DensePILAE: a feature reuse pseudoinverse learning algorithm for deep stacked autoencoder

Autoencoder has been widely used as a feature learning technique. In many works of autoencoder, the features of the original input are usually extracted layer by layer using multi-layer nonlinear mapping, and only the features of the last layer are used for classification or regression. Therefore, t...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Complex & intelligent systems Ročník 8; číslo 3; s. 2039 - 2049
Hlavní autori: Wang, Jue, Guo, Ping, Li, Yanjun
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Cham Springer International Publishing 01.06.2022
Springer Nature B.V
Predmet:
ISSN:2199-4536, 2198-6053
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Autoencoder has been widely used as a feature learning technique. In many works of autoencoder, the features of the original input are usually extracted layer by layer using multi-layer nonlinear mapping, and only the features of the last layer are used for classification or regression. Therefore, the features of the previous layer aren’t used explicitly. The loss of information and waste of computation is obvious. In addition, faster training and reasoning speed is generally required in the Internet of Things applications. But the stacked autoencoders model is usually trained by the BP algorithm, which has the problem of slow convergence. To solve the above two problems, the paper proposes a dense connection pseudoinverse learning autoencoder (DensePILAE) from reuse perspective. Pseudoinverse learning autoencoder (PILAE) can extract features in the form of analytic solution, without multiple iterations. Therefore, the time cost can be greatly reduced. At the same time, the features of all the previous layers in stacked PILAE are combined as the input of next layer. In this way, the information of all the previous layers not only has no loss, but also can be strengthened and refined, so that better features could be learned. The experimental results in 8 data sets of different domains show that the proposed DensePILAE is effective.
AbstractList Autoencoder has been widely used as a feature learning technique. In many works of autoencoder, the features of the original input are usually extracted layer by layer using multi-layer nonlinear mapping, and only the features of the last layer are used for classification or regression. Therefore, the features of the previous layer aren’t used explicitly. The loss of information and waste of computation is obvious. In addition, faster training and reasoning speed is generally required in the Internet of Things applications. But the stacked autoencoders model is usually trained by the BP algorithm, which has the problem of slow convergence. To solve the above two problems, the paper proposes a dense connection pseudoinverse learning autoencoder (DensePILAE) from reuse perspective. Pseudoinverse learning autoencoder (PILAE) can extract features in the form of analytic solution, without multiple iterations. Therefore, the time cost can be greatly reduced. At the same time, the features of all the previous layers in stacked PILAE are combined as the input of next layer. In this way, the information of all the previous layers not only has no loss, but also can be strengthened and refined, so that better features could be learned. The experimental results in 8 data sets of different domains show that the proposed DensePILAE is effective.
Author Guo, Ping
Li, Yanjun
Wang, Jue
Author_xml – sequence: 1
  givenname: Jue
  surname: Wang
  fullname: Wang, Jue
  organization: School of Computer Science and Technology, Beijing Institute of Technology, School of Space Information, Space Engineering University
– sequence: 2
  givenname: Ping
  surname: Guo
  fullname: Guo, Ping
  email: pguo@bnu.edu.cn
  organization: School of System Science, Beijing Normal University
– sequence: 3
  givenname: Yanjun
  surname: Li
  fullname: Li, Yanjun
  organization: School of Information, Shanxi University of Finance and Economics
BookMark eNp9kE1LAzEQhoNUsNb-AU8Bz6v52CS73kr9KhT0oAdPIc1O6tY2qUlW8N-7toLgoaeZgfeZGZ5TNPDBA0LnlFxSQtRVKokqVUEYLQgRVBbiCA0ZratCEsEHu74uSsHlCRqntCKEUKUqTtgQvd6AT_A0m09ur7HBDkzuIuAIXQK8TdA1ofWfEPtpDSb61i-xWS9DbPPbBrsQcQOwxSkb-w4NNl0O4G1oIJ6hY2fWCca_dYRe7m6fpw_F_PF-Np3MC1tymYuF5NZYYivhONBaVdbVtVACKiOqxjFKyYIyIReltKVrpHBs0UeUlE4YUJyP0MV-7zaGjw5S1qvQRd-f1EyqHmdVTfsU26dsDClFcHob242JX5oS_WNR7y3q3qLeWdSih6p_kG2zyW3wOZp2fRjlezT1d_wS4t9XB6hvb9-IyA
CitedBy_id crossref_primary_10_1109_TSMC_2024_3352019
crossref_primary_10_3390_app12189021
crossref_primary_10_1007_s00371_023_02780_7
Cites_doi 10.1016/j.neunet.2019.01.007
10.1109/MCOM.2018.1700298
10.1109/TSC.2017.2662008
10.1007/s12559-021-09853-6
10.1109/TPAMI.2013.50
10.1109/JIOT.2018.2853663
10.1109/TITS.2020.2980555
10.1093/mnras/stw2894
10.1016/j.neucom.2015.09.116
10.1126/science.1127647
10.1109/2.144401
10.1016/S0925-2312(03)00385-0
10.1109/CVPR.2018.00255
10.1007/s40747-021-00319-8
10.1109/CVPR.2016.90
10.1007/s40747-021-00284-2
10.1109/SmartCity.2015.63
10.1109/SMC.2017.8122732
10.1109/ICASSP.2012.6288333
10.1145/1390156.1390294
10.1109/CVPR.2017.76
10.1016/j.neucom.2019.03.024
10.1145/1961189.1961199
10.1109/IJCNN.2018.8489703
10.1109/ICCV.2019.00179
10.1007/978-3-319-92537-0_12
10.1109/CVPR.2017.243
10.1155/2019/9242598
ContentType Journal Article
Copyright The Author(s) 2021
The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: The Author(s) 2021
– notice: The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID C6C
AAYXX
CITATION
8FE
8FG
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
HCIFZ
P5Z
P62
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
DOI 10.1007/s40747-021-00516-5
DatabaseName Springer Nature OA Free Journals
CrossRef
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
AUTh Library subscriptions: ProQuest Central
Technology Collection
ProQuest One Community College
ProQuest Central
SciTech Premium Collection
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
DatabaseTitle CrossRef
Publicly Available Content Database
Advanced Technologies & Aerospace Collection
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
Advanced Technologies & Aerospace Database
ProQuest One Applied & Life Sciences
ProQuest One Academic UKI Edition
ProQuest Central Korea
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList
CrossRef
Publicly Available Content Database
Database_xml – sequence: 1
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Mathematics
EISSN 2198-6053
EndPage 2049
ExternalDocumentID 10_1007_s40747_021_00516_5
GroupedDBID 0R~
8FE
8FG
AAJSJ
AAKKN
ABEEZ
ABFTD
ACACY
ACGFS
ACULB
ADINQ
ADMLS
AFGXO
AFKRA
AHBYD
AHSBF
AHYZX
ALMA_UNASSIGNED_HOLDINGS
AMKLP
ARAPS
ASPBG
AVWKF
BAPOH
BENPR
BGLVJ
C24
C6C
CCPQU
EBLON
EBS
EJD
GROUPED_DOAJ
HCIFZ
IAO
ISR
ITC
M~E
OK1
P62
PIMPY
PROAC
RSV
SOJ
AASML
AAYXX
AFFHD
CITATION
PHGZM
PHGZT
PQGLB
ABUWG
AZQEC
DWQXO
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c436t-b63cac0c85f3e1978cf99575e8a58df2110b1256b46c4fd65f2bcf9766f5ae733
IEDL.DBID C24
ISICitedReferencesCount 6
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000694786600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2199-4536
IngestDate Wed Oct 08 14:21:19 EDT 2025
Tue Nov 18 21:29:47 EST 2025
Sat Nov 29 05:48:57 EST 2025
Fri Feb 21 02:45:44 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Keywords Pseudoinverse learning
Dense connection
Feature reuse
Pseudoinverse learning autoencoder
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c436t-b63cac0c85f3e1978cf99575e8a58df2110b1256b46c4fd65f2bcf9766f5ae733
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
OpenAccessLink https://link.springer.com/10.1007/s40747-021-00516-5
PQID 2671102891
PQPubID 2044308
PageCount 11
ParticipantIDs proquest_journals_2671102891
crossref_primary_10_1007_s40747_021_00516_5
crossref_citationtrail_10_1007_s40747_021_00516_5
springer_journals_10_1007_s40747_021_00516_5
PublicationCentury 2000
PublicationDate 20220600
2022-06-00
20220601
PublicationDateYYYYMMDD 2022-06-01
PublicationDate_xml – month: 6
  year: 2022
  text: 20220600
PublicationDecade 2020
PublicationPlace Cham
PublicationPlace_xml – name: Cham
– name: Heidelberg
PublicationTitle Complex & intelligent systems
PublicationTitleAbbrev Complex Intell. Syst
PublicationYear 2022
Publisher Springer International Publishing
Springer Nature B.V
Publisher_xml – name: Springer International Publishing
– name: Springer Nature B.V
References Sun, Gui, Li, Liu, An (CR19) 2019; 6
CR16
CR14
CR13
CR11
CR10
CR31
Pao, Takefuji (CR18) 1992; 5
CR30
Bengio, Courville, Vincent (CR1) 2013; 35
Wang, Guo (CR24) 2021; 13
Wang, Guo (CR23) 2021; 22
CR2
CR4
Hinton (CR12) 2006; 313
CR3
CR6
CR5
CR8
Mohammadi, Alfuqaha (CR17) 2018; 56
Wang, Guo, Luo (CR25) 2016; 465
CR7
Guo, Liu, Oerlemans, Lao, Wu, Lew (CR9) 2016; 187
CR28
CR27
CR26
CR22
Liu, Cao, Luo, Chen, Vokkarane, Yunsheng, Chen, Hou (CR15) 2018; 11
CR21
CR20
Zhang, Wu, Cai, Du, Yu (CR32) 2019; 112
Zhang, Mao, Huang, Xu, Ding (CR29) 2018; 9
X Sun (516_CR19) 2019; 6
K Wang (516_CR25) 2016; 465
K Wang (516_CR23) 2021; 22
GE Hinton (516_CR12) 2006; 313
516_CR2
516_CR3
516_CR28
516_CR27
516_CR26
Y Zhang (516_CR32) 2019; 112
516_CR22
516_CR21
516_CR20
K Wang (516_CR24) 2021; 13
Y Bengio (516_CR1) 2013; 35
Y Guo (516_CR9) 2016; 187
M Mohammadi (516_CR17) 2018; 56
516_CR8
C Liu (516_CR15) 2018; 11
516_CR4
516_CR5
F Zhang (516_CR29) 2018; 9
516_CR6
516_CR7
516_CR16
516_CR14
516_CR13
YH Pao (516_CR18) 1992; 5
516_CR11
516_CR10
516_CR31
516_CR30
References_xml – ident: CR22
– volume: 112
  start-page: 85
  year: 2019
  end-page: 97
  ident: CR32
  article-title: An unsupervised parameter learning model for RVFL neural network
  publication-title: Neural Netw
  doi: 10.1016/j.neunet.2019.01.007
– volume: 56
  start-page: 94
  issue: 2
  year: 2018
  end-page: 101
  ident: CR17
  article-title: Enabling cognitive smart cities using big data and machine learning: approaches and challenges
  publication-title: IEEE Commun Mag
  doi: 10.1109/MCOM.2018.1700298
– ident: CR4
– ident: CR14
– ident: CR2
– ident: CR16
– ident: CR30
– ident: CR10
– ident: CR6
– ident: CR8
– volume: 11
  start-page: 249
  issue: 2
  year: 2018
  end-page: 261
  ident: CR15
  article-title: A new deep learning-based food recognition system for dietary assessment on an edge computing service infrastructure
  publication-title: IEEE Trans Serv Comput
  doi: 10.1109/TSC.2017.2662008
– volume: 9
  start-page: 177
  year: 2018
  end-page: 187
  ident: CR29
  article-title: Deep learning models for EEG-based rapid serial visual presentation event classification
  publication-title: J Inf Hiding Multim Signal Process
– ident: CR27
– ident: CR21
– volume: 13
  start-page: 724
  issue: 3
  year: 2021
  end-page: 735
  ident: CR24
  article-title: A robust automated machine learning system with pseudoinverse learning
  publication-title: Cogn Comput
  doi: 10.1007/s12559-021-09853-6
– volume: 35
  start-page: 1798
  issue: 8
  year: 2013
  end-page: 1828
  ident: CR1
  article-title: Representation learning: a review and new perspectives
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2013.50
– volume: 6
  start-page: 679
  issue: 1
  year: 2019
  end-page: 691
  ident: CR19
  article-title: ResInNet: a novel deep neural network with feature reuse for internet of things
  publication-title: IEEE Internet Things J
  doi: 10.1109/JIOT.2018.2853663
– volume: 22
  start-page: 3303
  issue: 6
  year: 2021
  end-page: 3315
  ident: CR23
  article-title: An ensemble classification model with unsupervised representation learning for driving stress recognition using physiological signals
  publication-title: IEEE Trans Intell Transp Syst
  doi: 10.1109/TITS.2020.2980555
– volume: 465
  start-page: 4311
  issue: 4
  year: 2016
  end-page: 4324
  ident: CR25
  article-title: A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery
  publication-title: Mon Not R Astron Soc
  doi: 10.1093/mnras/stw2894
– ident: CR3
– ident: CR31
– ident: CR13
– ident: CR11
– volume: 187
  start-page: 27
  year: 2016
  end-page: 48
  ident: CR9
  article-title: Deep learning for visual understanding: a review
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.09.116
– volume: 313
  start-page: 504
  issue: 5786
  year: 2006
  end-page: 507
  ident: CR12
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
  doi: 10.1126/science.1127647
– ident: CR5
– ident: CR7
– ident: CR28
– ident: CR26
– ident: CR20
– volume: 5
  start-page: 76
  year: 1992
  end-page: 79
  ident: CR18
  article-title: Functional-link net computing: theory, system architecture, and functionalities
  publication-title: IEEE Comput
  doi: 10.1109/2.144401
– volume: 6
  start-page: 679
  issue: 1
  year: 2019
  ident: 516_CR19
  publication-title: IEEE Internet Things J
  doi: 10.1109/JIOT.2018.2853663
– ident: 516_CR8
  doi: 10.1016/S0925-2312(03)00385-0
– ident: 516_CR28
  doi: 10.1109/CVPR.2018.00255
– ident: 516_CR7
– ident: 516_CR4
  doi: 10.1007/s40747-021-00319-8
– volume: 112
  start-page: 85
  year: 2019
  ident: 516_CR32
  publication-title: Neural Netw
  doi: 10.1016/j.neunet.2019.01.007
– volume: 9
  start-page: 177
  year: 2018
  ident: 516_CR29
  publication-title: J Inf Hiding Multim Signal Process
– volume: 187
  start-page: 27
  year: 2016
  ident: 516_CR9
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.09.116
– ident: 516_CR10
  doi: 10.1109/CVPR.2016.90
– ident: 516_CR16
  doi: 10.1007/s40747-021-00284-2
– ident: 516_CR20
  doi: 10.1109/SmartCity.2015.63
– ident: 516_CR26
  doi: 10.1109/SMC.2017.8122732
– ident: 516_CR14
– ident: 516_CR3
  doi: 10.1109/ICASSP.2012.6288333
– ident: 516_CR21
  doi: 10.1145/1390156.1390294
– volume: 13
  start-page: 724
  issue: 3
  year: 2021
  ident: 516_CR24
  publication-title: Cogn Comput
  doi: 10.1007/s12559-021-09853-6
– ident: 516_CR31
  doi: 10.1109/CVPR.2017.76
– ident: 516_CR6
– volume: 35
  start-page: 1798
  issue: 8
  year: 2013
  ident: 516_CR1
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2013.50
– ident: 516_CR30
  doi: 10.1016/j.neucom.2019.03.024
– ident: 516_CR2
  doi: 10.1145/1961189.1961199
– volume: 56
  start-page: 94
  issue: 2
  year: 2018
  ident: 516_CR17
  publication-title: IEEE Commun Mag
  doi: 10.1109/MCOM.2018.1700298
– volume: 313
  start-page: 504
  issue: 5786
  year: 2006
  ident: 516_CR12
  publication-title: Science
  doi: 10.1126/science.1127647
– ident: 516_CR11
  doi: 10.1109/IJCNN.2018.8489703
– ident: 516_CR5
  doi: 10.1109/ICCV.2019.00179
– ident: 516_CR22
  doi: 10.1007/978-3-319-92537-0_12
– volume: 5
  start-page: 76
  year: 1992
  ident: 516_CR18
  publication-title: IEEE Comput
  doi: 10.1109/2.144401
– volume: 22
  start-page: 3303
  issue: 6
  year: 2021
  ident: 516_CR23
  publication-title: IEEE Trans Intell Transp Syst
  doi: 10.1109/TITS.2020.2980555
– volume: 465
  start-page: 4311
  issue: 4
  year: 2016
  ident: 516_CR25
  publication-title: Mon Not R Astron Soc
  doi: 10.1093/mnras/stw2894
– ident: 516_CR13
  doi: 10.1109/CVPR.2017.243
– ident: 516_CR27
  doi: 10.1155/2019/9242598
– volume: 11
  start-page: 249
  issue: 2
  year: 2018
  ident: 516_CR15
  publication-title: IEEE Trans Serv Comput
  doi: 10.1109/TSC.2017.2662008
SSID ssj0001778302
ssib044733412
ssib045327741
Score 2.2507703
Snippet Autoencoder has been widely used as a feature learning technique. In many works of autoencoder, the features of the original input are usually extracted layer...
SourceID proquest
crossref
springer
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 2039
SubjectTerms Algorithms
Complexity
Computational Intelligence
Cost analysis
Data Structures and Information Theory
Deep learning
Engineering
Exact solutions
Feature extraction
Intelligent systems
Internet of Things
Machine learning
Multilayers
Neural networks
Original Article
Teaching methods
SummonAdditionalLinks – databaseName: Publicly Available Content Database
  dbid: PIMPY
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NT9wwEB21Sw_l0G_EAq186I1abGLHsXupUAEVqaA9UAlOkePYtBLsLpssv78zXmdXVConznEcJW8yH_b4PYDPqtGZyo3jQRssUKw1XFstuWmENKOAVhVsFJsoz8_15aUZp-PRbWqr7H1idNRLtmfq20YnfNBMHa2YH-SqzCg0muzb7I6ThhTttSZBjeewQcRbowFsjE_Pxle9fUlZCiHX4VwWIi975Zm4JlOWRIdFenSZMVzGnc2d1Wk7SWTznHoayJQVLx7GsnWC-s-eagxVJ6-f9iXfwKuUsrLDpY29hWd-8g42z1Z8r-17uDrCatiPT38eHn9llgUf6ULZ3C9az2atX6DnnFADiGdJpuKa2ZtrfFj3-5Zh3swa72cMM1V0Kg2zi25KBJuNn3-AXyfHF99_8CTawJ0UquO1Es66kdNFED7DGtUFYzAn9NoWuglUb9aYVKlaKidDo4qQ1zikVCoU1iNAWzCYTCd-G5jDABsMBnFXa-KwqWVwQgVhRx7tX7ghZP3nr1xiNCdhjZtqxcUcIasQsipCVhVD2F_dM1vyeTw6eq_HqUr_dlutYRnClx7p9eX_z7bz-Gy78DKnsxVxiWcPBt184T_CC3ff_Wnnn5It_wVBTv0V
  priority: 102
  providerName: ProQuest
Title DensePILAE: a feature reuse pseudoinverse learning algorithm for deep stacked autoencoder
URI https://link.springer.com/article/10.1007/s40747-021-00516-5
https://www.proquest.com/docview/2671102891
Volume 8
WOSCitedRecordID wos000694786600001&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: PRVAON
  databaseName: Directory of Open Access Journals (DOAJ)
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001778302
  issn: 2199-4536
  databaseCode: DOA
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044733412
  issn: 2199-4536
  databaseCode: M~E
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001778302
  issn: 2199-4536
  databaseCode: P5Z
  dateStart: 20151201
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001778302
  issn: 2199-4536
  databaseCode: BENPR
  dateStart: 20151201
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001778302
  issn: 2199-4536
  databaseCode: PIMPY
  dateStart: 20151201
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerOpen
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001778302
  issn: 2199-4536
  databaseCode: C24
  dateStart: 20151201
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dS-QwEB88vYfzQb0vXD-WPPjmBbabNE1882NFQZdyKOi9lDRNPEF3l7br3-8ktrsqKOhLoSQNZTLJ_CYz-Q3AjihkJPrKUCcVOihaKyq15FQVjKueQ61yOhSbSIZDeXWl0uZSWNVmu7chybBTzy67cc_1Tn1KgdckQeMvsOTpxHwi1-Gcc5zzhDHeGO1w0pIknuTKV5mLlKI8xCs33h72pYWaw85XkdJggI5XP_fra7DSAE6y_6Qh32HBjn7A8jMaQnw7n3G3Vj_h-gg9W5uenu0P9ogmzgbqT1LaaWXJpLJT3AVHPpnDkqbkxA3Rdzfj8rb-f08QA5PC2glB1IkbREH0tB57sszClr_g8nhwcXhCmwIM1HAmapoLZrTpGRk7ZiP0N41TCvGdlTqWhfO-Y44ASeRcGO4KEbt-jl0SIVysLU7Db1gcjUd2HYhBY-kUGmSTS89Hk3NnmHBM9yzqMjMdiFqhZ6ZhJ_dFMu6yGa9yEGKGQsyCELO4A7uzbyZP3Bzv9t5q5zJr1mmV9UUSeYilog78aedu3vz2aBsf674J3_r-3kQ4vtmCxbqc2m34ah7q26rswtLBYJj-7QY97oZjAXym8T9sSU_P0-tH5z3rxw
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1bb9MwFD6aOiTggftExwA_wBNYNInj2JMQmnbRqrVVH4a0PQXHsQfSaEuTgvhT_Mad4yathsTe9sCzHUuOv3Pz5fsA3shSRTLWlnulsUAxRnNllOC6TITueUSVN0FsIhuN1NmZHm_An_YtDF2rbH1icNTl1NIe-YdYZhEFQx19mv3gpBpFp6uthMYSFifu9y8s2aqP_QNc37dxfHR4un_MG1UBbkUia17IxBrbsyr1iYuwiLJea0xanDKpKj0VRAVGfVkIaYUvZerjArtkUvrUuIw2QNHlbwoEe68Dm-P-cHzeIlgIbBfrhEGkSZy12jZh1yfLiHCLFO8irbkIZ6fbq_d8gujsOd2aIGORPL0eLdcp8F-ntiEYHj38337jI3jQpN1sb2knj2HDTZ7A_eGKs7Z6CucHWNG7cX-wd7jLDPMuUJ6yuVtUjs0qt0DvP6FLLI41UhsXzFxe4OTqr98Z5v6sdG7GMNtGx1gys6inRBJauvkz-Hwrc9uCzmQ6cc-BWUwSvMZExBaKeHgK4W0ifWJ6Dm04sV2I2gXObcPKTuIgl_mKTzqAIkdQ5AEUedqFd6tvZktOkht777RIyBv_VOVrGHThfYuldfO_R9u-ebTXcPf4dDjIB_3RyQu4F9NbkbBltQOder5wL-GO_Vl_q-avGsth8OW2UXYFjuJPMw
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dT9swED-NgtD2MD6ntePDD7xtFk3tOPbeEFANAVUfQGJPkePYBQnSKkn39-_spi1DYhLiMYljKXcX3-98vt8BHIlcRqKnDHVSYYCitaJSS05VzrjqOrQqp0OziWQwkHd3avisij-cdp-nJGc1DZ6lqaiPJ7k7XhS-cc_7Tv3xAm9VgsYrsIr3Em_Xp0v-cc4TxnjjwMOuS5J4wivfcS5SivKQu-y8Pu2_3moJQV9kTYMz6m-8_zM24XMDRMnJzHK24IMttuHTM3pCvLpecLpWO_D7DCNeO7y4Ojn_STRxNlCCktJOK0smlZ3i6lj4Qx6WNK0oRkQ_jsblQ33_RBAbk9zaCUE0igtHTvS0HnsSzdyWu3DbP785_UWbxgzUcCZqmglmtOkaGTtmI4xDjVMKcZ-VOpa58zFlhsBJZFwY7nIRu16GQxIhXKwtquQLtIpxYb8CMehEnUJHbTLpeWoy7gwTjumuRRtnpg3RXAGpaVjLffOMx3TBtxyEmKIQ0yDENG7D98U7kxlnx39H7831mjb_b5X2RBJ56KWiNvyY63H5-PXZOm8bfgjrw7N-enUxuPwGH3u-tCLs8OxBqy6ndh_WzJ_6oSoPgln_BcpS8k8
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=DensePILAE%3A+a+feature+reuse+pseudoinverse+learning+algorithm+for+deep+stacked+autoencoder&rft.jtitle=Complex+%26+intelligent+systems&rft.au=Wang%2C+Jue&rft.au=Guo%2C+Ping&rft.au=Li%2C+Yanjun&rft.date=2022-06-01&rft.pub=Springer+International+Publishing&rft.issn=2199-4536&rft.eissn=2198-6053&rft.volume=8&rft.issue=3&rft.spage=2039&rft.epage=2049&rft_id=info:doi/10.1007%2Fs40747-021-00516-5&rft.externalDocID=10_1007_s40747_021_00516_5
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2199-4536&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2199-4536&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2199-4536&client=summon