Constraints on Learning in Dynamic Synapses View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

1993

AUTHORS

Daniel J. Amit , Stefano Fusi

ABSTRACT

Some constraints intrinsic to unsupervised learning in at tractor neural networks (ANN) are discussed. Hebbian type learning is discussed in a network whose synapses are analog, dynamic variables, with a fixed finite number of states that are stable on long time scales. It is shown that if the patterns to be learned are random words of ±1 bits then in the limit of slow presentation, the network can learn at most O(ln N) patterns in N neurons. Going beyond the logarithmic contraint requires stochastic learning of patterns and low coding rate. More... »

PAGES

730-733

Book

TITLE

ICANN ’93

ISBN

978-3-540-19839-0
978-1-4471-2063-6

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-1-4471-2063-6_203

DOI

http://dx.doi.org/10.1007/978-1-4471-2063-6_203

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1027493734


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/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "INFN, Sezione di Roma, Istituto di Fisica, Universit\u00e0 di Roma, La Sapienza, P.le Aldo Moro, Roma, Italy", 
          "id": "http://www.grid.ac/institutes/grid.7841.a", 
          "name": [
            "INFN, Sezione di Roma, Istituto di Fisica, Universit\u00e0 di Roma, La Sapienza, P.le Aldo Moro, Roma, Italy"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Amit", 
        "givenName": "Daniel J.", 
        "id": "sg:person.0615137425.75", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0615137425.75"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "INFN, Sezione di Roma, Istituto di Fisica, Universit\u00e0 di Roma, La Sapienza, P.le Aldo Moro, Roma, Italy", 
          "id": "http://www.grid.ac/institutes/grid.7841.a", 
          "name": [
            "INFN, Sezione di Roma, Istituto di Fisica, Universit\u00e0 di Roma, La Sapienza, P.le Aldo Moro, Roma, Italy"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fusi", 
        "givenName": "Stefano", 
        "id": "sg:person.01326702501.50", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01326702501.50"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "1993", 
    "datePublishedReg": "1993-01-01", 
    "description": "Some constraints intrinsic to unsupervised learning in at tractor neural networks (ANN) are discussed. Hebbian type learning is discussed in a network whose synapses are analog, dynamic variables, with a fixed finite number of states that are stable on long time scales. It is shown that if the patterns to be learned are random words of \u00b11 bits then in the limit of slow presentation, the network can learn at most O(ln N) patterns in N neurons. Going beyond the logarithmic contraint requires stochastic learning of patterns and low coding rate.", 
    "editor": [
      {
        "familyName": "Gielen", 
        "givenName": "Stan", 
        "type": "Person"
      }, 
      {
        "familyName": "Kappen", 
        "givenName": "Bert", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-1-4471-2063-6_203", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-19839-0", 
        "978-1-4471-2063-6"
      ], 
      "name": "ICANN \u201993", 
      "type": "Book"
    }, 
    "keywords": [
      "finite number", 
      "stochastic learning", 
      "type learning", 
      "dynamic variables", 
      "slow presentation", 
      "unsupervised learning", 
      "random words", 
      "neural network", 
      "learning", 
      "constraints", 
      "network", 
      "coding rate", 
      "low coding rate", 
      "dynamic synapses", 
      "time scales", 
      "longer time scales", 
      "contraints", 
      "words", 
      "variables", 
      "patterns", 
      "scale", 
      "presentation", 
      "number", 
      "limit", 
      "state", 
      "neurons", 
      "synapses", 
      "rate", 
      "tractor neural networks", 
      "Hebbian type learning", 
      "logarithmic contraint"
    ], 
    "name": "Constraints on Learning in Dynamic Synapses", 
    "pagination": "730-733", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1027493734"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-1-4471-2063-6_203"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-1-4471-2063-6_203", 
      "https://app.dimensions.ai/details/publication/pub.1027493734"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-11-01T18:52", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211101/entities/gbq_results/chapter/chapter_246.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-1-4471-2063-6_203"
  }
]
 

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.10.1007/978-1-4471-2063-6_203'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-1-4471-2063-6_203'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-1-4471-2063-6_203'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-1-4471-2063-6_203'


 

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

103 TRIPLES      23 PREDICATES      57 URIs      50 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-1-4471-2063-6_203 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 schema:author N0d6cbe70ec52420cb77849a91f9267fb
4 schema:datePublished 1993
5 schema:datePublishedReg 1993-01-01
6 schema:description Some constraints intrinsic to unsupervised learning in at tractor neural networks (ANN) are discussed. Hebbian type learning is discussed in a network whose synapses are analog, dynamic variables, with a fixed finite number of states that are stable on long time scales. It is shown that if the patterns to be learned are random words of ±1 bits then in the limit of slow presentation, the network can learn at most O(ln N) patterns in N neurons. Going beyond the logarithmic contraint requires stochastic learning of patterns and low coding rate.
7 schema:editor N9543c398b36641b49491b7a5fa5353bc
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf Nbf221d2b78b348d0a8362955570ccf4b
12 schema:keywords Hebbian type learning
13 coding rate
14 constraints
15 contraints
16 dynamic synapses
17 dynamic variables
18 finite number
19 learning
20 limit
21 logarithmic contraint
22 longer time scales
23 low coding rate
24 network
25 neural network
26 neurons
27 number
28 patterns
29 presentation
30 random words
31 rate
32 scale
33 slow presentation
34 state
35 stochastic learning
36 synapses
37 time scales
38 tractor neural networks
39 type learning
40 unsupervised learning
41 variables
42 words
43 schema:name Constraints on Learning in Dynamic Synapses
44 schema:pagination 730-733
45 schema:productId N4ee807d67bc8448f98ba61fa744f30cb
46 Nd874a10c01be4448953aaf9e7a274c1b
47 schema:publisher Ncfa61ac2c03c499cb7bd54b487a559b8
48 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027493734
49 https://doi.org/10.1007/978-1-4471-2063-6_203
50 schema:sdDatePublished 2021-11-01T18:52
51 schema:sdLicense https://scigraph.springernature.com/explorer/license/
52 schema:sdPublisher N3da91c9c36cb424693ec572544c8bffa
53 schema:url https://doi.org/10.1007/978-1-4471-2063-6_203
54 sgo:license sg:explorer/license/
55 sgo:sdDataset chapters
56 rdf:type schema:Chapter
57 N0d6cbe70ec52420cb77849a91f9267fb rdf:first sg:person.0615137425.75
58 rdf:rest N8a07e4a94da44f509921313762d2e912
59 N3da91c9c36cb424693ec572544c8bffa schema:name Springer Nature - SN SciGraph project
60 rdf:type schema:Organization
61 N4ee807d67bc8448f98ba61fa744f30cb schema:name doi
62 schema:value 10.1007/978-1-4471-2063-6_203
63 rdf:type schema:PropertyValue
64 N8a07e4a94da44f509921313762d2e912 rdf:first sg:person.01326702501.50
65 rdf:rest rdf:nil
66 N8b51d5d19f5c4cb6bcc9d95934199be9 schema:familyName Kappen
67 schema:givenName Bert
68 rdf:type schema:Person
69 N9543c398b36641b49491b7a5fa5353bc rdf:first Naf4e5b5c63e04b969cdf8f724d7c6b1b
70 rdf:rest Ne8dbc2a8b4754c09a18858b99006a991
71 Naf4e5b5c63e04b969cdf8f724d7c6b1b schema:familyName Gielen
72 schema:givenName Stan
73 rdf:type schema:Person
74 Nbf221d2b78b348d0a8362955570ccf4b schema:isbn 978-1-4471-2063-6
75 978-3-540-19839-0
76 schema:name ICANN ’93
77 rdf:type schema:Book
78 Ncfa61ac2c03c499cb7bd54b487a559b8 schema:name Springer Nature
79 rdf:type schema:Organisation
80 Nd874a10c01be4448953aaf9e7a274c1b schema:name dimensions_id
81 schema:value pub.1027493734
82 rdf:type schema:PropertyValue
83 Ne8dbc2a8b4754c09a18858b99006a991 rdf:first N8b51d5d19f5c4cb6bcc9d95934199be9
84 rdf:rest rdf:nil
85 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
86 schema:name Mathematical Sciences
87 rdf:type schema:DefinedTerm
88 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
89 schema:name Statistics
90 rdf:type schema:DefinedTerm
91 sg:person.01326702501.50 schema:affiliation grid-institutes:grid.7841.a
92 schema:familyName Fusi
93 schema:givenName Stefano
94 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01326702501.50
95 rdf:type schema:Person
96 sg:person.0615137425.75 schema:affiliation grid-institutes:grid.7841.a
97 schema:familyName Amit
98 schema:givenName Daniel J.
99 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0615137425.75
100 rdf:type schema:Person
101 grid-institutes:grid.7841.a schema:alternateName INFN, Sezione di Roma, Istituto di Fisica, Università di Roma, La Sapienza, P.le Aldo Moro, Roma, Italy
102 schema:name INFN, Sezione di Roma, Istituto di Fisica, Università di Roma, La Sapienza, P.le Aldo Moro, Roma, Italy
103 rdf:type schema:Organization
 




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


...