Incremental extreme learning machine based on deep feature embedded View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2016-02

AUTHORS

Jian Zhang, Shifei Ding, Nan Zhang, Zhongzhi Shi

ABSTRACT

Extreme learning machine (ELM) algorithm is used to train Single-hidden Layer Feed forward Neural Networks. And Deep Belief Network (DBN) is based on Restricted Boltzmann Machine (RBM). The conventional DBN algorithm has some insufficiencies, i.e., Contrastive Divergence (CD) Algorithm is not an ideal approximation method to Maximum Likelihood Estimation. And bad parameters selected in RBM algorithm will produce a bad initialization in DBN model so that we will spend more training time and get a low classification accuracy. To solve the problems above, we summarize the features of extreme learning machine and deep belief networks, and then propose Incremental extreme learning machine based on Deep Feature Embedded algorithm which combines the deep feature extracting ability of Deep Learning Networks with the feature mapping ability of extreme learning machine. Firstly, we introduce Manifold Regularization to our model to attenuate the complexity of probability distribution. Secondly, we introduce the semi-restricted Boltzmann machine (SRBM) to our algorithm, and build a deep belief network based on SRBM. Thirdly, we introduce the thought of incremental feature mapping in ELM to the classifier of DBN model. Finally, we show validity of the algorithm by experiments. More... »

PAGES

111-120

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s13042-015-0419-5

DOI

http://dx.doi.org/10.1007/s13042-015-0419-5

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1007452930


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": "Institute Of Computing Technology", 
          "id": "https://www.grid.ac/institutes/grid.424936.e", 
          "name": [
            "School of Computer Science and Technology, China University of Mining and Technology, 221116, Xuzhou, China", 
            "Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, 100190, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhang", 
        "givenName": "Jian", 
        "id": "sg:person.07751313503.04", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07751313503.04"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Institute Of Computing Technology", 
          "id": "https://www.grid.ac/institutes/grid.424936.e", 
          "name": [
            "School of Computer Science and Technology, China University of Mining and Technology, 221116, Xuzhou, China", 
            "Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, 100190, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ding", 
        "givenName": "Shifei", 
        "id": "sg:person.015633117341.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015633117341.65"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Institute Of Computing Technology", 
          "id": "https://www.grid.ac/institutes/grid.424936.e", 
          "name": [
            "School of Computer Science and Technology, China University of Mining and Technology, 221116, Xuzhou, China", 
            "Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, 100190, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhang", 
        "givenName": "Nan", 
        "id": "sg:person.010670270012.43", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010670270012.43"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Institute Of Computing Technology", 
          "id": "https://www.grid.ac/institutes/grid.424936.e", 
          "name": [
            "Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, 100190, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Shi", 
        "givenName": "Zhongzhi", 
        "id": "sg:person.013526271652.94", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013526271652.94"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1162/neco.2006.18.7.1527", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004707137"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/089976602760128018", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007443228"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00521-013-1385-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1012600305", 
          "https://doi.org/10.1007/s00521-013-1385-z"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2014.04.067", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017699928"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1390156.1390290", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018298072"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2010.12.034", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021486101"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1553374.1553506", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033048871"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/j.1756-8765.2010.01109.x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034172924"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2001269.2001295", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037570815"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2005.12.126", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038265102"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2011.12.053", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045435951"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2015.07.058", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045566579"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2012.12.063", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1046848334"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tcyb.2014.2307349", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061579639"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tnn.2006.875977", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061717036"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tnn.2006.875977", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061717036"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2009.5206577", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093365752"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/ijcnn.2004.1380068", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094360980"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2016-02", 
    "datePublishedReg": "2016-02-01", 
    "description": "Extreme learning machine (ELM) algorithm is used to train Single-hidden Layer Feed forward Neural Networks. And Deep Belief Network (DBN) is based on Restricted Boltzmann Machine (RBM). The conventional DBN algorithm has some insufficiencies, i.e., Contrastive Divergence (CD) Algorithm is not an ideal approximation method to Maximum Likelihood Estimation. And bad parameters selected in RBM algorithm will produce a bad initialization in DBN model so that we will spend more training time and get a low classification accuracy. To solve the problems above, we summarize the features of extreme learning machine and deep belief networks, and then propose Incremental extreme learning machine based on Deep Feature Embedded algorithm which combines the deep feature extracting ability of Deep Learning Networks with the feature mapping ability of extreme learning machine. Firstly, we introduce Manifold Regularization to our model to attenuate the complexity of probability distribution. Secondly, we introduce the semi-restricted Boltzmann machine (SRBM) to our algorithm, and build a deep belief network based on SRBM. Thirdly, we introduce the thought of incremental feature mapping in ELM to the classifier of DBN model. Finally, we show validity of the algorithm by experiments.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s13042-015-0419-5", 
    "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": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "7"
      }
    ], 
    "name": "Incremental extreme learning machine based on deep feature embedded", 
    "pagination": "111-120", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "237fdf96985790e35edf38d4cdbfd472174ae79ca2d85041081c56c9afb85e46"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s13042-015-0419-5"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1007452930"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s13042-015-0419-5", 
      "https://app.dimensions.ai/details/publication/pub.1007452930"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-10T19:10", 
    "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_8678_00000520.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1007%2Fs13042-015-0419-5"
  }
]
 

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/s13042-015-0419-5'

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/s13042-015-0419-5'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s13042-015-0419-5'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s13042-015-0419-5'


 

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

135 TRIPLES      21 PREDICATES      44 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s13042-015-0419-5 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N2b79bde363fd4e2a99f767639f2a2fab
4 schema:citation sg:pub.10.1007/s00521-013-1385-z
5 https://doi.org/10.1016/j.neucom.2005.12.126
6 https://doi.org/10.1016/j.neucom.2010.12.034
7 https://doi.org/10.1016/j.neucom.2011.12.053
8 https://doi.org/10.1016/j.neucom.2012.12.063
9 https://doi.org/10.1016/j.neucom.2014.04.067
10 https://doi.org/10.1016/j.neucom.2015.07.058
11 https://doi.org/10.1109/cvpr.2009.5206577
12 https://doi.org/10.1109/ijcnn.2004.1380068
13 https://doi.org/10.1109/tcyb.2014.2307349
14 https://doi.org/10.1109/tnn.2006.875977
15 https://doi.org/10.1111/j.1756-8765.2010.01109.x
16 https://doi.org/10.1145/1390156.1390290
17 https://doi.org/10.1145/1553374.1553506
18 https://doi.org/10.1145/2001269.2001295
19 https://doi.org/10.1162/089976602760128018
20 https://doi.org/10.1162/neco.2006.18.7.1527
21 schema:datePublished 2016-02
22 schema:datePublishedReg 2016-02-01
23 schema:description Extreme learning machine (ELM) algorithm is used to train Single-hidden Layer Feed forward Neural Networks. And Deep Belief Network (DBN) is based on Restricted Boltzmann Machine (RBM). The conventional DBN algorithm has some insufficiencies, i.e., Contrastive Divergence (CD) Algorithm is not an ideal approximation method to Maximum Likelihood Estimation. And bad parameters selected in RBM algorithm will produce a bad initialization in DBN model so that we will spend more training time and get a low classification accuracy. To solve the problems above, we summarize the features of extreme learning machine and deep belief networks, and then propose Incremental extreme learning machine based on Deep Feature Embedded algorithm which combines the deep feature extracting ability of Deep Learning Networks with the feature mapping ability of extreme learning machine. Firstly, we introduce Manifold Regularization to our model to attenuate the complexity of probability distribution. Secondly, we introduce the semi-restricted Boltzmann machine (SRBM) to our algorithm, and build a deep belief network based on SRBM. Thirdly, we introduce the thought of incremental feature mapping in ELM to the classifier of DBN model. Finally, we show validity of the algorithm by experiments.
24 schema:genre research_article
25 schema:inLanguage en
26 schema:isAccessibleForFree false
27 schema:isPartOf N356465c4ac5b4439a8beaaee20a074e4
28 N6065b4fc43e7440da01563e034fb29f7
29 sg:journal.1136696
30 schema:name Incremental extreme learning machine based on deep feature embedded
31 schema:pagination 111-120
32 schema:productId N211d531f787b437fa9d4516f59d4e7b0
33 N8f4e7e929b55401d8b110999138e7d6b
34 Nac7bbd1e8f5a43a9b9ff0928416bdba0
35 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007452930
36 https://doi.org/10.1007/s13042-015-0419-5
37 schema:sdDatePublished 2019-04-10T19:10
38 schema:sdLicense https://scigraph.springernature.com/explorer/license/
39 schema:sdPublisher Na6462646d53a4960b7f60d25e2727f2e
40 schema:url http://link.springer.com/10.1007%2Fs13042-015-0419-5
41 sgo:license sg:explorer/license/
42 sgo:sdDataset articles
43 rdf:type schema:ScholarlyArticle
44 N211d531f787b437fa9d4516f59d4e7b0 schema:name doi
45 schema:value 10.1007/s13042-015-0419-5
46 rdf:type schema:PropertyValue
47 N2b79bde363fd4e2a99f767639f2a2fab rdf:first sg:person.07751313503.04
48 rdf:rest N324c5630cd284c4b96c1de4cf2d9d101
49 N324c5630cd284c4b96c1de4cf2d9d101 rdf:first sg:person.015633117341.65
50 rdf:rest N6d041838a65e411b97a914e33b16b7b8
51 N356465c4ac5b4439a8beaaee20a074e4 schema:volumeNumber 7
52 rdf:type schema:PublicationVolume
53 N6065b4fc43e7440da01563e034fb29f7 schema:issueNumber 1
54 rdf:type schema:PublicationIssue
55 N6d041838a65e411b97a914e33b16b7b8 rdf:first sg:person.010670270012.43
56 rdf:rest Nb989169abd504bce8d21da108e743700
57 N8f4e7e929b55401d8b110999138e7d6b schema:name readcube_id
58 schema:value 237fdf96985790e35edf38d4cdbfd472174ae79ca2d85041081c56c9afb85e46
59 rdf:type schema:PropertyValue
60 Na6462646d53a4960b7f60d25e2727f2e schema:name Springer Nature - SN SciGraph project
61 rdf:type schema:Organization
62 Nac7bbd1e8f5a43a9b9ff0928416bdba0 schema:name dimensions_id
63 schema:value pub.1007452930
64 rdf:type schema:PropertyValue
65 Nb989169abd504bce8d21da108e743700 rdf:first sg:person.013526271652.94
66 rdf:rest rdf:nil
67 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
68 schema:name Information and Computing Sciences
69 rdf:type schema:DefinedTerm
70 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
71 schema:name Artificial Intelligence and Image Processing
72 rdf:type schema:DefinedTerm
73 sg:journal.1136696 schema:issn 1868-8071
74 1868-808X
75 schema:name International Journal of Machine Learning and Cybernetics
76 rdf:type schema:Periodical
77 sg:person.010670270012.43 schema:affiliation https://www.grid.ac/institutes/grid.424936.e
78 schema:familyName Zhang
79 schema:givenName Nan
80 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010670270012.43
81 rdf:type schema:Person
82 sg:person.013526271652.94 schema:affiliation https://www.grid.ac/institutes/grid.424936.e
83 schema:familyName Shi
84 schema:givenName Zhongzhi
85 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013526271652.94
86 rdf:type schema:Person
87 sg:person.015633117341.65 schema:affiliation https://www.grid.ac/institutes/grid.424936.e
88 schema:familyName Ding
89 schema:givenName Shifei
90 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015633117341.65
91 rdf:type schema:Person
92 sg:person.07751313503.04 schema:affiliation https://www.grid.ac/institutes/grid.424936.e
93 schema:familyName Zhang
94 schema:givenName Jian
95 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07751313503.04
96 rdf:type schema:Person
97 sg:pub.10.1007/s00521-013-1385-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1012600305
98 https://doi.org/10.1007/s00521-013-1385-z
99 rdf:type schema:CreativeWork
100 https://doi.org/10.1016/j.neucom.2005.12.126 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038265102
101 rdf:type schema:CreativeWork
102 https://doi.org/10.1016/j.neucom.2010.12.034 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021486101
103 rdf:type schema:CreativeWork
104 https://doi.org/10.1016/j.neucom.2011.12.053 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045435951
105 rdf:type schema:CreativeWork
106 https://doi.org/10.1016/j.neucom.2012.12.063 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046848334
107 rdf:type schema:CreativeWork
108 https://doi.org/10.1016/j.neucom.2014.04.067 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017699928
109 rdf:type schema:CreativeWork
110 https://doi.org/10.1016/j.neucom.2015.07.058 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045566579
111 rdf:type schema:CreativeWork
112 https://doi.org/10.1109/cvpr.2009.5206577 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093365752
113 rdf:type schema:CreativeWork
114 https://doi.org/10.1109/ijcnn.2004.1380068 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094360980
115 rdf:type schema:CreativeWork
116 https://doi.org/10.1109/tcyb.2014.2307349 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061579639
117 rdf:type schema:CreativeWork
118 https://doi.org/10.1109/tnn.2006.875977 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061717036
119 rdf:type schema:CreativeWork
120 https://doi.org/10.1111/j.1756-8765.2010.01109.x schema:sameAs https://app.dimensions.ai/details/publication/pub.1034172924
121 rdf:type schema:CreativeWork
122 https://doi.org/10.1145/1390156.1390290 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018298072
123 rdf:type schema:CreativeWork
124 https://doi.org/10.1145/1553374.1553506 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033048871
125 rdf:type schema:CreativeWork
126 https://doi.org/10.1145/2001269.2001295 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037570815
127 rdf:type schema:CreativeWork
128 https://doi.org/10.1162/089976602760128018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007443228
129 rdf:type schema:CreativeWork
130 https://doi.org/10.1162/neco.2006.18.7.1527 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004707137
131 rdf:type schema:CreativeWork
132 https://www.grid.ac/institutes/grid.424936.e schema:alternateName Institute Of Computing Technology
133 schema:name Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, 100190, Beijing, China
134 School of Computer Science and Technology, China University of Mining and Technology, 221116, Xuzhou, China
135 rdf:type schema:Organization
 




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


...