Supervised Learning via Unsupervised Sparse Autoencoder

Dimensionality reduction is commonly used to preprocess high-dimensional data, which is an essential step in machine learning and data mining. An outstanding low-dimensional feature can improve the efficiency of subsequent learning tasks. However, existing methods of dimensionality reduction mostly...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE access Jg. 6; S. 73802 - 73814
Hauptverfasser:	Liu, Jianran, Li, Chan, Yang, Wenyuan
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 2018 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms Classification Cognitive tasks Data mining Datasets Dimensionality reduction Feature extraction feature representation Labels Machine learning Optimization Parameter sensitivity Principal component analysis Reduction Representations sparse autoencoder Stress Supervised learning
ISSN:	2169-3536, 2169-3536
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Dimensionality reduction is commonly used to preprocess high-dimensional data, which is an essential step in machine learning and data mining. An outstanding low-dimensional feature can improve the efficiency of subsequent learning tasks. However, existing methods of dimensionality reduction mostly involve datasets with sufficient labels and fail to achieve effective feature vectors for datasets with insufficient labels. In this paper, an unsupervised multiple layered sparse autoencoder model is studied. Its advantage is that it reduces the reconstruction error as its optimization goal, with the resulting low-dimensional feature being reconstructed to the original dataset as much as possible. Therefore, the reduction of high-dimensional datasets to low-dimensional datasets is effective. First, the relationship among the reconstructed data, the number of iterations, and the number of hidden variables is explored. Second, the dimensionality reduction ability of the sparse autoencoder is proven. Several classical feature representation methods are compared with the sparse autoencoder on publicly available datasets, and the corresponding low-dimensional representations are placed into different supervised classifiers and the classification performances reported. Finally, by adjusting the parameters that might influence the classification performance, the parametric sensitivity of the sparse autoencoder is shown. The extensively low-dimensional feature classification experimental results demonstrated that the sparse autoencoder is more efficient and reliable than the other selected classical dimensional reduction algorithms.
AbstractList	Dimensionality reduction is commonly used to preprocess high-dimensional data, which is an essential step in machine learning and data mining. An outstanding low-dimensional feature can improve the efficiency of subsequent learning tasks. However, existing methods of dimensionality reduction mostly involve datasets with sufficient labels and fail to achieve effective feature vectors for datasets with insufficient labels. In this paper, an unsupervised multiple layered sparse autoencoder model is studied. Its advantage is that it reduces the reconstruction error as its optimization goal, with the resulting low-dimensional feature being reconstructed to the original dataset as much as possible. Therefore, the reduction of high-dimensional datasets to low-dimensional datasets is effective. First, the relationship among the reconstructed data, the number of iterations, and the number of hidden variables is explored. Second, the dimensionality reduction ability of the sparse autoencoder is proven. Several classical feature representation methods are compared with the sparse autoencoder on publicly available datasets, and the corresponding low-dimensional representations are placed into different supervised classifiers and the classification performances reported. Finally, by adjusting the parameters that might influence the classification performance, the parametric sensitivity of the sparse autoencoder is shown. The extensively low-dimensional feature classification experimental results demonstrated that the sparse autoencoder is more efficient and reliable than the other selected classical dimensional reduction algorithms.
Author	Li, Chan Yang, Wenyuan Liu, Jianran
Author_xml	– sequence: 1 givenname: Jianran orcidid: 0000-0002-5835-7913 surname: Liu fullname: Liu, Jianran organization: Fujian Key Laboratory of Granular Computing and Application, Minnan Normal University, Zhangzhou, China – sequence: 2 givenname: Chan surname: Li fullname: Li, Chan organization: Xiamen University Tan KahKee College, Xiamen, China – sequence: 3 givenname: Wenyuan surname: Yang fullname: Yang, Wenyuan email: yangwycn@gmail.com organization: Fujian Key Laboratory of Granular Computing and Application, Minnan Normal University, Zhangzhou, China
BookMark	eNqFkF1LwzAYhYNMcOp-wW4KXnfmox_J5ShTBwMv6q5D2r4ZGTOpSTvw39vZMcUbc5Nw8p5zXp5bNLHOAkJzgheEYPG4LIpVWS4oJnxBOU8ykV-hKSWZiFnKssmv9w2ahbDHw-GDlOZTlJd9C_5oAjTRBpS3xu6io1HR1oafn7JVPkC07DsHtnYN-Ht0rdUhwOx836Ht0-qteIk3r8_rYrmJ6wTzLqYCCGCSANFap3WmE55mAKTCGcGZGpScak24yBOuVKV1njNgvKqA4oYowe7QesxtnNrL1pt35T-lU0Z-C87vpPKdqQ8gK9YIxjPKG4ETAkLkumFDEzQ1qJqTIethzGq9--ghdHLvem-H9SVN0lRQkeBTIxunau9C8KAvrQTLE3A5Apcn4PIMfHCJP67adKozznZemcM_3vnoNQBwaeNpOrAS7Aui9o_z
CODEN	IAECCG
CitedBy_id	crossref_primary_10_1109_TII_2021_3056993 crossref_primary_10_1016_j_cviu_2020_103154 crossref_primary_10_1016_j_jwpe_2024_105150 crossref_primary_10_1109_ACCESS_2019_2951596 crossref_primary_10_3390_electronics10192347 crossref_primary_10_1109_ACCESS_2019_2925093 crossref_primary_10_1109_TTE_2019_2946065 crossref_primary_10_32604_cmes_2022_020128 crossref_primary_10_1109_ACCESS_2020_2980757 crossref_primary_10_1109_ACCESS_2024_3355034 crossref_primary_10_3389_frsc_2025_1642184 crossref_primary_10_1016_j_neucom_2019_07_083 crossref_primary_10_1109_ACCESS_2022_3181194 crossref_primary_10_1049_smt2_12125
Cites_doi	10.1073/pnas.1031596100 10.1109/ACCESS.2018.2859299 10.1109/TVT.2015.2498281 10.1109/MIS.2017.38 10.1109/ACCESS.2018.2807700 10.1109/TNNLS.2016.2551724 10.1109/TMM.2017.2663324 10.1007/s11227-015-1421-0 10.1109/TIP.2015.2495116 10.1016/j.compbiomed.2018.05.027 10.1109/TNNLS.2016.2636325 10.1016/S0893-6080(99)00073-8 10.1109/TGRS.2016.2543748 10.1126/science.290.5500.2319 10.1103/PhysRevB.95.035105 10.1109/TKDE.2010.165 10.4049/jimmunol.1602077 10.1109/34.908974 10.1117/1.JRS.7.073478 10.1109/TNNLS.2017.2649101 10.1109/IJCNN.1990.137696 10.1109/TIP.2006.881945 10.1111/hcre.12114 10.1145/1458082.1458202 10.1109/TIE.2017.2739691 10.1126/science.1127647 10.1109/TSMC.2016.2605132 10.1103/PhysRevB.97.085104 10.1155/2018/3078374 10.1109/TMI.2015.2458702 10.1126/science.290.5500.2323
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2018.2884697
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	73814
ExternalDocumentID	oai_doaj_org_article_b3d938628d9041e997fd31b0edceac81 10_1109_ACCESS_2018_2884697 8558569
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 61703196 funderid: 10.13039/501100001809 – fundername: Natural Science Foundation of Fujian Province grantid: 2018J01549 funderid: 10.13039/501100003392
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c408t-29e1e014e1fff5c6f4856ee1b06106a5c672ff189748aabff773e38bbe20d1a93
IEDL.DBID	DOA
ISICitedReferencesCount	19
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000454257600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:43:43 EDT 2025 Sun Nov 30 04:05:28 EST 2025 Sat Nov 29 03:33:33 EST 2025 Tue Nov 18 21:51:49 EST 2025 Wed Aug 27 03:03:39 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/OAPA.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c408t-29e1e014e1fff5c6f4856ee1b06106a5c672ff189748aabff773e38bbe20d1a93
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-5835-7913
OpenAccessLink	https://doaj.org/article/b3d938628d9041e997fd31b0edceac81
PQID	2455929409
PQPubID	4845423
PageCount	13
ParticipantIDs	ieee_primary_8558569 doaj_primary_oai_doaj_org_article_b3d938628d9041e997fd31b0edceac81 crossref_citationtrail_10_1109_ACCESS_2018_2884697 crossref_primary_10_1109_ACCESS_2018_2884697 proquest_journals_2455929409
PublicationCentury	2000
PublicationDate	20180000 2018-00-00 20180101 2018-01-01
PublicationDateYYYYMMDD	2018-01-01
PublicationDate_xml	– year: 2018 text: 20180000
PublicationDecade	2010
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2018
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	roweis (ref30) 2000; 290 ref13 fischer (ref37) 2012; 7441 ref12 ah-hin (ref28) 2016; 50 ref36 ref14 ref10 ref2 ref1 ref17 ref38 donoho (ref31) 2003; 100 ref18 belkin (ref33) 2009; 14 hu (ref19) 2009; 31 vapnik (ref23) 1996; 9 krizhevsky (ref40) 2009 yang (ref15) 2018; 6 ref24 ng (ref39) 2011 ref45 ref26 ref25 ref20 ref22 ref44 van der maaten (ref11) 2008; 9 ref21 tan (ref27) 2005 netzer (ref43) 2011 tenenbaum (ref32) 2000; 290 he (ref35) 2003; 16 ref29 ref8 ref7 ref9 ref4 ref3 hinton (ref16) 2006; 313 ref6 ref5 he (ref34) 2005; 2 de campos (ref41) 2009 marcel (ref42) 1999; 1739
References_xml	– volume: 100 start-page: 5591 year: 2003 ident: ref31 article-title: Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data publication-title: Proc Nat Acad Sci USA doi: 10.1073/pnas.1031596100 – volume: 6 start-page: 40723 year: 2018 ident: ref15 article-title: $L_{2,1}$ -norm discriminant manifold learning publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2859299 – ident: ref5 doi: 10.1109/TVT.2015.2498281 – ident: ref3 doi: 10.1109/MIS.2017.38 – volume: 9 start-page: 281 year: 1996 ident: ref23 article-title: Support vector method for function approximation, regression estimation and signal processing publication-title: Proc Adv Neural Inf Process Syst – volume: 50 start-page: 79 year: 2016 ident: ref28 article-title: Modelling and forecasting with financial duration data using non-linear model publication-title: Econ Comput Econ Stud Res – ident: ref22 doi: 10.1109/ACCESS.2018.2807700 – ident: ref9 doi: 10.1109/TNNLS.2016.2551724 – ident: ref8 doi: 10.1109/TMM.2017.2663324 – ident: ref25 doi: 10.1007/s11227-015-1421-0 – year: 2011 ident: ref39 publication-title: Sparse Autoencoder – ident: ref4 doi: 10.1109/TIP.2015.2495116 – ident: ref21 doi: 10.1016/j.compbiomed.2018.05.027 – volume: 9 start-page: 2579 year: 2008 ident: ref11 article-title: Visualizing data using t-SNE publication-title: J Mach Learn Res – volume: 7441 start-page: 14 year: 2012 ident: ref37 article-title: An introduction to restricted Boltzmann machines publication-title: Proc 17th Iberoamer Congr (CIARP) – ident: ref17 doi: 10.1109/TNNLS.2016.2636325 – ident: ref24 doi: 10.1016/S0893-6080(99)00073-8 – ident: ref6 doi: 10.1109/TGRS.2016.2543748 – volume: 290 start-page: 2319 year: 2000 ident: ref32 article-title: A global geometric framework for nonlinear dimensionality reduction publication-title: Science doi: 10.1126/science.290.5500.2319 – volume: 14 start-page: 585 year: 2009 ident: ref33 article-title: Laplacian eigenmaps and spectral techniques for embedding and clustering publication-title: Proc Adv Neural Inf Process Syst – volume: 1739 start-page: 302 year: 1999 ident: ref42 article-title: Hand posture recognition in a body-face centered space publication-title: Gesture-Based Communication in Human-Computer Interaction – ident: ref13 doi: 10.1103/PhysRevB.95.035105 – ident: ref45 doi: 10.1109/TKDE.2010.165 – volume: 16 start-page: 186 year: 2003 ident: ref35 article-title: Locality preserving projections publication-title: Proc Adv Neural Inf Process Syst – ident: ref12 doi: 10.4049/jimmunol.1602077 – ident: ref26 doi: 10.1109/34.908974 – start-page: 273 year: 2009 ident: ref41 article-title: Character recognition in natural images publication-title: Proc Int Conf Comput Vis Theory Appl (VISAPP) – ident: ref29 doi: 10.1117/1.JRS.7.073478 – ident: ref2 doi: 10.1109/TNNLS.2017.2649101 – ident: ref10 doi: 10.1109/IJCNN.1990.137696 – year: 2005 ident: ref27 publication-title: The theory and application of the dimension reduction on the high-dimentional data set – start-page: 5 year: 2011 ident: ref43 article-title: Reading digits in natural images with unsupervised feature learning publication-title: Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning – ident: ref36 doi: 10.1109/TIP.2006.881945 – volume: 2 start-page: 1208 year: 2005 ident: ref34 article-title: Neighborhood preserving embedding publication-title: Proc 10th IEEE Int Conf Comput Vis – ident: ref1 doi: 10.1111/hcre.12114 – ident: ref44 doi: 10.1145/1458082.1458202 – start-page: 1 year: 2009 ident: ref40 article-title: Learning multiple layers of features from tiny images publication-title: Proc Int Conf Comput Vis Theory Appl (VISAPP) – ident: ref18 doi: 10.1109/TIE.2017.2739691 – volume: 313 start-page: 504 year: 2006 ident: ref16 article-title: Reducing the dimensionality of data with neural networks publication-title: Science doi: 10.1126/science.1127647 – volume: 31 start-page: 1189 year: 2009 ident: ref19 article-title: Dimensionality reduction and reconstruction of data based on autoencoder network publication-title: J Electron Inf Technol – ident: ref7 doi: 10.1109/TSMC.2016.2605132 – ident: ref14 doi: 10.1103/PhysRevB.97.085104 – ident: ref20 doi: 10.1155/2018/3078374 – ident: ref38 doi: 10.1109/TMI.2015.2458702 – volume: 290 start-page: 2323 year: 2000 ident: ref30 article-title: Nonlinear dimensionality reduction by locally linear embedding publication-title: Science doi: 10.1126/science.290.5500.2323
SSID	ssj0000816957
Score	2.233034
Snippet	Dimensionality reduction is commonly used to preprocess high-dimensional data, which is an essential step in machine learning and data mining. An outstanding...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	73802
SubjectTerms	Algorithms Classification Cognitive tasks Data mining Datasets Dimensionality reduction Feature extraction feature representation Labels Machine learning Optimization Parameter sensitivity Principal component analysis Reduction Representations sparse autoencoder Stress Supervised learning
SummonAdditionalLinks	– databaseName: IEEE Electronic Library (IEL) dbid: RIE link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS-QwEB50uQd9OE89cXVP-uCj1aRpm-RxXRSfRPAE30LSTESQ3WV_-PffpI1V8BB8K2lSkpkmM98k-QbglAUySoWVOXPe52XcJLQiEOZxlW7IngTmmzbZhLy9VY-P-m4Dzvq7MIjYHj7D8_jY7uX7WbOOobILVZFzW-tN2JRSdne1-nhKTCChK5mIhTjTF-PJhMYQT2-p80KRnY3ETh-MT8vRn5KqfFqJW_NyvfO9jv2Cn8mNzMad3ndhA6d7sP2BXHAf5P16HheCJfossag-Za_PNnuYLt_f3M8J2WI2Xq9mkdLS4-I3PFxf_Z3c5ClNQt6UTK3yQiNHQjrIQwhVU4eS-oLIHZlqVlsqkUUIXBFyUNa6EKQUKJRzWDDPrRYHMJjOpngImcI6SBZdMPJUaiZcZW0Q2jmmA6-ZGkLxJj_TJA7xmMrixbRYgmnTCd1EoZsk9CGc9Y3mHYXG19Uvo2L6qpH_ui0giZs0nYwTXgsCY8prVnLUWgYvaMTxTKttFB_CftRS_5GkoCGM3tRs0lxdmqIkVFVoArpH_291DFuxg13gZQSD1WKNf-BH87p6Xi5O2t_wH7jr2lM priority: 102 providerName: IEEE
Title	Supervised Learning via Unsupervised Sparse Autoencoder
URI	https://ieeexplore.ieee.org/document/8558569 https://www.proquest.com/docview/2455929409 https://doaj.org/article/b3d938628d9041e997fd31b0edceac81
Volume	6
WOSCitedRecordID	wos000454257600001&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: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 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: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3PS8MwFA4iHvQg6hTnL3rwaDU_2iY5zjHxogg68BaSJpGBzLF1O_q3-5JmcyDoxUsPadom32vy3tcm30PoEntwSlTzHBtr8yL8JNTMA-cxpazBn3hs65hsgj8-itdX-bSW6iusCWvlgVvgbgyzkkHYLazEBXFScm8ZMTisXtR13HRNIepZI1NxDhakkiVPMkMEy5tevw89Cmu5xDUV4HWDzNOaK4qK_SnFyo95OTqbuz20m6LErNe2bh9tuPEB2lnTDuwg_jyfhHE-czZLIqlv2WKks-F49n3meQLE1WW9efMRFCutmx6i4d3gpX-fpywIeV1g0eRUOuKAyDjivS_ryheirJwDCCDyqTSUcOo9EUAMhNbGe86ZY8IYR7ElWrIjtDn-GLtjlAlXeY5DhAWBSIWZKbX2TBqDpScVFl1El4CoOkmEh0wV7ypSBSxVi6IKKKqEYhddrS6atAoZv1e_DUivqgZ561gARlfJ6Oovo3dRJ9hpdRNRAuupZBedLe2m0lCcKVoAaaISeOzJfzz6FG2H7rRfYc7QZjOdu3O0VS-a0Wx6Ed9COD58Di7iXsIvIXnfyA
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La9wwEB7StNDmkD7S0k3T1oce40QP25KO26UhpelSSAK5CckalUDZXfaR35-RrTiBlkJuRpaMNGNp5htJ3wB8YZGMknCqZD6EskqbhE5Gwjy-Ni3Zk8hC2yWbUNOpvroyv7bgcLgLg4jd4TM8So_dXn6Yt5sUKjvWNTm3jXkCT-uqEry_rTVEVFIKCVOrTC3EmTkeTyY0inR-Sx8JTZY2UTs9MD8dS39Oq_LXWtwZmJOXj-vaK9jNjmQx7jX_GrZw9gZ2HtAL7oE63yzSUrDCUGQe1d_FzbUrLmer-zfnC8K2WIw363kitQy4fAuXJ98uJqdlTpRQthXT61IY5EhYB3mMsW6bWFFfELknY80aRyVKxMg1YQftnI9RKYlSe4-CBe6MfAfbs_kM30OhsYmKJSeMfJWGSV87F6XxnpnIG6ZHIO7kZ9vMIp6SWfyxHZpgxvZCt0noNgt9BIdDo0VPovH_6l-TYoaqiQG7KyCJ2zyhrJfBSIJjOhhWcTRGxSBpxOlUq2s1H8Fe0tLwkaygERzcqdnm2bqyoiJcJQxB3f1_t_oMz08vfp7Zs-_THx_gRepsH4Y5gO31coMf4Vl7s75eLT91v-QtOsrdmg
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=Supervised+Learning+via+Unsupervised+Sparse+Autoencoder&rft.jtitle=IEEE+access&rft.au=Liu%2C+Jianran&rft.au=Li%2C+Chan&rft.au=Yang%2C+Wenyuan&rft.date=2018&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=6&rft.spage=73802&rft.epage=73814&rft_id=info:doi/10.1109%2FACCESS.2018.2884697&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2018_2884697
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon