Hebbian and error-correction learning for complex-valued neurons View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2013-02

AUTHORS

Igor Aizenberg

ABSTRACT

In this paper, we observe some important aspects of Hebbian and error-correction learning rules for complex-valued neurons. These learning rules, which were previously considered for the multi-valued neuron (MVN) whose inputs and output are located on the unit circle, are generalized for a complex-valued neuron whose inputs and output are arbitrary complex numbers. The Hebbian learning rule is also considered for the MVN with a periodic activation function. It is experimentally shown that Hebbian weights, even if they still cannot implement an input/output mapping to be learned, are better starting weights for the error-correction learning, which converges faster starting from the Hebbian weights rather than from the random ones. More... »

PAGES

265-273

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00500-012-0891-8

DOI

http://dx.doi.org/10.1007/s00500-012-0891-8

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1034051080


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/2008/1109", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Neurosciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/11", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Medical and Health Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Texas A&M University \u2013 Texarkana", 
          "id": "https://www.grid.ac/institutes/grid.264762.3", 
          "name": [
            "Texas A&M University-Texarkana, 7101 University Ave, 75503, Texarkana, TX, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Aizenberg", 
        "givenName": "Igor", 
        "id": "sg:person.010651634015.21", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010651634015.21"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s00500-007-0204-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002010240", 
          "https://doi.org/10.1007/s00500-007-0204-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-33457-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004168507", 
          "https://doi.org/10.1007/978-3-540-33457-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-33457-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004168507", 
          "https://doi.org/10.1007/978-3-540-33457-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-45723-2_44", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007354410", 
          "https://doi.org/10.1007/3-540-45723-2_44"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-45723-2_44", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007354410", 
          "https://doi.org/10.1007/3-540-45723-2_44"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-20353-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007584937", 
          "https://doi.org/10.1007/978-3-642-20353-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-20353-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007584937", 
          "https://doi.org/10.1007/978-3-642-20353-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/0899766053429381", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024420009"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-31182-3_55", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037945160", 
          "https://doi.org/10.1007/3-540-31182-3_55"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.renene.2005.07.006", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041708369"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.renene.2005.07.006", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041708369"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00500-006-0075-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049275324", 
          "https://doi.org/10.1007/s00500-006-0075-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00500-006-0075-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049275324", 
          "https://doi.org/10.1007/s00500-006-0075-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1051979123", 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4757-3115-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051979123", 
          "https://doi.org/10.1007/978-1-4757-3115-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4757-3115-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051979123", 
          "https://doi.org/10.1007/978-1-4757-3115-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/72.548176", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061218830"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tcsii.2003.810486", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061568797"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tnn.2003.813844", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061716601"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tnn.2010.2082561", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061717794"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cnna.1992.274330", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1086276533"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/9780470742624", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1098661861"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/9780470742624", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1098661861"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2013-02", 
    "datePublishedReg": "2013-02-01", 
    "description": "In this paper, we observe some important aspects of Hebbian and error-correction learning rules for complex-valued neurons. These learning rules, which were previously considered for the multi-valued neuron (MVN) whose inputs and output are located on the unit circle, are generalized for a complex-valued neuron whose inputs and output are arbitrary complex numbers. The Hebbian learning rule is also considered for the MVN with a periodic activation function. It is experimentally shown that Hebbian weights, even if they still cannot implement an input/output mapping to be learned, are better starting weights for the error-correction learning, which converges faster starting from the Hebbian weights rather than from the random ones.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s00500-012-0891-8", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isFundedItemOf": [
      {
        "id": "sg:grant.3104551", 
        "type": "MonetaryGrant"
      }
    ], 
    "isPartOf": [
      {
        "id": "sg:journal.1050238", 
        "issn": [
          "1432-7643", 
          "1433-7479"
        ], 
        "name": "Soft Computing", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "2", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "17"
      }
    ], 
    "name": "Hebbian and error-correction learning for complex-valued neurons", 
    "pagination": "265-273", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "a23600a13224802eea721acd3e60b941955a535233be8f904e50048477cf6d35"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00500-012-0891-8"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1034051080"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00500-012-0891-8", 
      "https://app.dimensions.ai/details/publication/pub.1034051080"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-10T14:10", 
    "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_8660_00000514.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1007%2Fs00500-012-0891-8"
  }
]
 

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/s00500-012-0891-8'

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/s00500-012-0891-8'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00500-012-0891-8'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00500-012-0891-8'


 

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

117 TRIPLES      21 PREDICATES      43 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00500-012-0891-8 schema:about anzsrc-for:11
2 anzsrc-for:1109
3 schema:author N120f0e68b16341be9c322005a17286a2
4 schema:citation sg:pub.10.1007/3-540-31182-3_55
5 sg:pub.10.1007/3-540-45723-2_44
6 sg:pub.10.1007/978-1-4757-3115-6
7 sg:pub.10.1007/978-3-540-33457-6
8 sg:pub.10.1007/978-3-642-20353-4
9 sg:pub.10.1007/s00500-006-0075-5
10 sg:pub.10.1007/s00500-007-0204-9
11 https://app.dimensions.ai/details/publication/pub.1051979123
12 https://doi.org/10.1002/9780470742624
13 https://doi.org/10.1016/j.renene.2005.07.006
14 https://doi.org/10.1109/72.548176
15 https://doi.org/10.1109/cnna.1992.274330
16 https://doi.org/10.1109/tcsii.2003.810486
17 https://doi.org/10.1109/tnn.2003.813844
18 https://doi.org/10.1109/tnn.2010.2082561
19 https://doi.org/10.1162/0899766053429381
20 schema:datePublished 2013-02
21 schema:datePublishedReg 2013-02-01
22 schema:description In this paper, we observe some important aspects of Hebbian and error-correction learning rules for complex-valued neurons. These learning rules, which were previously considered for the multi-valued neuron (MVN) whose inputs and output are located on the unit circle, are generalized for a complex-valued neuron whose inputs and output are arbitrary complex numbers. The Hebbian learning rule is also considered for the MVN with a periodic activation function. It is experimentally shown that Hebbian weights, even if they still cannot implement an input/output mapping to be learned, are better starting weights for the error-correction learning, which converges faster starting from the Hebbian weights rather than from the random ones.
23 schema:genre research_article
24 schema:inLanguage en
25 schema:isAccessibleForFree false
26 schema:isPartOf N10dd7db3faa148d69d9a30a5236e6eea
27 N294eb0099eba41069bdb194336aab99e
28 sg:journal.1050238
29 schema:name Hebbian and error-correction learning for complex-valued neurons
30 schema:pagination 265-273
31 schema:productId N552eba519c21417da8909f17db822d94
32 N90b06eeaa403473c83197385e8077be6
33 Nf5063c84254544c5b86022a25eaf1190
34 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034051080
35 https://doi.org/10.1007/s00500-012-0891-8
36 schema:sdDatePublished 2019-04-10T14:10
37 schema:sdLicense https://scigraph.springernature.com/explorer/license/
38 schema:sdPublisher N0b1ea95fea164c23b85b80511b2737b3
39 schema:url http://link.springer.com/10.1007%2Fs00500-012-0891-8
40 sgo:license sg:explorer/license/
41 sgo:sdDataset articles
42 rdf:type schema:ScholarlyArticle
43 N0b1ea95fea164c23b85b80511b2737b3 schema:name Springer Nature - SN SciGraph project
44 rdf:type schema:Organization
45 N10dd7db3faa148d69d9a30a5236e6eea schema:volumeNumber 17
46 rdf:type schema:PublicationVolume
47 N120f0e68b16341be9c322005a17286a2 rdf:first sg:person.010651634015.21
48 rdf:rest rdf:nil
49 N294eb0099eba41069bdb194336aab99e schema:issueNumber 2
50 rdf:type schema:PublicationIssue
51 N552eba519c21417da8909f17db822d94 schema:name dimensions_id
52 schema:value pub.1034051080
53 rdf:type schema:PropertyValue
54 N90b06eeaa403473c83197385e8077be6 schema:name readcube_id
55 schema:value a23600a13224802eea721acd3e60b941955a535233be8f904e50048477cf6d35
56 rdf:type schema:PropertyValue
57 Nf5063c84254544c5b86022a25eaf1190 schema:name doi
58 schema:value 10.1007/s00500-012-0891-8
59 rdf:type schema:PropertyValue
60 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
61 schema:name Medical and Health Sciences
62 rdf:type schema:DefinedTerm
63 anzsrc-for:1109 schema:inDefinedTermSet anzsrc-for:
64 schema:name Neurosciences
65 rdf:type schema:DefinedTerm
66 sg:grant.3104551 http://pending.schema.org/fundedItem sg:pub.10.1007/s00500-012-0891-8
67 rdf:type schema:MonetaryGrant
68 sg:journal.1050238 schema:issn 1432-7643
69 1433-7479
70 schema:name Soft Computing
71 rdf:type schema:Periodical
72 sg:person.010651634015.21 schema:affiliation https://www.grid.ac/institutes/grid.264762.3
73 schema:familyName Aizenberg
74 schema:givenName Igor
75 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010651634015.21
76 rdf:type schema:Person
77 sg:pub.10.1007/3-540-31182-3_55 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037945160
78 https://doi.org/10.1007/3-540-31182-3_55
79 rdf:type schema:CreativeWork
80 sg:pub.10.1007/3-540-45723-2_44 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007354410
81 https://doi.org/10.1007/3-540-45723-2_44
82 rdf:type schema:CreativeWork
83 sg:pub.10.1007/978-1-4757-3115-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051979123
84 https://doi.org/10.1007/978-1-4757-3115-6
85 rdf:type schema:CreativeWork
86 sg:pub.10.1007/978-3-540-33457-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004168507
87 https://doi.org/10.1007/978-3-540-33457-6
88 rdf:type schema:CreativeWork
89 sg:pub.10.1007/978-3-642-20353-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007584937
90 https://doi.org/10.1007/978-3-642-20353-4
91 rdf:type schema:CreativeWork
92 sg:pub.10.1007/s00500-006-0075-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049275324
93 https://doi.org/10.1007/s00500-006-0075-5
94 rdf:type schema:CreativeWork
95 sg:pub.10.1007/s00500-007-0204-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002010240
96 https://doi.org/10.1007/s00500-007-0204-9
97 rdf:type schema:CreativeWork
98 https://app.dimensions.ai/details/publication/pub.1051979123 schema:CreativeWork
99 https://doi.org/10.1002/9780470742624 schema:sameAs https://app.dimensions.ai/details/publication/pub.1098661861
100 rdf:type schema:CreativeWork
101 https://doi.org/10.1016/j.renene.2005.07.006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041708369
102 rdf:type schema:CreativeWork
103 https://doi.org/10.1109/72.548176 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061218830
104 rdf:type schema:CreativeWork
105 https://doi.org/10.1109/cnna.1992.274330 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086276533
106 rdf:type schema:CreativeWork
107 https://doi.org/10.1109/tcsii.2003.810486 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061568797
108 rdf:type schema:CreativeWork
109 https://doi.org/10.1109/tnn.2003.813844 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061716601
110 rdf:type schema:CreativeWork
111 https://doi.org/10.1109/tnn.2010.2082561 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061717794
112 rdf:type schema:CreativeWork
113 https://doi.org/10.1162/0899766053429381 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024420009
114 rdf:type schema:CreativeWork
115 https://www.grid.ac/institutes/grid.264762.3 schema:alternateName Texas A&M University – Texarkana
116 schema:name Texas A&M University-Texarkana, 7101 University Ave, 75503, Texarkana, TX, USA
117 rdf:type schema:Organization
 




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


...