italia", 
            "Dipartimento di Fisica Teorica \u2018E.R.Caianiello\u201d, Universita\u2019 di Salerno, Via S. Allende, 84081, Baronissi (SA), Italia"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Scarpetta", 
        "givenName": "Silvia", 
        "id": "sg:person.01134412304.81", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01134412304.81"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1063/1.1665510", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1057743590"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1999", 
    "datePublishedReg": "1999-01-01", 
    "description": "We present a method for analyzing the behavior of RBFs in an on-line scenario which provides a description of the learning dynamics without invoking the thermodynamic limit. Our analysis is based on a master equation that describes the dynamics of the weight space probability density for any value of the input space dimension. Because the transition probability appearing in the master equation cannot be written in closed form, some approximate form of the dynamics is developed. We assume a arbitrary small learning rate (small noise) and we derive in this limit the dynamic evolution of the means and the variances of the net weights. The analytic results are then confirmed by simulations.", 
    "editor": [
      {
        "familyName": "Marinaro", 
        "givenName": "Maria", 
        "type": "Person"
      }, 
      {
        "familyName": "Tagliaferri", 
        "givenName": "Roberto", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-1-4471-0877-1_11", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-1-4471-1226-6", 
        "978-1-4471-0877-1"
      ], 
      "name": "Neural Nets WIRN Vietri-99", 
      "type": "Book"
    }, 
    "name": "Dynamics of On-Line Learning in Radial Basis Function Neural Networks", 
    "pagination": "139-144", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1007516235"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-1-4471-0877-1_11"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "23cd51f6930760c93c191f82e25b49a737e8cf1160341bc891981a24c8060cac"
        ]
      }
    ], 
    "publisher": {
      "location": "London", 
      "name": "Springer London", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-1-4471-0877-1_11", 
      "https://app.dimensions.ai/details/publication/pub.1007516235"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T09:02", 
    "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_46741_00000000.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F978-1-4471-0877-1_11"
  }
]
 

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.10.1007/978-1-4471-0877-1_11'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-1-4471-0877-1_11'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-1-4471-0877-1_11'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-1-4471-0877-1_11'


 

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

82 TRIPLES      23 PREDICATES      28 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-1-4471-0877-1_11 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 schema:author N82d9fa62e649499193d0b08041d23023
4 schema:citation https://doi.org/10.1063/1.1665510
5 schema:datePublished 1999
6 schema:datePublishedReg 1999-01-01
7 schema:description We present a method for analyzing the behavior of RBFs in an on-line scenario which provides a description of the learning dynamics without invoking the thermodynamic limit. Our analysis is based on a master equation that describes the dynamics of the weight space probability density for any value of the input space dimension. Because the transition probability appearing in the master equation cannot be written in closed form, some approximate form of the dynamics is developed. We assume a arbitrary small learning rate (small noise) and we derive in this limit the dynamic evolution of the means and the variances of the net weights. The analytic results are then confirmed by simulations.
8 schema:editor Naddc622be3ff4a0baeb64155da35dfb0
9 schema:genre chapter
10 schema:inLanguage en
11 schema:isAccessibleForFree false
12 schema:isPartOf N2bf94c910639489eb84d4e8affe9d148
13 schema:name Dynamics of On-Line Learning in Radial Basis Function Neural Networks
14 schema:pagination 139-144
15 schema:productId N61cff7ee06e84902a76d1763ff0f3abb
16 N8693f5b9fcaa4b17a071bca4f3c57a24
17 Na5603fc6d65b48aa83ac5247ca43c935
18 schema:publisher N27f872a1bb2d41c3967bb077223efacc
19 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007516235
20 https://doi.org/10.1007/978-1-4471-0877-1_11
21 schema:sdDatePublished 2019-04-16T09:02
22 schema:sdLicense https://scigraph.springernature.com/explorer/license/
23 schema:sdPublisher N93fcf5ebc1244e0e89689f709b8f1ee0
24 schema:url https://link.springer.com/10.1007%2F978-1-4471-0877-1_11
25 sgo:license sg:explorer/license/
26 sgo:sdDataset chapters
27 rdf:type schema:Chapter
28 N27f872a1bb2d41c3967bb077223efacc schema:location London
29 schema:name Springer London
30 rdf:type schema:Organisation
31 N2bf94c910639489eb84d4e8affe9d148 schema:isbn 978-1-4471-0877-1
32 978-1-4471-1226-6
33 schema:name Neural Nets WIRN Vietri-99
34 rdf:type schema:Book
35 N5a03f019409d4287a641a17be887a258 rdf:first sg:person.01134412304.81
36 rdf:rest rdf:nil
37 N5ae95e0bd6f54fabaf5c29b8264ba32c schema:familyName Tagliaferri
38 schema:givenName Roberto
39 rdf:type schema:Person
40 N61cff7ee06e84902a76d1763ff0f3abb schema:name dimensions_id
41 schema:value pub.1007516235
42 rdf:type schema:PropertyValue
43 N82d9fa62e649499193d0b08041d23023 rdf:first sg:person.01027564003.17
44 rdf:rest N5a03f019409d4287a641a17be887a258
45 N8693f5b9fcaa4b17a071bca4f3c57a24 schema:name doi
46 schema:value 10.1007/978-1-4471-0877-1_11
47 rdf:type schema:PropertyValue
48 N93fcf5ebc1244e0e89689f709b8f1ee0 schema:name Springer Nature - SN SciGraph project
49 rdf:type schema:Organization
50 Na5603fc6d65b48aa83ac5247ca43c935 schema:name readcube_id
51 schema:value 23cd51f6930760c93c191f82e25b49a737e8cf1160341bc891981a24c8060cac
52 rdf:type schema:PropertyValue
53 Naddc622be3ff4a0baeb64155da35dfb0 rdf:first Nd9ae4835d4c744539d64de92b6987dc8
54 rdf:rest Ncd2d894e66864b57bbc51616378fedf2
55 Ncd2d894e66864b57bbc51616378fedf2 rdf:first N5ae95e0bd6f54fabaf5c29b8264ba32c
56 rdf:rest rdf:nil
57 Nd9ae4835d4c744539d64de92b6987dc8 schema:familyName Marinaro
58 schema:givenName Maria
59 rdf:type schema:Person
60 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
61 schema:name Mathematical Sciences
62 rdf:type schema:DefinedTerm
63 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
64 schema:name Statistics
65 rdf:type schema:DefinedTerm
66 sg:person.01027564003.17 schema:affiliation https://www.grid.ac/institutes/grid.11780.3f
67 schema:familyName Marinaro
68 schema:givenName Maria
69 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01027564003.17
70 rdf:type schema:Person
71 sg:person.01134412304.81 schema:affiliation https://www.grid.ac/institutes/grid.11780.3f
72 schema:familyName Scarpetta
73 schema:givenName Silvia
74 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01134412304.81
75 rdf:type schema:Person
76 https://doi.org/10.1063/1.1665510 schema:sameAs https://app.dimensions.ai/details/publication/pub.1057743590
77 rdf:type schema:CreativeWork
78 https://www.grid.ac/institutes/grid.11780.3f schema:alternateName University of Salerno
79 schema:name Dipartimento di Fisica Teorica ‘E.R.Caianiello”, Universita’ di Salerno, Via S. Allende, 84081, Baronissi (SA), Italia
80 INFM, Unita’ di Salerno, Salerno, Italia
81 International Institute for Advanced Science Studies, Via G. Pellegrino 19, 84019, Vietri sul Mare, Salerno, Italia
82 rdf:type schema:Organization
 




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


...