Denoising Autoencoder Self-Organizing Map (DASOM)

In this report, we address the question of combining nonlinearities of neurons into networks for modeling increasingly varying and progressively more complex functions. A fundamental approach is the use of higher-level representations devised by restricted Boltzmann machines and (denoising) autoenco...

Full description

Saved in:

Bibliographic Details
Published in:	Neural networks Vol. 105; pp. 112 - 131
Main Authors:	Ferles, Christos, Papanikolaou, Yannis, Naidoo, Kevin J.
Format:	Journal Article
Language:	English
Published:	United States Elsevier Ltd 01.09.2018
Subjects:	Clustering Denoising autoencoder Self-organizing map Unsupervised learning Visualization Visualization Denoising autoencoder Clustering Self-organizing map Unsupervised learning
ISSN:	0893-6080, 1879-2782, 1879-2782
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	In this report, we address the question of combining nonlinearities of neurons into networks for modeling increasingly varying and progressively more complex functions. A fundamental approach is the use of higher-level representations devised by restricted Boltzmann machines and (denoising) autoencoders. We present the Denoising Autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end component is a grid of topologically ordered neurons. The approach is to interpose a layer of hidden representations between the input space and the neural lattice of the self-organizing map. In so doing the parameters are adjusted by the proposed unsupervised learning algorithm. The model therefore maintains the clustering properties of its predecessor, whereas by extending and enhancing its visualization capacity enables an inclusion and an analysis of the intermediate representation space. A comprehensive series of experiments comprising optical recognition of text and images, and cancer type clustering and categorization is used to demonstrate DASOM’s efficiency, performance and projection capabilities.
AbstractList	In this report, we address the question of combining nonlinearities of neurons into networks for modeling increasingly varying and progressively more complex functions. A fundamental approach is the use of higher-level representations devised by restricted Boltzmann machines and (denoising) autoencoders. We present the Denoising Autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end component is a grid of topologically ordered neurons. The approach is to interpose a layer of hidden representations between the input space and the neural lattice of the self-organizing map. In so doing the parameters are adjusted by the proposed unsupervised learning algorithm. The model therefore maintains the clustering properties of its predecessor, whereas by extending and enhancing its visualization capacity enables an inclusion and an analysis of the intermediate representation space. A comprehensive series of experiments comprising optical recognition of text and images, and cancer type clustering and categorization is used to demonstrate DASOM’s efficiency, performance and projection capabilities. In this report, we address the question of combining nonlinearities of neurons into networks for modeling increasingly varying and progressively more complex functions. A fundamental approach is the use of higher-level representations devised by restricted Boltzmann machines and (denoising) autoencoders. We present the Denoising Autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end component is a grid of topologically ordered neurons. The approach is to interpose a layer of hidden representations between the input space and the neural lattice of the self-organizing map. In so doing the parameters are adjusted by the proposed unsupervised learning algorithm. The model therefore maintains the clustering properties of its predecessor, whereas by extending and enhancing its visualization capacity enables an inclusion and an analysis of the intermediate representation space. A comprehensive series of experiments comprising optical recognition of text and images, and cancer type clustering and categorization is used to demonstrate DASOM's efficiency, performance and projection capabilities.In this report, we address the question of combining nonlinearities of neurons into networks for modeling increasingly varying and progressively more complex functions. A fundamental approach is the use of higher-level representations devised by restricted Boltzmann machines and (denoising) autoencoders. We present the Denoising Autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end component is a grid of topologically ordered neurons. The approach is to interpose a layer of hidden representations between the input space and the neural lattice of the self-organizing map. In so doing the parameters are adjusted by the proposed unsupervised learning algorithm. The model therefore maintains the clustering properties of its predecessor, whereas by extending and enhancing its visualization capacity enables an inclusion and an analysis of the intermediate representation space. A comprehensive series of experiments comprising optical recognition of text and images, and cancer type clustering and categorization is used to demonstrate DASOM's efficiency, performance and projection capabilities.
Author	Papanikolaou, Yannis Naidoo, Kevin J. Ferles, Christos
Author_xml	– sequence: 1 givenname: Christos surname: Ferles fullname: Ferles, Christos email: christos.ferles@gmail.com, Christos.Ferles@uct.ac.za organization: Scientific Computing Research Unit, Faculty of Science, University of Cape Town, Rondebosch, 7701, South Africa – sequence: 2 givenname: Yannis surname: Papanikolaou fullname: Papanikolaou, Yannis email: ypapanik@csd.auth.gr organization: Department of Informatics, Aristotle University of Thessaloniki, 54124, Thessaloniki, Greece – sequence: 3 givenname: Kevin J. orcidid: 0000-0002-9898-3708 surname: Naidoo fullname: Naidoo, Kevin J. email: kevin.naidoo@uct.ac.za organization: Scientific Computing Research Unit, Faculty of Science, University of Cape Town, Rondebosch, 7701, South Africa
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/29803188$$D View this record in MEDLINE/PubMed
BookMark	eNqFkE1LxDAQhoMoun78A5E96qF1kqYx9SAs6ycoe1DPIU0nkqWbrEkr6K-3y6oHD3oaeOd5B-bZJZs-eCTkkEJOgYrTee6x99jlDKjMgedDuEFGVJ5VGTuTbJOMQFZFJkDCDtlNaQ4AQvJim-ywSkJBpRwReok-uOT8y3jSdwG9CQ3G8SO2NpvFF-3dx2r3oJfj48vJ4-zhZJ9sWd0mPPiae-T5-uppepvdz27uppP7zBSCdZkR3AphGLesroQoDasBagncMIoaS7B11XBkphSyZqU2w8JKbssKLdQWij1yvL67jOG1x9SphUsG21Z7DH1SDHjJRFWWfECPvtC-XmCjltEtdHxX328OAF8DJoaUItofhIJa2VRztbapVjYVcDWEQ-38V824Tncu-C5q1_5XvliXcZD05jCqZNzgFxsX0XSqCe7vA58bO5DI
CitedBy_id	crossref_primary_10_1109_ACCESS_2020_3040298 crossref_primary_10_1016_j_jrras_2023_100691 crossref_primary_10_1109_TII_2019_2906083 crossref_primary_10_3390_make3040044 crossref_primary_10_1109_ACCESS_2021_3112397 crossref_primary_10_1016_j_aej_2024_08_081 crossref_primary_10_1145_3568308 crossref_primary_10_1016_j_procs_2020_03_341 crossref_primary_10_1016_j_neunet_2025_107528 crossref_primary_10_1007_s00521_021_06331_w crossref_primary_10_1016_j_buildenv_2023_110573 crossref_primary_10_1016_j_ijar_2019_02_006 crossref_primary_10_1016_j_ins_2023_119121 crossref_primary_10_1051_matecconf_201925209001 crossref_primary_10_3390_mti7080075 crossref_primary_10_1190_geo2021_0798_1 crossref_primary_10_1109_ACCESS_2020_3000829 crossref_primary_10_1109_TVCG_2023_3337868 crossref_primary_10_1007_s42979_022_01344_1 crossref_primary_10_1016_j_asoc_2020_106627 crossref_primary_10_3390_ijms221910891 crossref_primary_10_1111_exsy_12435 crossref_primary_10_1007_s00170_020_06009_y crossref_primary_10_1007_s40747_022_00826_2 crossref_primary_10_1016_j_ins_2021_04_074 crossref_primary_10_1016_j_sasc_2024_200079 crossref_primary_10_1007_s11063_020_10251_6 crossref_primary_10_1155_2020_2971565 crossref_primary_10_1049_iet_sen_2019_0278 crossref_primary_10_1016_j_asoc_2020_107003
Cites_doi	10.1016/j.neunet.2012.09.018 10.1109/TNN.2005.845141 10.1016/S0893-6080(05)80089-9 10.1007/BF00288907 10.3233/IDA-1999-3203 10.1364/JOSAA.20.001434 10.1109/72.977314 10.1016/j.neunet.2006.05.013 10.1016/j.neunet.2014.09.003 10.1007/BF00275687 10.1523/JNEUROSCI.4364-03.2004 10.1145/331499.331504 10.1109/TNN.2007.909556 10.1016/S0042-6989(97)00464-1 10.1016/j.neucom.2004.01.008 10.1561/2200000006 10.1142/S0129065791000030 10.1109/34.291440 10.1016/j.patrec.2009.09.011 10.1109/TNN.2008.2005409 10.1162/neco.2006.18.7.1527 10.1109/TNN.2006.871720 10.1109/TSMCB.2003.810442
ContentType	Journal Article
Copyright	2018 Elsevier Ltd Copyright © 2018 Elsevier Ltd. All rights reserved.
Copyright_xml	– notice: 2018 Elsevier Ltd – notice: Copyright © 2018 Elsevier Ltd. All rights reserved.
DBID	AAYXX CITATION NPM 7X8
DOI	10.1016/j.neunet.2018.04.016
DatabaseName	CrossRef PubMed MEDLINE - Academic
DatabaseTitle	CrossRef PubMed MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic PubMed
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	1879-2782
EndPage	131
ExternalDocumentID	29803188 10_1016_j_neunet_2018_04_016 S0893608018301382
Genre	Journal Article
GroupedDBID	--- --K --M -~X .DC .~1 0R~ 123 186 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 53G 5RE 5VS 6TJ 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXLA AAXUO AAYFN ABAOU ABBOA ABCQJ ABEFU ABFNM ABFRF ABHFT ABIVO ABJNI ABLJU ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFO ACGFS ACIUM ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADRHT AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HMQ HVGLF HZ~ IHE J1W JJJVA K-O KOM KZ1 LG9 LMP M2V M41 MHUIS MO0 MOBAO MVM N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCC SDF SDG SDP SES SEW SNS SPC SPCBC SSN SST SSV SSW SSZ T5K TAE UAP UNMZH VOH WUQ XPP ZMT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD AGCQF AGRNS NPM SSH 7X8
ID	FETCH-LOGICAL-c362t-c64f66c24f2b9665c2b00b804c21eae50fb9d4e2c568b25ac4c2f84f59ef0bf03
ISICitedReferencesCount	44
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000441874700010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0893-6080 1879-2782
IngestDate	Sun Sep 28 10:06:04 EDT 2025 Mon Jul 21 05:55:51 EDT 2025 Sat Nov 29 07:09:31 EST 2025 Tue Nov 18 22:00:30 EST 2025 Fri Feb 23 02:48:56 EST 2024
IsPeerReviewed	true
IsScholarly	true
Keywords	Visualization Denoising autoencoder Clustering Self-organizing map Unsupervised learning
Language	English
License	Copyright © 2018 Elsevier Ltd. All rights reserved.
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c362t-c64f66c24f2b9665c2b00b804c21eae50fb9d4e2c568b25ac4c2f84f59ef0bf03
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0002-9898-3708
PMID	29803188
PQID	2045269554
PQPubID	23479
PageCount	20
ParticipantIDs	proquest_miscellaneous_2045269554 pubmed_primary_29803188 crossref_primary_10_1016_j_neunet_2018_04_016 crossref_citationtrail_10_1016_j_neunet_2018_04_016 elsevier_sciencedirect_doi_10_1016_j_neunet_2018_04_016
PublicationCentury	2000
PublicationDate	2018-09-01
PublicationDateYYYYMMDD	2018-09-01
PublicationDate_xml	– month: 09 year: 2018 text: 2018-09-01 day: 01
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	Neural networks
PublicationTitleAlternate	Neural Netw
PublicationYear	2018
Publisher	Elsevier Ltd
Publisher_xml	– name: Elsevier Ltd
References	Heskes (b11) 1999 Ito, Komatsu (b14) 2004; 24 Vesanto (b34) 1999; 3 Kohonen (b19) 2014 Arthur, Vassilvitskii (b1) 2007 (pp. 225–230). Von der Malsburg (b37) 1973; 14 Hammer, Micheli, Sperduti, Strickert (b10) 2004; 57 Pampalk, Rauber, Merkl (b26) 2002 Bengio, Lamblin, Popovici, Larochelle (b5) 2007; 19 Erhan, Manzagol, Bengio, Bengio, Vincent (b9) 2009 Jain, Murty, Flynn (b16) 1999; 31 Becker (b3) 1991; 2 Jain (b15) 2010; 31 Ultsch, A. (2005). Clustering wih som: U* c. In Brugger, Bogdan, Rosenstiel (b7) 2008; 19 Lee, Mumford (b21) 2003; 20 Erhan, Bengio, Courville, Manzagol, Vincent, Bengio (b8) 2010; 11 Vincent, Larochelle, Lajoie, Bengio, Manzagol (b36) 2010; 11 Yin (b39) 2002; 13 (pp. 75–82). Kohonen (b17) 2001; vol. 30 Tasdemir, Merényi (b31) 2009; 20 Ultsch, A. (2003). Maps for the visualization of high-dimensional data spaces. In Pölzlbauer, Dittenbach, Rauber (b27) 2006; 19 Lee, Mumford, Romero, Lamme (b22) 1998; 38 Oja (b24) 1982; 15 Vincent, Larochelle, Bengio, Manzagol (b35) 2008 Bache, Lichman (b2) 2013 Nene, S. A., Nayar, S. K., & Murase, H. (1996). Columbia object image library (COIL-20). In: Technical report CUCS-005-96. Xu, Wunsch (b38) 2005; 16 Lee, Ekanadham, Ng (b20) 2008 Hinton, Osindero, Teh (b12) 2006; 18 Shah-Hosseini, Safabakhsh (b29) 2003; 33 Hull (b13) 1994; 16 Kohonen (b18) 2013; 37 Oja (b25) 1992; 5 Bengio (b4) 2009; 2 Schmidhuber (b28) 2015; 61 Strehl, Ghosh (b30) 2002; 3 Berglund, Sitte (b6) 2006; 17 Erhan (10.1016/j.neunet.2018.04.016_b9) 2009 10.1016/j.neunet.2018.04.016_b23 Vincent (10.1016/j.neunet.2018.04.016_b36) 2010; 11 Xu (10.1016/j.neunet.2018.04.016_b38) 2005; 16 Shah-Hosseini (10.1016/j.neunet.2018.04.016_b29) 2003; 33 Pampalk (10.1016/j.neunet.2018.04.016_b26) 2002 Vincent (10.1016/j.neunet.2018.04.016_b35) 2008 Becker (10.1016/j.neunet.2018.04.016_b3) 1991; 2 Hammer (10.1016/j.neunet.2018.04.016_b10) 2004; 57 Lee (10.1016/j.neunet.2018.04.016_b21) 2003; 20 Jain (10.1016/j.neunet.2018.04.016_b16) 1999; 31 Arthur (10.1016/j.neunet.2018.04.016_b1) 2007 Lee (10.1016/j.neunet.2018.04.016_b22) 1998; 38 Kohonen (10.1016/j.neunet.2018.04.016_b18) 2013; 37 Bache (10.1016/j.neunet.2018.04.016_b2) 2013 Schmidhuber (10.1016/j.neunet.2018.04.016_b28) 2015; 61 Heskes (10.1016/j.neunet.2018.04.016_b11) 1999 Strehl (10.1016/j.neunet.2018.04.016_b30) 2002; 3 Von der Malsburg (10.1016/j.neunet.2018.04.016_b37) 1973; 14 Lee (10.1016/j.neunet.2018.04.016_b20) 2008 Oja (10.1016/j.neunet.2018.04.016_b24) 1982; 15 Pölzlbauer (10.1016/j.neunet.2018.04.016_b27) 2006; 19 Brugger (10.1016/j.neunet.2018.04.016_b7) 2008; 19 Jain (10.1016/j.neunet.2018.04.016_b15) 2010; 31 Bengio (10.1016/j.neunet.2018.04.016_b4) 2009; 2 10.1016/j.neunet.2018.04.016_b33 10.1016/j.neunet.2018.04.016_b32 Hinton (10.1016/j.neunet.2018.04.016_b12) 2006; 18 Ito (10.1016/j.neunet.2018.04.016_b14) 2004; 24 Tasdemir (10.1016/j.neunet.2018.04.016_b31) 2009; 20 Yin (10.1016/j.neunet.2018.04.016_b39) 2002; 13 Hull (10.1016/j.neunet.2018.04.016_b13) 1994; 16 Berglund (10.1016/j.neunet.2018.04.016_b6) 2006; 17 Kohonen (10.1016/j.neunet.2018.04.016_b19) 2014 Bengio (10.1016/j.neunet.2018.04.016_b5) 2007; 19 Oja (10.1016/j.neunet.2018.04.016_b25) 1992; 5 Erhan (10.1016/j.neunet.2018.04.016_b8) 2010; 11 Kohonen (10.1016/j.neunet.2018.04.016_b17) 2001; vol. 30 Vesanto (10.1016/j.neunet.2018.04.016_b34) 1999; 3
References_xml	– volume: 19 start-page: 153 year: 2007 ident: b5 article-title: Greedy layer-wise training of deep networks publication-title: Advances in Neural Information Processing Systems – volume: 31 start-page: 264 year: 1999 end-page: 323 ident: b16 article-title: Data clustering: a review publication-title: ACM Computing Surveys (CSUR) – volume: 5 start-page: 927 year: 1992 end-page: 935 ident: b25 article-title: Principal components, minor components, and linear neural networks publication-title: Neural Networks – volume: 20 start-page: 1434 year: 2003 end-page: 1448 ident: b21 article-title: Hierarchical Bayesian inference in the visual cortex publication-title: Journal of the Optical Society of America A – start-page: 1096 year: 2008 end-page: 1103 ident: b35 article-title: Extracting and composing robust features with denoising autoencoders publication-title: Proceedings of the 25th international conference on machine learning – start-page: 1027 year: 2007 end-page: 1035 ident: b1 article-title: k-means++: The advantages of careful seeding publication-title: Proceedings of the eighteenth annual ACM-SIAM symposium on discrete algorithms – reference: Nene, S. A., Nayar, S. K., & Murase, H. (1996). Columbia object image library (COIL-20). In: Technical report CUCS-005-96. – volume: 19 start-page: 442 year: 2008 end-page: 459 ident: b7 article-title: Automatic cluster detection in Kohonen’s SOM publication-title: IEEE Transactions on Neural Networks – volume: 19 start-page: 911 year: 2006 end-page: 922 ident: b27 article-title: Advanced visualization of self-organizing maps with vector fields publication-title: Neural Networks – start-page: 153 year: 2009 end-page: 160 ident: b9 article-title: The difficulty of training deep architectures and the effect of unsupervised pre-training publication-title: AISTATS, Vol. 5 – volume: 11 start-page: 3371 year: 2010 end-page: 3408 ident: b36 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: Journal of Machine Learning Research (JMLR) – volume: 3 start-page: 111 year: 1999 end-page: 126 ident: b34 article-title: SOM-based data visualization methods publication-title: Intelligent Data Analysis – volume: 14 start-page: 85 year: 1973 end-page: 100 ident: b37 article-title: Self-organization of orientation sensitive cells in the striate cortex publication-title: Kybernetik – year: 2013 ident: b2 article-title: UCI machine learning repository – reference: Ultsch, A. (2003). Maps for the visualization of high-dimensional data spaces. In: – volume: 24 start-page: 3313 year: 2004 end-page: 3324 ident: b14 article-title: Representation of angles embedded within contour stimuli in area V2 of macaque monkeys publication-title: The Journal of Neuroscience – volume: 15 start-page: 267 year: 1982 end-page: 273 ident: b24 article-title: Simplified neuron model as a principal component analyzer publication-title: Journal of Mathematical Biology – volume: 2 start-page: 1 year: 2009 end-page: 127 ident: b4 article-title: Learning deep architectures for AI publication-title: Foundation and Trends – volume: 57 start-page: 3 year: 2004 end-page: 35 ident: b10 article-title: A general framework for unsupervised processing of structured data publication-title: Neurocomputing – volume: 18 start-page: 1527 year: 2006 end-page: 1554 ident: b12 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Computation – start-page: 873 year: 2008 end-page: 880 ident: b20 article-title: Sparse deep belief net model for visual area V2 publication-title: Advances in Neural Information Processing Systems – volume: 33 start-page: 271 year: 2003 end-page: 282 ident: b29 article-title: TASOM: a new time adaptive self-organizing map publication-title: IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) – volume: 16 start-page: 550 year: 1994 end-page: 554 ident: b13 article-title: A database for handwritten text recognition research publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: 61 start-page: 85 year: 2015 end-page: 117 ident: b28 article-title: Deep learning in neural networks: An overview publication-title: Neural Networks – reference: , (pp. 225–230). – volume: 20 start-page: 549 year: 2009 end-page: 562 ident: b31 article-title: Exploiting data topology in visualization and clustering of self-organizing maps publication-title: IEEE Transactions on Neural Networks – reference: , (pp. 75–82). – volume: 31 start-page: 651 year: 2010 end-page: 666 ident: b15 article-title: Data clustering: 50 years beyond K-means publication-title: Pattern Recognition Letters – volume: vol. 30 year: 2001 ident: b17 publication-title: Self-organizing maps – volume: 38 start-page: 2429 year: 1998 end-page: 2454 ident: b22 article-title: The role of the primary visual cortex in higher level vision publication-title: Vision Research – start-page: 871 year: 2002 end-page: 876 ident: b26 article-title: Using smoothed data histograms for cluster visualization in self-organizing maps publication-title: International conference on artificial neural networks – volume: 17 start-page: 305 year: 2006 end-page: 316 ident: b6 article-title: The parameterless self-organizing map algorithm publication-title: IEEE Transactions on Neural Networks – volume: 2 start-page: 17 year: 1991 end-page: 33 ident: b3 article-title: Unsupervised learning procedures for neural networks publication-title: International Journal of Neural Systems – start-page: 303 year: 1999 end-page: 315 ident: b11 article-title: Energy functions for self-organizing maps publication-title: Kohonen maps – volume: 37 start-page: 52 year: 2013 end-page: 65 ident: b18 article-title: Essentials of the self-organizing map publication-title: Neural Networks – volume: 3 start-page: 583 year: 2002 end-page: 617 ident: b30 article-title: Cluster ensembles—a knowledge reuse framework for combining multiple partitions publication-title: Journal of Machine Learning Research (JMLR) – volume: 16 start-page: 645 year: 2005 end-page: 678 ident: b38 article-title: Survey of clustering algorithms publication-title: IEEE Transactions on Neural Networks – volume: 13 start-page: 237 year: 2002 end-page: 243 ident: b39 article-title: ViSOM-a novel method for multivariate data projection and structure visualization publication-title: IEEE Transactions on Neural Networks – volume: 11 start-page: 625 year: 2010 end-page: 660 ident: b8 article-title: Why does unsupervised pre-training help deep learning? publication-title: Journal of Machine Learning Research (JMLR) – reference: Ultsch, A. (2005). Clustering wih som: U* c. In: – start-page: 11 year: 2014 end-page: 23 ident: b19 article-title: MATLAB implementations and applications of the self-organizing map – start-page: 153 year: 2009 ident: 10.1016/j.neunet.2018.04.016_b9 article-title: The difficulty of training deep architectures and the effect of unsupervised pre-training – volume: vol. 30 year: 2001 ident: 10.1016/j.neunet.2018.04.016_b17 – volume: 11 start-page: 625 year: 2010 ident: 10.1016/j.neunet.2018.04.016_b8 article-title: Why does unsupervised pre-training help deep learning? publication-title: Journal of Machine Learning Research (JMLR) – volume: 37 start-page: 52 year: 2013 ident: 10.1016/j.neunet.2018.04.016_b18 article-title: Essentials of the self-organizing map publication-title: Neural Networks doi: 10.1016/j.neunet.2012.09.018 – volume: 16 start-page: 645 year: 2005 ident: 10.1016/j.neunet.2018.04.016_b38 article-title: Survey of clustering algorithms publication-title: IEEE Transactions on Neural Networks doi: 10.1109/TNN.2005.845141 – volume: 5 start-page: 927 year: 1992 ident: 10.1016/j.neunet.2018.04.016_b25 article-title: Principal components, minor components, and linear neural networks publication-title: Neural Networks doi: 10.1016/S0893-6080(05)80089-9 – start-page: 1096 year: 2008 ident: 10.1016/j.neunet.2018.04.016_b35 article-title: Extracting and composing robust features with denoising autoencoders – volume: 14 start-page: 85 year: 1973 ident: 10.1016/j.neunet.2018.04.016_b37 article-title: Self-organization of orientation sensitive cells in the striate cortex publication-title: Kybernetik doi: 10.1007/BF00288907 – ident: 10.1016/j.neunet.2018.04.016_b32 – volume: 3 start-page: 111 year: 1999 ident: 10.1016/j.neunet.2018.04.016_b34 article-title: SOM-based data visualization methods publication-title: Intelligent Data Analysis doi: 10.3233/IDA-1999-3203 – volume: 20 start-page: 1434 year: 2003 ident: 10.1016/j.neunet.2018.04.016_b21 article-title: Hierarchical Bayesian inference in the visual cortex publication-title: Journal of the Optical Society of America A doi: 10.1364/JOSAA.20.001434 – volume: 13 start-page: 237 year: 2002 ident: 10.1016/j.neunet.2018.04.016_b39 article-title: ViSOM-a novel method for multivariate data projection and structure visualization publication-title: IEEE Transactions on Neural Networks doi: 10.1109/72.977314 – year: 2013 ident: 10.1016/j.neunet.2018.04.016_b2 – volume: 11 start-page: 3371 year: 2010 ident: 10.1016/j.neunet.2018.04.016_b36 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: Journal of Machine Learning Research (JMLR) – start-page: 303 year: 1999 ident: 10.1016/j.neunet.2018.04.016_b11 article-title: Energy functions for self-organizing maps – start-page: 871 year: 2002 ident: 10.1016/j.neunet.2018.04.016_b26 article-title: Using smoothed data histograms for cluster visualization in self-organizing maps – volume: 19 start-page: 911 year: 2006 ident: 10.1016/j.neunet.2018.04.016_b27 article-title: Advanced visualization of self-organizing maps with vector fields publication-title: Neural Networks doi: 10.1016/j.neunet.2006.05.013 – volume: 19 start-page: 153 year: 2007 ident: 10.1016/j.neunet.2018.04.016_b5 article-title: Greedy layer-wise training of deep networks publication-title: Advances in Neural Information Processing Systems – volume: 61 start-page: 85 year: 2015 ident: 10.1016/j.neunet.2018.04.016_b28 article-title: Deep learning in neural networks: An overview publication-title: Neural Networks doi: 10.1016/j.neunet.2014.09.003 – volume: 15 start-page: 267 year: 1982 ident: 10.1016/j.neunet.2018.04.016_b24 article-title: Simplified neuron model as a principal component analyzer publication-title: Journal of Mathematical Biology doi: 10.1007/BF00275687 – volume: 24 start-page: 3313 year: 2004 ident: 10.1016/j.neunet.2018.04.016_b14 article-title: Representation of angles embedded within contour stimuli in area V2 of macaque monkeys publication-title: The Journal of Neuroscience doi: 10.1523/JNEUROSCI.4364-03.2004 – volume: 31 start-page: 264 year: 1999 ident: 10.1016/j.neunet.2018.04.016_b16 article-title: Data clustering: a review publication-title: ACM Computing Surveys (CSUR) doi: 10.1145/331499.331504 – volume: 19 start-page: 442 year: 2008 ident: 10.1016/j.neunet.2018.04.016_b7 article-title: Automatic cluster detection in Kohonen’s SOM publication-title: IEEE Transactions on Neural Networks doi: 10.1109/TNN.2007.909556 – volume: 3 start-page: 583 year: 2002 ident: 10.1016/j.neunet.2018.04.016_b30 article-title: Cluster ensembles—a knowledge reuse framework for combining multiple partitions publication-title: Journal of Machine Learning Research (JMLR) – start-page: 11 year: 2014 ident: 10.1016/j.neunet.2018.04.016_b19 – volume: 38 start-page: 2429 year: 1998 ident: 10.1016/j.neunet.2018.04.016_b22 article-title: The role of the primary visual cortex in higher level vision publication-title: Vision Research doi: 10.1016/S0042-6989(97)00464-1 – ident: 10.1016/j.neunet.2018.04.016_b23 – volume: 57 start-page: 3 year: 2004 ident: 10.1016/j.neunet.2018.04.016_b10 article-title: A general framework for unsupervised processing of structured data publication-title: Neurocomputing doi: 10.1016/j.neucom.2004.01.008 – volume: 2 start-page: 1 year: 2009 ident: 10.1016/j.neunet.2018.04.016_b4 article-title: Learning deep architectures for AI publication-title: Foundation and Trends® in Machine Learning doi: 10.1561/2200000006 – volume: 2 start-page: 17 year: 1991 ident: 10.1016/j.neunet.2018.04.016_b3 article-title: Unsupervised learning procedures for neural networks publication-title: International Journal of Neural Systems doi: 10.1142/S0129065791000030 – volume: 16 start-page: 550 year: 1994 ident: 10.1016/j.neunet.2018.04.016_b13 article-title: A database for handwritten text recognition research publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/34.291440 – volume: 31 start-page: 651 year: 2010 ident: 10.1016/j.neunet.2018.04.016_b15 article-title: Data clustering: 50 years beyond K-means publication-title: Pattern Recognition Letters doi: 10.1016/j.patrec.2009.09.011 – volume: 20 start-page: 549 year: 2009 ident: 10.1016/j.neunet.2018.04.016_b31 article-title: Exploiting data topology in visualization and clustering of self-organizing maps publication-title: IEEE Transactions on Neural Networks doi: 10.1109/TNN.2008.2005409 – ident: 10.1016/j.neunet.2018.04.016_b33 – volume: 18 start-page: 1527 year: 2006 ident: 10.1016/j.neunet.2018.04.016_b12 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Computation doi: 10.1162/neco.2006.18.7.1527 – volume: 17 start-page: 305 year: 2006 ident: 10.1016/j.neunet.2018.04.016_b6 article-title: The parameterless self-organizing map algorithm publication-title: IEEE Transactions on Neural Networks doi: 10.1109/TNN.2006.871720 – start-page: 1027 year: 2007 ident: 10.1016/j.neunet.2018.04.016_b1 article-title: k-means++: The advantages of careful seeding – start-page: 873 year: 2008 ident: 10.1016/j.neunet.2018.04.016_b20 article-title: Sparse deep belief net model for visual area V2 publication-title: Advances in Neural Information Processing Systems – volume: 33 start-page: 271 year: 2003 ident: 10.1016/j.neunet.2018.04.016_b29 article-title: TASOM: a new time adaptive self-organizing map publication-title: IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) doi: 10.1109/TSMCB.2003.810442
SSID	ssj0006843
Score	2.4401407
Snippet	In this report, we address the question of combining nonlinearities of neurons into networks for modeling increasingly varying and progressively more complex...
SourceID	proquest pubmed crossref elsevier
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	112
SubjectTerms	Clustering Denoising autoencoder Self-organizing map Unsupervised learning Visualization
Title	Denoising Autoencoder Self-Organizing Map (DASOM)
URI	https://dx.doi.org/10.1016/j.neunet.2018.04.016 https://www.ncbi.nlm.nih.gov/pubmed/29803188 https://www.proquest.com/docview/2045269554
Volume	105
WOSCitedRecordID	wos000441874700010&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: ScienceDirect database customDbUrl: eissn: 1879-2782 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006843 issn: 0893-6080 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3JbtswECWapIdeui_uEqhAUbQHBhKthTwajYO2cJwAcQDfCIkiAbkB5dpWkM_vcFOCJkHSQy-CQIq2zBkPZ8iZ9xD6xJSCQIIKXMua4FTVFWa5qnA9ZDkbSnCgKwviOimmUzqfs2PP1b62dAKF1vTigi3_q6ihDYRtSmf_Qdz9h0ID3IPQ4Qpih-u9BL8vddvYHYBRt2kNTqWBiziRZwr7wkvTd1gujXO5Pzo5Ogy7AYuA5GShOLRLEL-sD5Erz4_tAQn6nmNYcHXzC4LktrMm3fAg9b3Tsqnb1tUAnTfan0P5jYaE9plUwTbSgmFSOK6gPXlDWzCocXbFJCYuTfqaqXa7Bos9LTv4QSbJjlrQ2eQGZOzpET84nUz4bDyffV7-xoY0zByuewaVLbRDioyBUdsZ_RjPf_ZLcU5dhUV4y1A7aRP8rn_xbb7JbbGH9UFmT9FjHzxEIyf0Z-iB1M_Rk0DMEXk7_QIlvQ5EV3Qg-ksHItCB6IvVgK8v0enBePbtO_bcGFiAy7HBIk9VnguSKlJBxJoJAvazonEqSCJLmcWqYnUqichyWpGsFNChaKoyJlVcqXj4Cm3rVss3KEpgnUlzYZF-UmVq_ytaS1nlpT3TLQdoGGaFCw8cb_hLznjIEFxwN5fczCWPUw6NA4T7UUsHnHLH80WYcO6dP-fUcVCYO0Z-DPLhYBvNgVepZdutuaFaIDkDj3mAXjvB9e9CGDXrGX17j9Hv0KPLP8R7tL1ZdfIDeijON816tYu2ijnd9ar3BxDnjFA
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=Denoising+Autoencoder+Self-Organizing+Map+%28DASOM%29&rft.jtitle=Neural+networks&rft.au=Ferles%2C+Christos&rft.au=Papanikolaou%2C+Yannis&rft.au=Naidoo%2C+Kevin+J&rft.date=2018-09-01&rft.issn=1879-2782&rft.eissn=1879-2782&rft.volume=105&rft.spage=112&rft_id=info:doi/10.1016%2Fj.neunet.2018.04.016&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0893-6080&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0893-6080&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0893-6080&client=summon