DEVDAN: Deep evolving denoising autoencoder

The Denoising Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves in-depth study because it characterizes a fixed network capacity which cannot adapt to rapidly changing environments....

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Neurocomputing (Amsterdam) Ročník 390; s. 297 - 314
Hlavní autori: Ashfahani, Andri, Pratama, Mahardhika, Lughofer, Edwin, Ong, Yew-Soon
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 21.05.2020
Predmet:
ISSN:0925-2312, 1872-8286
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract The Denoising Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves in-depth study because it characterizes a fixed network capacity which cannot adapt to rapidly changing environments. Deep evolving denoising autoencoder (DEVDAN), is proposed in this paper. It features an open structure in the generative phase and the discriminative phase where the hidden units can be automatically added and discarded on the fly. The generative phase refines the predictive performance of discriminative model exploiting unlabeled data. Furthermore, DEVDAN is free of the problem-specific threshold and works fully in the single-pass learning fashion. We show that DEVDAN can find competitive network architecture compared with state-of-the-art methods on the classification task using ten prominent datasets simulated under the prequential test-then-train protocol.
AbstractList The Denoising Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves in-depth study because it characterizes a fixed network capacity which cannot adapt to rapidly changing environments. Deep evolving denoising autoencoder (DEVDAN), is proposed in this paper. It features an open structure in the generative phase and the discriminative phase where the hidden units can be automatically added and discarded on the fly. The generative phase refines the predictive performance of discriminative model exploiting unlabeled data. Furthermore, DEVDAN is free of the problem-specific threshold and works fully in the single-pass learning fashion. We show that DEVDAN can find competitive network architecture compared with state-of-the-art methods on the classification task using ten prominent datasets simulated under the prequential test-then-train protocol.
Author Ashfahani, Andri
Ong, Yew-Soon
Lughofer, Edwin
Pratama, Mahardhika
Author_xml – sequence: 1
  givenname: Andri
  orcidid: 0000-0002-7126-4412
  surname: Ashfahani
  fullname: Ashfahani, Andri
  organization: School of Computer Science and Engineering, Nanyang Technological University, Singapore
– sequence: 2
  givenname: Mahardhika
  orcidid: 0000-0001-6531-5087
  surname: Pratama
  fullname: Pratama, Mahardhika
  email: mpratama@ntu.edu.sg
  organization: School of Computer Science and Engineering, Nanyang Technological University, Singapore
– sequence: 3
  givenname: Edwin
  surname: Lughofer
  fullname: Lughofer, Edwin
  organization: Johannes Kepler University Linz, Austria
– sequence: 4
  givenname: Yew-Soon
  orcidid: 0000-0002-4480-169X
  surname: Ong
  fullname: Ong, Yew-Soon
  organization: School of Computer Science and Engineering, Nanyang Technological University, Singapore
BookMark eNqFj01LAzEURYNUsK3-Axfdy4wvSScz04VQ2voBRTfqNmTevJGUNinJdMB_3yl15UJX774L58IZsYHzjhi75ZBy4Op-kzo6oN-lAniZQt636oINeZGLpBCFGrAhlCJLhOTiio1i3ADwnItyyO6Wq8_l_HU2WRLtJ9T5bWfd16Qm5208JXNoPTn0NYVrdtmYbaSbnztmH4-r98Vzsn57elnM1wlKUG2SQUHTrASBUjVFbkzWYG0aI0tCQlEWHCUhVEpVEinD_qdK1RVlBgUZKcdsdt7F4GMM1Gi0rWmtd20wdqs56JO23uiztj5pa8j7VvXw9Be8D3Znwvd_2MMZo16ssxR0RNt7U20DYatrb_8eOAJneXba
CitedBy_id crossref_primary_10_1016_j_ipm_2023_103532
crossref_primary_10_3390_app13010287
crossref_primary_10_1016_j_ins_2021_11_047
crossref_primary_10_1002_cpe_8034
crossref_primary_10_3390_s22041522
crossref_primary_10_1016_j_expthermflusci_2024_111195
crossref_primary_10_1016_j_ins_2021_09_031
crossref_primary_10_1016_j_ins_2021_05_018
crossref_primary_10_1016_j_neucom_2021_04_112
crossref_primary_10_1007_s00500_021_05995_9
crossref_primary_10_1049_2023_5566781
crossref_primary_10_3390_app13116515
crossref_primary_10_1007_s00521_023_08459_3
crossref_primary_10_1109_TNNLS_2023_3331506
crossref_primary_10_1155_2023_6048087
crossref_primary_10_1016_j_ins_2023_119411
crossref_primary_10_1080_15366367_2023_2246112
crossref_primary_10_1007_s00521_021_05912_z
crossref_primary_10_1007_s00521_021_05890_2
crossref_primary_10_1016_j_engappai_2024_109105
crossref_primary_10_1016_j_ins_2021_11_038
crossref_primary_10_3390_rs13091761
crossref_primary_10_1016_j_asoc_2023_110053
crossref_primary_10_1007_s00542_022_05252_5
crossref_primary_10_1007_s10489_020_01869_z
crossref_primary_10_1016_j_neucom_2023_126352
crossref_primary_10_1007_s00521_021_06324_9
crossref_primary_10_3390_data6060055
crossref_primary_10_1007_s00521_020_05350_3
crossref_primary_10_1007_s00521_020_05503_4
crossref_primary_10_3390_rs14030682
crossref_primary_10_1016_j_scriptamat_2024_116315
crossref_primary_10_3390_s20143903
crossref_primary_10_1007_s10489_020_02058_8
crossref_primary_10_1145_3494832
crossref_primary_10_1109_TFUZZ_2022_3179148
crossref_primary_10_3390_app131910994
crossref_primary_10_1145_3427476
crossref_primary_10_1007_s12530_020_09350_5
crossref_primary_10_1109_JSTARS_2025_3568715
crossref_primary_10_1016_j_ins_2021_06_075
crossref_primary_10_1007_s00521_021_05787_0
crossref_primary_10_1007_s12530_021_09398_x
crossref_primary_10_1177_21582440231182060
crossref_primary_10_1016_j_asoc_2021_107255
crossref_primary_10_1007_s13534_024_00425_9
crossref_primary_10_1016_j_flowmeasinst_2021_102009
crossref_primary_10_3389_frai_2023_1048010
crossref_primary_10_1109_TAI_2021_3067574
crossref_primary_10_1109_TAI_2024_3363116
crossref_primary_10_1007_s00521_020_05201_1
crossref_primary_10_1109_ACCESS_2021_3086529
crossref_primary_10_1109_TNNLS_2022_3163362
crossref_primary_10_3390_s21154968
crossref_primary_10_1007_s10489_020_02150_z
crossref_primary_10_1016_j_cmpb_2024_108478
crossref_primary_10_1016_j_comcom_2021_03_004
crossref_primary_10_1007_s10489_023_04694_2
crossref_primary_10_1016_j_inffus_2023_101945
crossref_primary_10_1109_JIOT_2024_3392329
crossref_primary_10_1007_s10772_021_09851_x
crossref_primary_10_1109_TETCI_2024_3358377
crossref_primary_10_3390_info16030222
crossref_primary_10_1016_j_ins_2024_121762
crossref_primary_10_3390_app14219758
crossref_primary_10_1002_qj_5009
crossref_primary_10_1109_TPWRS_2022_3204176
crossref_primary_10_3390_app15126455
crossref_primary_10_1016_j_knosys_2022_110172
crossref_primary_10_1016_j_ins_2024_120799
Cites_doi 10.1109/TCYB.2017.2734043
10.1016/j.enbuild.2015.11.071
10.3233/IDA-2006-10103
10.1007/s10994-012-5320-9
10.1038/ncomms5308
10.1109/TFUZZ.2018.2796099
10.24963/ijcai.2018/369
10.1073/pnas.1611835114
10.1016/S0168-1699(99)00046-0
10.1145/2523813
10.1016/j.neucom.2017.08.043
10.1109/TNN.2011.2160459
10.1109/TPAMI.2013.50
10.1137/1.9781611975673.75
10.1007/978-3-030-05645-2_10
ContentType Journal Article
Copyright 2019 Elsevier B.V.
Copyright_xml – notice: 2019 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.neucom.2019.07.106
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-8286
EndPage 314
ExternalDocumentID 10_1016_j_neucom_2019_07_106
S0925231219314535
GroupedDBID ---
--K
--M
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JM
9JN
AABNK
AACTN
AADPK
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXLA
AAXUO
AAYFN
ABBOA
ABCQJ
ABFNM
ABJNI
ABMAC
ABYKQ
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
AEBSH
AEKER
AENEX
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGWIK
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
KOM
LG9
M41
MO0
MOBAO
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SDP
SES
SPC
SPCBC
SSN
SSV
SSZ
T5K
ZMT
~G-
29N
9DU
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
HLZ
HVGLF
HZ~
R2-
SBC
SEW
WUQ
XPP
~HD
ID FETCH-LOGICAL-c306t-508e45902c36f87aa5fcdafa39ecec2981c3ec0b66b3ce5c81ceb6dbe5ac2ea33
ISICitedReferencesCount 86
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000531728800010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0925-2312
IngestDate Tue Nov 18 22:00:30 EST 2025
Sat Nov 29 07:16:04 EST 2025
Fri Feb 23 02:47:40 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Denoising autoencoder
Incremental learning
Data streams
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-508e45902c36f87aa5fcdafa39ecec2981c3ec0b66b3ce5c81ceb6dbe5ac2ea33
ORCID 0000-0002-4480-169X
0000-0002-7126-4412
0000-0001-6531-5087
PageCount 18
ParticipantIDs crossref_citationtrail_10_1016_j_neucom_2019_07_106
crossref_primary_10_1016_j_neucom_2019_07_106
elsevier_sciencedirect_doi_10_1016_j_neucom_2019_07_106
PublicationCentury 2000
PublicationDate 2020-05-21
PublicationDateYYYYMMDD 2020-05-21
PublicationDate_xml – month: 05
  year: 2020
  text: 2020-05-21
  day: 21
PublicationDecade 2020
PublicationTitle Neurocomputing (Amsterdam)
PublicationYear 2020
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Murphy (bib0034) 2012
Street, Kim (bib0019) 2001
Gama (bib0005) 2010
Bifet, Holmes, Kirkby, Pfahringer (bib0020) 2010; 11
A. Ashfahani, M. Pratama, E. Lughofer, Q. Cai, H. Sheng, An Online RFID Localization in the Manufacturing Shopfloor, Springer International Publishing, pp. 287–309. doi
Stolfo, Fan, Lee, Prodromidis, Chan (bib0023) 2000
J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A.A. Rusu, K. Milan, J. Quan, T. Ramalho, A. Grabska-Barwinska, D. Hassabis, C. Clopath, D. Kumaran, R. Hadsell, Overcoming Catastrophic Forgetting in Neural Networks, 2016. Cite arxiv
Pratama, Pedrycz, Lughofer (bib0025) 2018; 26
D. Sahoo, Q.D. Pham, J. Lu, S.C. Hoi, Online Deep Learning: Learning Deep Neural Networks on the Fly, arXiv preprint arXiv
Goodfellow, Bengio, Courville (bib0038) 2016
M. Mohammadi, A.I. Al-Fuqaha, S. Sorour, M. Guizani, Deep Learning for iot Big Data and Streaming Analytics: A Survey, CoRR abs/1712.04301(2017).
Gama, Žliobaite, Bifet, Pechenizkiy, Bouchachia (bib0032) 2014; 46
Denil, Shakibi, Dinh, Ranzato, de Freitas (bib0003) 2013; 2
Srivastava, Masci, Kazerounian, Gomez, Schmidhuber (bib0016) 2013; 26
Wang, Li (bib0036) 2017; 47
A. Ashfahani, M. Pratama, Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments, Society for Industrial and Applied Mathematics, pp. 666–674.
Candanedo, Feldheim (bib0021) 2016; 112
J. Yoon, E. Yang, J. Lee, S. J. Hwang, Lifelong Learning with Dynamically Expandable Networks (2018).
Bengio, Lamblin, Popovici, Larochelle (bib0037) 2006
G. Hinton, O. Vinyals, J. Dean, Distilling the Knowledge in a Neural Network, ArXiv e-prints arXiv
Blackard, Dean (bib0018) 1999; 24
Jia, Shelhamer, Donahue, Karayev, Long, Girshick, Guadarrama, Darrell (bib0039) 2014
Bengio, Courville, Vincent (bib0006) 2013; 35
abs/1711.03705 (2017).
Hinton, Zemel (bib0033) 1993
Woolson (bib0040) 2007
(2015).
Alvares, Salzmann (bib0002) 2016
Pretorius, Kroon, Kamper (bib0007) 2018; 80
Jung, Goetz, Tewari (bib0026) 2017
Vincent, Larochelle, Bengio, Manzagol (bib0011) 2008
Baldi, Sadowski, Whiteson (bib0024) 2014; 5
.
Elwell, Polikar (bib0029) 2011; 22
A.A. Rusu, N.C. Rabinowitz, G. Desjardins, H. Soyer, J. Kirkpatrick, K. Kavukcuoglu, R. Pascanu, R. Hadsell, Progressive Neural Networks, CoRR abs/1606.04671 (2016).
Oza Nikunj, Russell Stuart (bib0027) 2001
Y. LeCun, C. Cortes, MNIST Handwritten Digit Database(2010).
Zeng, Zhang, Song, Liu, Li, Dobaie (bib0008) 2018; 273
Zhou, Sohn, Lee (bib0010) 2012; 22
M. Pratama, E. Dimla, E. Lughofer, W. Pedrycz, T. Tjahjowidodo, Online Tool Condition Monitoring Based on Parsimonious Ensemble+, CoRR abs/1711.01843 (2017).
Gama, Sebastião, Rodrigues (bib0031) 2013; 90
Lopez-Paz, Ranzato (bib0015) 2017; 30
Gama, Fernandes, Rocha (bib0035) 2006; 10
Goodfellow (10.1016/j.neucom.2019.07.106_bib0038) 2016
Jia (10.1016/j.neucom.2019.07.106_bib0039) 2014
Jung (10.1016/j.neucom.2019.07.106_bib0026) 2017
Murphy (10.1016/j.neucom.2019.07.106_bib0034) 2012
Elwell (10.1016/j.neucom.2019.07.106_bib0029) 2011; 22
Gama (10.1016/j.neucom.2019.07.106_bib0031) 2013; 90
Srivastava (10.1016/j.neucom.2019.07.106_sbref0010) 2013; 26
10.1016/j.neucom.2019.07.106_bib0014
Stolfo (10.1016/j.neucom.2019.07.106_bib0023) 2000
10.1016/j.neucom.2019.07.106_bib0017
Baldi (10.1016/j.neucom.2019.07.106_bib0024) 2014; 5
Bengio (10.1016/j.neucom.2019.07.106_bib0006) 2013; 35
10.1016/j.neucom.2019.07.106_bib0013
10.1016/j.neucom.2019.07.106_bib0012
Woolson (10.1016/j.neucom.2019.07.106_bib0040) 2007
Pretorius (10.1016/j.neucom.2019.07.106_sbref0005) 2018; 80
10.1016/j.neucom.2019.07.106_bib0030
Denil (10.1016/j.neucom.2019.07.106_bib0003) 2013; 2
Wang (10.1016/j.neucom.2019.07.106_bib0036) 2017; 47
Zhou (10.1016/j.neucom.2019.07.106_bib0010) 2012; 22
Vincent (10.1016/j.neucom.2019.07.106_bib0011) 2008
Bifet (10.1016/j.neucom.2019.07.106_sbref0013) 2010; 11
Gama (10.1016/j.neucom.2019.07.106_bib0035) 2006; 10
Pratama (10.1016/j.neucom.2019.07.106_bib0025) 2018; 26
Street (10.1016/j.neucom.2019.07.106_bib0019) 2001
Gama (10.1016/j.neucom.2019.07.106_bib0032) 2014; 46
Bengio (10.1016/j.neucom.2019.07.106_bib0037) 2006
Zeng (10.1016/j.neucom.2019.07.106_bib0008) 2018; 273
10.1016/j.neucom.2019.07.106_bib0009
10.1016/j.neucom.2019.07.106_bib0004
10.1016/j.neucom.2019.07.106_bib0028
10.1016/j.neucom.2019.07.106_bib0022
Oza Nikunj (10.1016/j.neucom.2019.07.106_bib0027) 2001
Alvares (10.1016/j.neucom.2019.07.106_bib0002) 2016
Blackard (10.1016/j.neucom.2019.07.106_bib0018) 1999; 24
Hinton (10.1016/j.neucom.2019.07.106_bib0033) 1993
10.1016/j.neucom.2019.07.106_bib0001
Gama (10.1016/j.neucom.2019.07.106_bib0005) 2010
Candanedo (10.1016/j.neucom.2019.07.106_bib0021) 2016; 112
Lopez-Paz (10.1016/j.neucom.2019.07.106_sbref0009) 2017; 30
References_xml – start-page: 675
  year: 2014
  end-page: 678
  ident: bib0039
  article-title: Caffe: Convolutional architecture for fast feature embedding
  publication-title: Proceedings of the 22nd ACM international conference on Multimedia
– start-page: 130
  year: 2000
  end-page: 144
  ident: bib0023
  article-title: Cost-based modeling for fraud and intrusion detection: Results from the jam project
  publication-title: Proceedings of the 2000 DARPA Information Survivability Conference and Exposition
– volume: 24
  start-page: 131
  year: 1999
  end-page: 151
  ident: bib0018
  article-title: Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables
  publication-title: Comput. Electron. Agric.
– reference: G. Hinton, O. Vinyals, J. Dean, Distilling the Knowledge in a Neural Network, ArXiv e-prints arXiv:
– start-page: 1096
  year: 2008
  end-page: 1103
  ident: bib0011
  article-title: Extracting and composing robust features with denoising autoencoders
  publication-title: Proceedings of the 25th International Conference on Machine Learning, ICML ’08
– volume: 80
  start-page: 4141
  year: 2018
  end-page: 4150
  ident: bib0007
  article-title: Learning dynamics of linear denoising autoencoders
  publication-title: Proceedings of the 35th International Conference on Machine Learning
– reference: M. Pratama, E. Dimla, E. Lughofer, W. Pedrycz, T. Tjahjowidodo, Online Tool Condition Monitoring Based on Parsimonious Ensemble+, CoRR abs/1711.01843 (2017).
– volume: 26
  start-page: 2552
  year: 2018
  end-page: 2567
  ident: bib0025
  article-title: Evolving ensemble fuzzy classifier
  publication-title: IEEE Trans. Fuzzy Syst.
– start-page: 3
  year: 1993
  end-page: 10
  ident: bib0033
  article-title: Autoencoders, minimum description length and Helmholtz free energy
  publication-title: Proceedings of the 6th International Conference on Neural Information Processing Systems, NIPS’93
– volume: 22
  start-page: 1453
  year: 2012
  end-page: 1461
  ident: bib0010
  article-title: Online incremental feature learning with denoising autoencoders
  publication-title: J. Mach. Learn. Res.
– volume: 273
  start-page: 643
  year: 2018
  end-page: 649
  ident: bib0008
  article-title: Facial expression recognition via learning deep sparse autoencoders
  publication-title: Neurocomputing
– reference: A. Ashfahani, M. Pratama, E. Lughofer, Q. Cai, H. Sheng, An Online RFID Localization in the Manufacturing Shopfloor, Springer International Publishing, pp. 287–309. doi:
– year: 2012
  ident: bib0034
  article-title: Machine Learning: A Probabilistic Perspective
– volume: 46
  start-page: 44:1
  year: 2014
  end-page: 44:37
  ident: bib0032
  article-title: A survey on concept drift adaptation
  publication-title: ACM Comput. Surv.
– start-page: 2270
  year: 2016
  end-page: 2278
  ident: bib0002
  article-title: Learning the number of neurons in deep networks
  publication-title: Advances in Neural Information Processing Systems 29
– reference: M. Mohammadi, A.I. Al-Fuqaha, S. Sorour, M. Guizani, Deep Learning for iot Big Data and Streaming Analytics: A Survey, CoRR abs/1712.04301(2017).
– reference: abs/1711.03705 (2017).
– reference: (2015).
– reference: A. Ashfahani, M. Pratama, Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments, Society for Industrial and Applied Mathematics, pp. 666–674.
– volume: 2
  start-page: 2148
  year: 2013
  end-page: 2156
  ident: bib0003
  article-title: Predicting parameters in deep learning
  publication-title: Proceedings of the 26th International Conference on Neural Information Processing Systems, NIPS’13
– volume: 47
  start-page: 3466
  year: 2017
  end-page: 3479
  ident: bib0036
  article-title: Stochastic configuration networks: Fundamentals and algorithms
  publication-title: IEEE Trans. Cybern.
– volume: 112
  start-page: 28
  year: 2016
  end-page: 39
  ident: bib0021
  article-title: Accurate occupancy detection of an office room from light, temperature, humidity and CO2 measurements using statistical learning models
  publication-title: Energy Build.
– year: 2016
  ident: bib0038
  article-title: Deep Learning
– start-page: 105
  year: 2001
  end-page: 112
  ident: bib0027
  article-title: Online bagging and boosting. Jaakkola Tommi and richardson thomas, editors
  publication-title: Proceedings of Eighth International Workshop on Artificial Intelligence and Statistics
– volume: 10
  start-page: 23
  year: 2006
  end-page: 45
  ident: bib0035
  article-title: Decision trees for mining data streams
  publication-title: Intell. Data Anal.
– volume: 22
  start-page: 1517
  year: 2011
  end-page: 1531
  ident: bib0029
  article-title: Incremental learning of concept drift in nonstationary environments
  publication-title: Trans. Neural Netw.
– start-page: 1
  year: 2007
  end-page: 3
  ident: bib0040
  article-title: Wilcoxon Signed-rank Test
  publication-title: Wiley Encyclopedia of Clinical Trials
– volume: 11
  start-page: 1601
  year: 2010
  end-page: 1604
  ident: bib0020
  article-title: Moa: massive online analysis
  publication-title: J. Mach. Learn. Res.
– reference: Y. LeCun, C. Cortes, MNIST Handwritten Digit Database(2010).
– reference: .
– volume: 26
  start-page: 2310
  year: 2013
  end-page: 2318
  ident: bib0016
  article-title: Compete to compute
  publication-title: Advances in Neural Information Processing Systems
– reference: J. Yoon, E. Yang, J. Lee, S. J. Hwang, Lifelong Learning with Dynamically Expandable Networks (2018).
– volume: 5
  start-page: 4308
  year: 2014
  ident: bib0024
  article-title: Searching for exotic particles in high-energy physics with deep learning.
  publication-title: Nat. Commun.
– reference: A.A. Rusu, N.C. Rabinowitz, G. Desjardins, H. Soyer, J. Kirkpatrick, K. Kavukcuoglu, R. Pascanu, R. Hadsell, Progressive Neural Networks, CoRR abs/1606.04671 (2016).
– reference: D. Sahoo, Q.D. Pham, J. Lu, S.C. Hoi, Online Deep Learning: Learning Deep Neural Networks on the Fly, arXiv preprint arXiv:
– volume: 30
  start-page: 6467
  year: 2017
  end-page: 6476
  ident: bib0015
  article-title: Gradient episodic memory for continual learning
  publication-title: Advances in Neural Information Processing Systems
– volume: 90
  start-page: 317
  year: 2013
  end-page: 346
  ident: bib0031
  article-title: On evaluating stream learning algorithms
  publication-title: Mach. Learn.
– reference: J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A.A. Rusu, K. Milan, J. Quan, T. Ramalho, A. Grabska-Barwinska, D. Hassabis, C. Clopath, D. Kumaran, R. Hadsell, Overcoming Catastrophic Forgetting in Neural Networks, 2016. Cite arxiv:
– volume: 35
  start-page: 1798
  year: 2013
  end-page: 1828
  ident: bib0006
  article-title: Representation learning: a review and new perspectives
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 919
  year: 2017
  end-page: 928
  ident: bib0026
  article-title: Online multiclass boosting
  publication-title: Proceedings of Advances in Neural Information Processing Systems
– year: 2010
  ident: bib0005
  article-title: Knowledge Discovery from Data Streams
– start-page: 377
  year: 2001
  end-page: 382
  ident: bib0019
  article-title: A streaming ensemble algorithm (sea) for large-scale classification
  publication-title: Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’01
– start-page: 153
  year: 2006
  end-page: 160
  ident: bib0037
  article-title: Greedy layer-wise training of deep networks
  publication-title: Proceedings of the 19th International Conference on Neural Information Processing Systems, NIPS’06
– start-page: 2270
  year: 2016
  ident: 10.1016/j.neucom.2019.07.106_bib0002
  article-title: Learning the number of neurons in deep networks
– volume: 47
  start-page: 3466
  issue: 10
  year: 2017
  ident: 10.1016/j.neucom.2019.07.106_bib0036
  article-title: Stochastic configuration networks: Fundamentals and algorithms
  publication-title: IEEE Trans. Cybern.
  doi: 10.1109/TCYB.2017.2734043
– volume: 11
  start-page: 1601
  year: 2010
  ident: 10.1016/j.neucom.2019.07.106_sbref0013
  article-title: Moa: massive online analysis
  publication-title: J. Mach. Learn. Res.
– year: 2016
  ident: 10.1016/j.neucom.2019.07.106_bib0038
– start-page: 1096
  year: 2008
  ident: 10.1016/j.neucom.2019.07.106_bib0011
  article-title: Extracting and composing robust features with denoising autoencoders
– start-page: 153
  year: 2006
  ident: 10.1016/j.neucom.2019.07.106_bib0037
  article-title: Greedy layer-wise training of deep networks
– start-page: 675
  year: 2014
  ident: 10.1016/j.neucom.2019.07.106_bib0039
  article-title: Caffe: Convolutional architecture for fast feature embedding
– volume: 112
  start-page: 28
  year: 2016
  ident: 10.1016/j.neucom.2019.07.106_bib0021
  article-title: Accurate occupancy detection of an office room from light, temperature, humidity and CO2 measurements using statistical learning models
  publication-title: Energy Build.
  doi: 10.1016/j.enbuild.2015.11.071
– volume: 10
  start-page: 23
  issue: 1
  year: 2006
  ident: 10.1016/j.neucom.2019.07.106_bib0035
  article-title: Decision trees for mining data streams
  publication-title: Intell. Data Anal.
  doi: 10.3233/IDA-2006-10103
– volume: 90
  start-page: 317
  issue: 3
  year: 2013
  ident: 10.1016/j.neucom.2019.07.106_bib0031
  article-title: On evaluating stream learning algorithms
  publication-title: Mach. Learn.
  doi: 10.1007/s10994-012-5320-9
– ident: 10.1016/j.neucom.2019.07.106_bib0001
– year: 2010
  ident: 10.1016/j.neucom.2019.07.106_bib0005
– ident: 10.1016/j.neucom.2019.07.106_bib0017
– volume: 5
  start-page: 4308
  year: 2014
  ident: 10.1016/j.neucom.2019.07.106_bib0024
  article-title: Searching for exotic particles in high-energy physics with deep learning.
  publication-title: Nat. Commun.
  doi: 10.1038/ncomms5308
– start-page: 105
  year: 2001
  ident: 10.1016/j.neucom.2019.07.106_bib0027
  article-title: Online bagging and boosting. Jaakkola Tommi and richardson thomas, editors
– volume: 26
  start-page: 2552
  issue: 5
  year: 2018
  ident: 10.1016/j.neucom.2019.07.106_bib0025
  article-title: Evolving ensemble fuzzy classifier
  publication-title: IEEE Trans. Fuzzy Syst.
  doi: 10.1109/TFUZZ.2018.2796099
– ident: 10.1016/j.neucom.2019.07.106_bib0012
  doi: 10.24963/ijcai.2018/369
– volume: 26
  start-page: 2310
  year: 2013
  ident: 10.1016/j.neucom.2019.07.106_sbref0010
  article-title: Compete to compute
– start-page: 130
  year: 2000
  ident: 10.1016/j.neucom.2019.07.106_bib0023
  article-title: Cost-based modeling for fraud and intrusion detection: Results from the jam project
– volume: 22
  start-page: 1453
  year: 2012
  ident: 10.1016/j.neucom.2019.07.106_bib0010
  article-title: Online incremental feature learning with denoising autoencoders
  publication-title: J. Mach. Learn. Res.
– ident: 10.1016/j.neucom.2019.07.106_bib0030
  doi: 10.1073/pnas.1611835114
– ident: 10.1016/j.neucom.2019.07.106_bib0009
– volume: 24
  start-page: 131
  year: 1999
  ident: 10.1016/j.neucom.2019.07.106_bib0018
  article-title: Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables
  publication-title: Comput. Electron. Agric.
  doi: 10.1016/S0168-1699(99)00046-0
– volume: 46
  start-page: 44:1
  issue: 4
  year: 2014
  ident: 10.1016/j.neucom.2019.07.106_bib0032
  article-title: A survey on concept drift adaptation
  publication-title: ACM Comput. Surv.
  doi: 10.1145/2523813
– ident: 10.1016/j.neucom.2019.07.106_bib0013
– ident: 10.1016/j.neucom.2019.07.106_bib0028
– volume: 2
  start-page: 2148
  year: 2013
  ident: 10.1016/j.neucom.2019.07.106_bib0003
  article-title: Predicting parameters in deep learning
– start-page: 377
  year: 2001
  ident: 10.1016/j.neucom.2019.07.106_bib0019
  article-title: A streaming ensemble algorithm (sea) for large-scale classification
– start-page: 1
  year: 2007
  ident: 10.1016/j.neucom.2019.07.106_bib0040
  article-title: Wilcoxon Signed-rank Test
  publication-title: Wiley Encyclopedia of Clinical Trials
– volume: 273
  start-page: 643
  year: 2018
  ident: 10.1016/j.neucom.2019.07.106_bib0008
  article-title: Facial expression recognition via learning deep sparse autoencoders
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2017.08.043
– start-page: 3
  year: 1993
  ident: 10.1016/j.neucom.2019.07.106_bib0033
  article-title: Autoencoders, minimum description length and Helmholtz free energy
– year: 2012
  ident: 10.1016/j.neucom.2019.07.106_bib0034
– volume: 80
  start-page: 4141
  year: 2018
  ident: 10.1016/j.neucom.2019.07.106_sbref0005
  article-title: Learning dynamics of linear denoising autoencoders
– volume: 22
  start-page: 1517
  issue: 10
  year: 2011
  ident: 10.1016/j.neucom.2019.07.106_bib0029
  article-title: Incremental learning of concept drift in nonstationary environments
  publication-title: Trans. Neural Netw.
  doi: 10.1109/TNN.2011.2160459
– ident: 10.1016/j.neucom.2019.07.106_bib0004
– volume: 35
  start-page: 1798
  issue: 8
  year: 2013
  ident: 10.1016/j.neucom.2019.07.106_bib0006
  article-title: Representation learning: a review and new perspectives
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2013.50
– ident: 10.1016/j.neucom.2019.07.106_bib0014
  doi: 10.1137/1.9781611975673.75
– volume: 30
  start-page: 6467
  year: 2017
  ident: 10.1016/j.neucom.2019.07.106_sbref0009
  article-title: Gradient episodic memory for continual learning
– start-page: 919
  year: 2017
  ident: 10.1016/j.neucom.2019.07.106_bib0026
  article-title: Online multiclass boosting
– ident: 10.1016/j.neucom.2019.07.106_bib0022
  doi: 10.1007/978-3-030-05645-2_10
SSID ssj0017129
Score 2.5885143
Snippet The Denoising Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 297
SubjectTerms Data streams
Denoising autoencoder
Incremental learning
Title DEVDAN: Deep evolving denoising autoencoder
URI https://dx.doi.org/10.1016/j.neucom.2019.07.106
Volume 390
WOSCitedRecordID wos000531728800010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-8286
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017129
  issn: 0925-2312
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELfKxgMvML7EGEN54G0ySuwkTvZW0U4DTQVpA5WnyLEva8qWVFuz7c_nHDtpRRFfEi9Ra8WN6_vp7ny53x0hb9CkyyQtIlqkmtFQR5rKQgdUBRKNtZRQJC1R-ERMJsl0mn4aDBYdF-bmQlRVcneXLv6rqHEMhW2os38h7v5HcQA_o9DximLH6x8JfjT-MhpOzEl_BLA4ANQ_bdAAFUxdtpEB2SxrU79Su8zceVfBqUFr1nZ5cPGD4aUpo6ANZlbxgutZIWe2E1SbDln22hXBJC-lZQAZMtes_NYr_ZPmfFYXjlyjb8sekx-tsvkKt_S0dhhxUQjWvkBnqyjEJj3GxhgZ3sVdnjRYDZsI1nLX11Uwty1DOyVqM3adPeaWZLqh6m3UYf62gsbk_aAjk5oyrIH_Q2Xt1lafmqWYlaC_GoQRj-6RbSaiFPXg9vD9ePqhf_MkAmbrM7qld3TLNidw81k_d2fWXJSzHfLQnS28ocXEYzKA6gl51PXt8Jwaf0oOLEQOPQMQrwOI1wPEWwPIM_L5aHz27pi6phlU4elvSdHhhtDU5FE8LhIhZVQoLQvJU1CgWJoEioPy8zjOuYJI4XfIY51DJBUDyflzslXVFbwgXqBDXzGfA3qZocxFakjSsRAyCgP0JP1dwrv_nilXUd40NrnIutTBeWZ3LDM7lvkCR-NdQvtZC1tR5Tf3i25bM-cVWm8vQyT8cubLf565Rx6sQP6KbC2vGtgn99XNsry-eu0g8x1XCYY6
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=DEVDAN%3A+Deep+evolving+denoising+autoencoder&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Ashfahani%2C+Andri&rft.au=Pratama%2C+Mahardhika&rft.au=Lughofer%2C+Edwin&rft.au=Ong%2C+Yew-Soon&rft.date=2020-05-21&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.eissn=1872-8286&rft.volume=390&rft.spage=297&rft.epage=314&rft_id=info:doi/10.1016%2Fj.neucom.2019.07.106&rft.externalDocID=S0925231219314535
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon