Multi-criteria decision making based architecture selection for single-hidden layer feedforward neural networks View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-04

AUTHORS

Ran Wang, Haoran Xie, Jiqiang Feng, Fu Lee Wang, Chen Xu

ABSTRACT

Architecture selection is a fundamental problem in artificial neural networks, which could be treated as a decision making process that evaluates, ranks, and makes choices from a set of network structures. Traditional methods evaluate a network structure by designing a criterion based on a validation model or an error bound model. On one hand, the time complexity of a validation model is usually high; on the other hand, different validation models or error bound models may lead to different (even conflicting) results, which post challenges to the traditional single criterion-based architecture selection methods. In the area of decision making, many problems employed multiple criteria since the performance is better than using a single criterion. In this paper, we propose a multi-criteria decision making based architecture selection algorithm for single-hidden layer feedforward neural networks trained by extreme learning machine. Two criteria are incorporated into the selection process, i.e., training accuracy and the Q-value estimated by the localized generalization error model. The training accuracy reflects the capability of the model on correctly categorizing the known samples, and the Q-value estimated by localized generalization error model reflects the size of the neighbourhood of training samples in which the model can predict unseen samples with confidence. By achieving a trade-off between these two criteria, a new architecture selection algorithm is proposed. Experimental comparisons demonstrate the feasibility and effectiveness of the proposed method. More... »

PAGES

655-666

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s13042-017-0746-9

DOI

http://dx.doi.org/10.1007/s13042-017-0746-9

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1092766692


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": "Shenzhen University", 
          "id": "https://www.grid.ac/institutes/grid.263488.3", 
          "name": [
            "College of Mathematics and Statistics, Shenzhen University, 518060, Shenzhen, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Ran", 
        "id": "sg:person.01223171431.25", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01223171431.25"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Education University of Hong Kong", 
          "id": "https://www.grid.ac/institutes/grid.419993.f", 
          "name": [
            "Department of Mathematics and Information Technology, The Education University of Hong Kong, Hong Kong, Hong Kong"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Xie", 
        "givenName": "Haoran", 
        "id": "sg:person.013223104263.63", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013223104263.63"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Shenzhen University", 
          "id": "https://www.grid.ac/institutes/grid.263488.3", 
          "name": [
            "College of Mathematics and Statistics, Shenzhen University, 518060, Shenzhen, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Feng", 
        "givenName": "Jiqiang", 
        "id": "sg:person.014161626063.09", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014161626063.09"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Caritas Institute of Higher Education", 
          "id": "https://www.grid.ac/institutes/grid.469890.a", 
          "name": [
            "Caritas Institute of Higher Education, Hong Kong, Hong Kong"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Fu Lee", 
        "id": "sg:person.012750674362.62", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012750674362.62"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Shenzhen University", 
          "id": "https://www.grid.ac/institutes/grid.263488.3", 
          "name": [
            "College of Mathematics and Statistics, Shenzhen University, 518060, Shenzhen, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Xu", 
        "givenName": "Chen", 
        "id": "sg:person.012010640735.32", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012010640735.32"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.neucom.2011.12.046", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000299405"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2015.10.036", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1001300158"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patcog.2014.03.011", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004491449"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsmcb.2011.2168604", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006047450"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.ins.2008.10.012", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016011377"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0965-9978(00)00110-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016696104"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.dss.2011.05.003", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016990898"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/evco.1994.2.3.221", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026010259"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00521-015-1994-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026867133", 
          "https://doi.org/10.1007/s00521-015-1994-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1029258068", 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1029258068", 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s13042-010-0009-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030190707", 
          "https://doi.org/10.1007/s13042-010-0009-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0893-6080(01)00061-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030956040"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0377-2217(00)00184-3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1031857346"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00521-016-2510-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033241208", 
          "https://doi.org/10.1007/s00521-016-2510-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00521-016-2510-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033241208", 
          "https://doi.org/10.1007/s00521-016-2510-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2015.05.139", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033813457"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2007.05.005", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035131567"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00500-012-0829-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037460514", 
          "https://doi.org/10.1007/s00500-012-0829-1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00500-012-0829-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037460514", 
          "https://doi.org/10.1007/s00500-012-0829-1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(94)00089-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041532522"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/b:grup.0000042894.00775.75", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041554117", 
          "https://doi.org/10.1023/b:grup.0000042894.00775.75"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neunet.2014.10.001", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045581577"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-45356-3_82", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047358338", 
          "https://doi.org/10.1007/3-540-45356-3_82"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-45356-3_82", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047358338", 
          "https://doi.org/10.1007/3-540-45356-3_82"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neunet.2016.01.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051284072"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.ins.2009.06.001", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051930592"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/01621459.1963.10500830", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1058299773"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/21.247900", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061121706"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tnn.2007.894058", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061717205"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1142/s0218488513400114", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062977425"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1051/ro/1993270100451", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1083714017"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/confluence.2017.7943123", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094180965"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cec.2016.7743903", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095336950"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icmlc.2004.1384590", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095401175"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/roma.2016.7847805", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095821571"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/1218955.1219030", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099221259"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/1218955.1219030", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099221259"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-04", 
    "datePublishedReg": "2019-04-01", 
    "description": "Architecture selection is a fundamental problem in artificial neural networks, which could be treated as a decision making process that evaluates, ranks, and makes choices from a set of network structures. Traditional methods evaluate a network structure by designing a criterion based on a validation model or an error bound model. On one hand, the time complexity of a validation model is usually high; on the other hand, different validation models or error bound models may lead to different (even conflicting) results, which post challenges to the traditional single criterion-based architecture selection methods. In the area of decision making, many problems employed multiple criteria since the performance is better than using a single criterion. In this paper, we propose a multi-criteria decision making based architecture selection algorithm for single-hidden layer feedforward neural networks trained by extreme learning machine. Two criteria are incorporated into the selection process, i.e., training accuracy and the Q-value estimated by the localized generalization error model. The training accuracy reflects the capability of the model on correctly categorizing the known samples, and the Q-value estimated by localized generalization error model reflects the size of the neighbourhood of training samples in which the model can predict unseen samples with confidence. By achieving a trade-off between these two criteria, a new architecture selection algorithm is proposed. Experimental comparisons demonstrate the feasibility and effectiveness of the proposed method.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s13042-017-0746-9", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1136696", 
        "issn": [
          "1868-8071", 
          "1868-808X"
        ], 
        "name": "International Journal of Machine Learning and Cybernetics", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "4", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "10"
      }
    ], 
    "name": "Multi-criteria decision making based architecture selection for single-hidden layer feedforward neural networks", 
    "pagination": "655-666", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "67bd88282ef7c3f2f4944c6603c0e5089cd0eff55247bb2cab07abfbbb23e0d0"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s13042-017-0746-9"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1092766692"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s13042-017-0746-9", 
      "https://app.dimensions.ai/details/publication/pub.1092766692"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T12:53", 
    "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/v90/0000000364_0000000364/records_72843_00000000.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs13042-017-0746-9"
  }
]
 

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/s13042-017-0746-9'

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/s13042-017-0746-9'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s13042-017-0746-9'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s13042-017-0746-9'


 

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

199 TRIPLES      21 PREDICATES      60 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s13042-017-0746-9 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nc6a01ab5dc9f4e24991da25966468861
4 schema:citation sg:pub.10.1007/3-540-45356-3_82
5 sg:pub.10.1007/s00500-012-0829-1
6 sg:pub.10.1007/s00521-015-1994-9
7 sg:pub.10.1007/s00521-016-2510-6
8 sg:pub.10.1007/s13042-010-0009-5
9 sg:pub.10.1023/b:grup.0000042894.00775.75
10 https://app.dimensions.ai/details/publication/pub.1029258068
11 https://doi.org/10.1016/0893-6080(94)00089-5
12 https://doi.org/10.1016/j.dss.2011.05.003
13 https://doi.org/10.1016/j.ins.2008.10.012
14 https://doi.org/10.1016/j.ins.2009.06.001
15 https://doi.org/10.1016/j.neucom.2007.05.005
16 https://doi.org/10.1016/j.neucom.2011.12.046
17 https://doi.org/10.1016/j.neucom.2015.05.139
18 https://doi.org/10.1016/j.neucom.2015.10.036
19 https://doi.org/10.1016/j.neunet.2014.10.001
20 https://doi.org/10.1016/j.neunet.2016.01.002
21 https://doi.org/10.1016/j.patcog.2014.03.011
22 https://doi.org/10.1016/s0377-2217(00)00184-3
23 https://doi.org/10.1016/s0893-6080(01)00061-2
24 https://doi.org/10.1016/s0965-9978(00)00110-1
25 https://doi.org/10.1051/ro/1993270100451
26 https://doi.org/10.1080/01621459.1963.10500830
27 https://doi.org/10.1109/21.247900
28 https://doi.org/10.1109/cec.2016.7743903
29 https://doi.org/10.1109/confluence.2017.7943123
30 https://doi.org/10.1109/icmlc.2004.1384590
31 https://doi.org/10.1109/roma.2016.7847805
32 https://doi.org/10.1109/tnn.2007.894058
33 https://doi.org/10.1109/tsmcb.2011.2168604
34 https://doi.org/10.1142/s0218488513400114
35 https://doi.org/10.1162/evco.1994.2.3.221
36 https://doi.org/10.3115/1218955.1219030
37 schema:datePublished 2019-04
38 schema:datePublishedReg 2019-04-01
39 schema:description Architecture selection is a fundamental problem in artificial neural networks, which could be treated as a decision making process that evaluates, ranks, and makes choices from a set of network structures. Traditional methods evaluate a network structure by designing a criterion based on a validation model or an error bound model. On one hand, the time complexity of a validation model is usually high; on the other hand, different validation models or error bound models may lead to different (even conflicting) results, which post challenges to the traditional single criterion-based architecture selection methods. In the area of decision making, many problems employed multiple criteria since the performance is better than using a single criterion. In this paper, we propose a multi-criteria decision making based architecture selection algorithm for single-hidden layer feedforward neural networks trained by extreme learning machine. Two criteria are incorporated into the selection process, i.e., training accuracy and the Q-value estimated by the localized generalization error model. The training accuracy reflects the capability of the model on correctly categorizing the known samples, and the Q-value estimated by localized generalization error model reflects the size of the neighbourhood of training samples in which the model can predict unseen samples with confidence. By achieving a trade-off between these two criteria, a new architecture selection algorithm is proposed. Experimental comparisons demonstrate the feasibility and effectiveness of the proposed method.
40 schema:genre research_article
41 schema:inLanguage en
42 schema:isAccessibleForFree false
43 schema:isPartOf N2a48f4331fee42738f622fe220c4f806
44 N6827108391064b70a3fc657bda327a75
45 sg:journal.1136696
46 schema:name Multi-criteria decision making based architecture selection for single-hidden layer feedforward neural networks
47 schema:pagination 655-666
48 schema:productId N1388d17e40bb42b18312d27a71e0ef48
49 Na04162044f074626aafdbdaea2dd0571
50 Nd41847e6474242ac8696c860a9ed6c7f
51 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092766692
52 https://doi.org/10.1007/s13042-017-0746-9
53 schema:sdDatePublished 2019-04-11T12:53
54 schema:sdLicense https://scigraph.springernature.com/explorer/license/
55 schema:sdPublisher N75e34a12075a4d29b15e9bddf62c78c6
56 schema:url https://link.springer.com/10.1007%2Fs13042-017-0746-9
57 sgo:license sg:explorer/license/
58 sgo:sdDataset articles
59 rdf:type schema:ScholarlyArticle
60 N00f441330b2d47688842dc530ddd21f3 rdf:first sg:person.012750674362.62
61 rdf:rest N1154737bb42a4a5f89eee383236a5c3e
62 N016852718b794549be6e779744511e75 rdf:first sg:person.014161626063.09
63 rdf:rest N00f441330b2d47688842dc530ddd21f3
64 N1154737bb42a4a5f89eee383236a5c3e rdf:first sg:person.012010640735.32
65 rdf:rest rdf:nil
66 N1388d17e40bb42b18312d27a71e0ef48 schema:name doi
67 schema:value 10.1007/s13042-017-0746-9
68 rdf:type schema:PropertyValue
69 N2a48f4331fee42738f622fe220c4f806 schema:issueNumber 4
70 rdf:type schema:PublicationIssue
71 N5633da00af1844878ecc8c3f2e3a0ff6 rdf:first sg:person.013223104263.63
72 rdf:rest N016852718b794549be6e779744511e75
73 N6827108391064b70a3fc657bda327a75 schema:volumeNumber 10
74 rdf:type schema:PublicationVolume
75 N75e34a12075a4d29b15e9bddf62c78c6 schema:name Springer Nature - SN SciGraph project
76 rdf:type schema:Organization
77 Na04162044f074626aafdbdaea2dd0571 schema:name dimensions_id
78 schema:value pub.1092766692
79 rdf:type schema:PropertyValue
80 Nc6a01ab5dc9f4e24991da25966468861 rdf:first sg:person.01223171431.25
81 rdf:rest N5633da00af1844878ecc8c3f2e3a0ff6
82 Nd41847e6474242ac8696c860a9ed6c7f schema:name readcube_id
83 schema:value 67bd88282ef7c3f2f4944c6603c0e5089cd0eff55247bb2cab07abfbbb23e0d0
84 rdf:type schema:PropertyValue
85 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
86 schema:name Information and Computing Sciences
87 rdf:type schema:DefinedTerm
88 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
89 schema:name Artificial Intelligence and Image Processing
90 rdf:type schema:DefinedTerm
91 sg:journal.1136696 schema:issn 1868-8071
92 1868-808X
93 schema:name International Journal of Machine Learning and Cybernetics
94 rdf:type schema:Periodical
95 sg:person.012010640735.32 schema:affiliation https://www.grid.ac/institutes/grid.263488.3
96 schema:familyName Xu
97 schema:givenName Chen
98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012010640735.32
99 rdf:type schema:Person
100 sg:person.01223171431.25 schema:affiliation https://www.grid.ac/institutes/grid.263488.3
101 schema:familyName Wang
102 schema:givenName Ran
103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01223171431.25
104 rdf:type schema:Person
105 sg:person.012750674362.62 schema:affiliation https://www.grid.ac/institutes/grid.469890.a
106 schema:familyName Wang
107 schema:givenName Fu Lee
108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012750674362.62
109 rdf:type schema:Person
110 sg:person.013223104263.63 schema:affiliation https://www.grid.ac/institutes/grid.419993.f
111 schema:familyName Xie
112 schema:givenName Haoran
113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013223104263.63
114 rdf:type schema:Person
115 sg:person.014161626063.09 schema:affiliation https://www.grid.ac/institutes/grid.263488.3
116 schema:familyName Feng
117 schema:givenName Jiqiang
118 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014161626063.09
119 rdf:type schema:Person
120 sg:pub.10.1007/3-540-45356-3_82 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047358338
121 https://doi.org/10.1007/3-540-45356-3_82
122 rdf:type schema:CreativeWork
123 sg:pub.10.1007/s00500-012-0829-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037460514
124 https://doi.org/10.1007/s00500-012-0829-1
125 rdf:type schema:CreativeWork
126 sg:pub.10.1007/s00521-015-1994-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026867133
127 https://doi.org/10.1007/s00521-015-1994-9
128 rdf:type schema:CreativeWork
129 sg:pub.10.1007/s00521-016-2510-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033241208
130 https://doi.org/10.1007/s00521-016-2510-6
131 rdf:type schema:CreativeWork
132 sg:pub.10.1007/s13042-010-0009-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030190707
133 https://doi.org/10.1007/s13042-010-0009-5
134 rdf:type schema:CreativeWork
135 sg:pub.10.1023/b:grup.0000042894.00775.75 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041554117
136 https://doi.org/10.1023/b:grup.0000042894.00775.75
137 rdf:type schema:CreativeWork
138 https://app.dimensions.ai/details/publication/pub.1029258068 schema:CreativeWork
139 https://doi.org/10.1016/0893-6080(94)00089-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041532522
140 rdf:type schema:CreativeWork
141 https://doi.org/10.1016/j.dss.2011.05.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016990898
142 rdf:type schema:CreativeWork
143 https://doi.org/10.1016/j.ins.2008.10.012 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016011377
144 rdf:type schema:CreativeWork
145 https://doi.org/10.1016/j.ins.2009.06.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051930592
146 rdf:type schema:CreativeWork
147 https://doi.org/10.1016/j.neucom.2007.05.005 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035131567
148 rdf:type schema:CreativeWork
149 https://doi.org/10.1016/j.neucom.2011.12.046 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000299405
150 rdf:type schema:CreativeWork
151 https://doi.org/10.1016/j.neucom.2015.05.139 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033813457
152 rdf:type schema:CreativeWork
153 https://doi.org/10.1016/j.neucom.2015.10.036 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001300158
154 rdf:type schema:CreativeWork
155 https://doi.org/10.1016/j.neunet.2014.10.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045581577
156 rdf:type schema:CreativeWork
157 https://doi.org/10.1016/j.neunet.2016.01.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051284072
158 rdf:type schema:CreativeWork
159 https://doi.org/10.1016/j.patcog.2014.03.011 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004491449
160 rdf:type schema:CreativeWork
161 https://doi.org/10.1016/s0377-2217(00)00184-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031857346
162 rdf:type schema:CreativeWork
163 https://doi.org/10.1016/s0893-6080(01)00061-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030956040
164 rdf:type schema:CreativeWork
165 https://doi.org/10.1016/s0965-9978(00)00110-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016696104
166 rdf:type schema:CreativeWork
167 https://doi.org/10.1051/ro/1993270100451 schema:sameAs https://app.dimensions.ai/details/publication/pub.1083714017
168 rdf:type schema:CreativeWork
169 https://doi.org/10.1080/01621459.1963.10500830 schema:sameAs https://app.dimensions.ai/details/publication/pub.1058299773
170 rdf:type schema:CreativeWork
171 https://doi.org/10.1109/21.247900 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061121706
172 rdf:type schema:CreativeWork
173 https://doi.org/10.1109/cec.2016.7743903 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095336950
174 rdf:type schema:CreativeWork
175 https://doi.org/10.1109/confluence.2017.7943123 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094180965
176 rdf:type schema:CreativeWork
177 https://doi.org/10.1109/icmlc.2004.1384590 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095401175
178 rdf:type schema:CreativeWork
179 https://doi.org/10.1109/roma.2016.7847805 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095821571
180 rdf:type schema:CreativeWork
181 https://doi.org/10.1109/tnn.2007.894058 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061717205
182 rdf:type schema:CreativeWork
183 https://doi.org/10.1109/tsmcb.2011.2168604 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006047450
184 rdf:type schema:CreativeWork
185 https://doi.org/10.1142/s0218488513400114 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062977425
186 rdf:type schema:CreativeWork
187 https://doi.org/10.1162/evco.1994.2.3.221 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026010259
188 rdf:type schema:CreativeWork
189 https://doi.org/10.3115/1218955.1219030 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099221259
190 rdf:type schema:CreativeWork
191 https://www.grid.ac/institutes/grid.263488.3 schema:alternateName Shenzhen University
192 schema:name College of Mathematics and Statistics, Shenzhen University, 518060, Shenzhen, China
193 rdf:type schema:Organization
194 https://www.grid.ac/institutes/grid.419993.f schema:alternateName Education University of Hong Kong
195 schema:name Department of Mathematics and Information Technology, The Education University of Hong Kong, Hong Kong, Hong Kong
196 rdf:type schema:Organization
197 https://www.grid.ac/institutes/grid.469890.a schema:alternateName Caritas Institute of Higher Education
198 schema:name Caritas Institute of Higher Education, Hong Kong, Hong Kong
199 rdf:type schema:Organization
 




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


...