{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T07:30:49Z","timestamp":1769758249655,"version":"3.49.0"},"reference-count":71,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2021,11,14]],"date-time":"2021-11-14T00:00:00Z","timestamp":1636848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Greece and the European Union (European Social Fund-ESF)","award":["MIS 5050185"],"award-info":[{"award-number":["MIS 5050185"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>The self-organizing convolutional map (SOCOM) hybridizes convolutional neural networks, self-organizing maps, and gradient backpropagation optimization into a novel integrated unsupervised deep learning model. SOCOM structurally combines, architecturally stacks, and algorithmically fuses its deep\/unsupervised learning components. The higher-level representations produced by its underlying convolutional deep architecture are embedded in its topologically ordered neural map output. The ensuing unsupervised clustering and visualization operations reflect the model\u2019s degree of synergy between its building blocks and synopsize its range of applications. Clustering results are reported on the STL-10 benchmark dataset coupled with the devised neural map visualizations. The series of conducted experiments utilize a deep VGG-based SOCOM model.<\/jats:p>","DOI":"10.3390\/make3040044","type":"journal-article","created":{"date-parts":[[2021,11,14]],"date-time":"2021-11-14T20:52:28Z","timestamp":1636923148000},"page":"879-899","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Deep Self-Organizing Map of Convolutional Layers for Clustering and Visualizing Image Data"],"prefix":"10.3390","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3155-1780","authenticated-orcid":false,"given":"Christos","family":"Ferles","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronics Engineering, University of West Attica, GR-12241 Aegaleo, Attica, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yannis","family":"Papanikolaou","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, University of West Attica, GR-12241 Aegaleo, Attica, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stylianos P.","family":"Savaidis","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, University of West Attica, GR-12241 Aegaleo, Attica, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2485-234X","authenticated-orcid":false,"given":"Stelios A.","family":"Mitilineos","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, University of West Attica, GR-12241 Aegaleo, Attica, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"ref_2","unstructured":"Northcutt, C.G., Athalye, A., and Mueller, J. (2021). Pervasive label errors in test sets destabilize machine learning benchmarks. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1016\/j.ins.2018.12.007","article-title":"Spark-GHSOM: Growing hierarchical self-organizing map for large scale mixed attribute datasets","volume":"496","author":"Malondkar","year":"2019","journal-title":"Inf. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.1016\/j.neunet.2006.02.009","article-title":"Growing Hierarchical Tree SOM: An unsupervised neural network with dynamic topology","volume":"19","author":"Forti","year":"2006","journal-title":"Neural Netw."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.ins.2003.03.020","article-title":"Expanding self-organizing map for data visualization and cluster analysis","volume":"163","author":"Jin","year":"2004","journal-title":"Inf. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2131","DOI":"10.1093\/bioinformatics\/btg296","article-title":"An unsupervised hierarchical dynamic self-organizing approach to cancer class discovery and marker gene identification in microarray data","volume":"19","author":"Hsu","year":"2003","journal-title":"Bioinformatics"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/72.554195","article-title":"Face recognition: A convolutional neural-network approach","volume":"8","author":"Lawrence","year":"1997","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Liu, N., Wang, J., and Gong, Y. (2015, January 12\u201317). Deep self-organizing map for visual classification. Proceedings of the 2015 International Joint Conference on Neural Networks (IJCNN), Killarney, Ireland.","DOI":"10.1109\/IJCNN.2015.7280357"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Hankins, R., Peng, Y., and Yin, H. (2018, January 21\u201323). Towards complex features: Competitive receptive fields in unsupervised deep networks. Proceedings of the International Conference on Intelligent Data Engineering and Automated Learning, Madrid, Spain.","DOI":"10.1007\/978-3-030-03493-1_87"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"5837","DOI":"10.1109\/TII.2019.2906083","article-title":"Deep self-organizing maps for unsupervised image classification","volume":"15","author":"Wickramasinghe","year":"2019","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"107035","DOI":"10.1109\/ACCESS.2020.3000829","article-title":"Deep convolutional self-organizing map network for robust handwritten digit recognition","volume":"8","author":"Aly","year":"2020","journal-title":"IEEE Access"},{"key":"ref_12","unstructured":"Friedlander, D. (2018). Pattern Analysis with Layered Self-Organizing Maps. arXiv."},{"key":"ref_13","unstructured":"Pesteie, M., Abolmaesumi, P., and Rohling, R. (2018). Deep neural maps. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Stuhr, B., and Brauer, J. (2019, January 16\u201319). Csnns: Unsupervised, backpropagation-free convolutional neural networks for representation learning. Proceedings of the 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), Boca Raton, FL, USA.","DOI":"10.1109\/ICMLA.2019.00265"},{"key":"ref_15","unstructured":"Part, J.L., and Lemon, O. (2016, January 9\u201314). Incremental on-line learning of object classes using a combination of self-organizing incremental neural networks and deep convolutional neural networks. Proceedings of the Workshop on Bio-Inspired Social Robot Learning in Home Scenarios (IROS), Daejeon, Korea."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wang, M., Zhou, W., Tian, Q., Pu, J., and Li, H. (2017, January 23\u201327). Deep supervised quantization by self-organizing map. Proceedings of the 25th ACM international conference on Multimedia, Mountain View, CA, USA.","DOI":"10.1145\/3123266.3123415"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kohonen, T. (1995). Self-Organizing Maps, Springer.","DOI":"10.1007\/978-3-642-97610-0"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Heskes, T. (1999). Energy functions for self-organizing maps. Kohonen Maps, Elsevier.","DOI":"10.1016\/B978-044450270-4\/50024-3"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.neunet.2013.07.011","article-title":"Self-organizing hidden markov model map (SOHMMM)","volume":"48","author":"Ferles","year":"2013","journal-title":"Neural Netw."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.neunet.2018.04.016","article-title":"Denoising autoencoder self-organizing map (DASOM)","volume":"105","author":"Ferles","year":"2018","journal-title":"Neural Netw."},{"key":"ref_21","unstructured":"Ultsch, A. (2003, January 11\u201314). Maps for the visualization of high-dimensional data spaces. Proceedings of the Workshop on Self Organizing Maps, Hibikono, Japan."},{"key":"ref_22","unstructured":"Ultsch, A. (2005, January 5\u20138). Clustering with SOM: U^* C. Proceedings of the Workshop on Self-Organizing Maps, Paris, France."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ferles, C., Beaufort, W.-S., and Ferle, V. (2017). Self-Organizing Hidden Markov Model Map (SOHMMM): Biological sequence clustering and cluster visualization. Hidden Markov Models, Springer.","DOI":"10.1007\/978-1-4939-6753-7_6"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1109\/TNN.2008.2005409","article-title":"Exploiting data topology in visualization and clustering of self-organizing maps","volume":"20","author":"Tasdemir","year":"2009","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1109\/TNN.2007.909556","article-title":"Automatic cluster detection in Kohonen\u2019s SOM","volume":"19","author":"Brugger","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1016\/j.neunet.2006.05.013","article-title":"Advanced visualization of self-organizing maps with vector fields","volume":"19","author":"Dittenbach","year":"2006","journal-title":"Neural Netw."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1109\/72.977314","article-title":"ViSOM-a novel method for multivariate data projection and structure visualization","volume":"13","author":"Yin","year":"2002","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Pampalk, E., Rauber, A., and Merkl, D. (2002, January 28\u201330). Using smoothed data histograms for cluster visualization in self-organizing maps. Proceedings of the International Conference on Artificial Neural Networks, Madrid, Spain.","DOI":"10.1007\/3-540-46084-5_141"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"111","DOI":"10.3233\/IDA-1999-3203","article-title":"SOM-based data visualization methods","volume":"3","author":"Vesanto","year":"1999","journal-title":"Intell. Data Anal."},{"key":"ref_30","first-page":"1","article-title":"Visualizing higher-layer features of a deep network","volume":"1341","author":"Erhan","year":"2009","journal-title":"Univ. Montr."},{"key":"ref_31","unstructured":"Simonyan, K., Vedaldi, A., and Zisserman, A. (2013). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv."},{"key":"ref_32","unstructured":"Nguyen, A., Yosinski, J., and Clune, J. (2016). Multifaceted feature visualization: Uncovering the different types of features learned by each neuron in deep neural networks. arXiv."},{"key":"ref_33","unstructured":"Yosinski, J., Clune, J., Nguyen, A., Fuchs, T., and Lipson, H. (2015). Understanding neural networks through deep visualization. arXiv."},{"key":"ref_34","unstructured":"Mahendran, A., and Vedaldi, A. (2005, January 20\u201325). Understanding deep image representations by inverting them. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"e7","DOI":"10.23915\/distill.00007","article-title":"Feature visualization","volume":"2","author":"Olah","year":"2017","journal-title":"Distill"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"e10","DOI":"10.23915\/distill.00010","article-title":"The building blocks of interpretability","volume":"3","author":"Olah","year":"2018","journal-title":"Distill"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"e15","DOI":"10.23915\/distill.00015","article-title":"Activation atlas","volume":"4","author":"Carter","year":"2019","journal-title":"Distill"},{"key":"ref_38","unstructured":"Zeiler, M.D., and Fergus, R. Visualizing and understanding convolutional networks. Proceedings of the European Conference on Computer Vision, Z\u00fcrich, Switzerland."},{"key":"ref_39","unstructured":"Zintgraf, L.M., Cohen, T.S., and Welling, M. (2016). A new method to visualize deep neural networks. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Bach, S., Binder, A., Montavon, G., Klauschen, F., M\u00fcller, K.-R., and Samek, W. (2015). On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref_41","unstructured":"Nguyen, A., Yosinski, J., and Clune, J. (12, January 7\u201312). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA."},{"key":"ref_42","unstructured":"Goodfellow, I.J., Shlens, J., and Szegedy, C. (2014). Explaining and harnessing adversarial examples. arXiv."},{"key":"ref_43","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. (2013). Intriguing properties of neural networks. arXiv."},{"key":"ref_44","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_45","unstructured":"Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv."},{"key":"ref_46","unstructured":"Sutskever, I., Martens, J., Dahl, G., and Hinton, G. (2013, January 16\u201321). On the importance of initialization and momentum in deep learning. Proceedings of the International Conference on Machine Learning, Atlanta, GA, USA."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Braga, P.H., Medeiros, H.R., and Bassani, H.F. (2020, January 19\u201324). Deep Categorization with Semi-Supervised Self-Organizing Maps. Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.","DOI":"10.1109\/IJCNN48605.2020.9206695"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Ferles, C., Papanikolaou, Y., Savaidis, S.P., and Mitilineos, S.A. (2021, January 20\u201321). Deep learning self-organizing map of convolutional layers. Proceedings of the 2nd International Conference on Artificial Intelligence and Big Data (AIBD 2021), Vienna, Austria.","DOI":"10.5121\/csit.2021.110303"},{"key":"ref_49","unstructured":"Coates, A., Ng, A., and Lee, H. (2011, January 11\u201313). An analysis of single-layer networks in unsupervised feature learning. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA. JMLR Workshop and Conference Proceedings."},{"key":"ref_50","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_51","unstructured":"Yu, W., Yang, K., Bai, Y., Xiao, T., Yao, H., and Rui, Y. (2016, January 19\u201324). Visualizing and comparing AlexNet and VGG using deconvolutional layers. Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Nam, W.-J., Choi, J., and Lee, S.-W. (2020). Interpreting Deep Neural Networks with Relative Sectional Propagation by Analyzing Comparative Gradients and Hostile Activations. arXiv.","DOI":"10.1609\/aaai.v35i13.17380"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Sharif Razavian, A., Azizpour, H., Sullivan, J., and Carlsson, S. (2014, January 28). CNN features off-the-shelf: An astounding baseline for recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Columbus, OH, USA.","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref_54","unstructured":"Yosinski, J., Clune, J., Bengio, Y., and Lipson, H. (2014). How transferable are features in deep neural networks?. arXiv."},{"key":"ref_55","unstructured":"Glorot, X., and Bengio, Y. (2010, January 13\u201315). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy. JMLR Workshop and Conference Proceedings."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Smith, L.N. (2017, January 24\u201331). Cyclical learning rates for training neural networks. Proceedings of the 2017 IEEE winter conference on applications of computer vision (WACV), Santa Rosa, CA, USA.","DOI":"10.1109\/WACV.2017.58"},{"key":"ref_57","unstructured":"Pointer, I. (2019). Programming PyTorch for Deep Learning: Creating and Deploying Deep Learning Applications, O\u2019Reilly Media, Inc."},{"key":"ref_58","unstructured":"Hoffer, E., Hubara, I., and Ailon, N. (2016). Deep unsupervised learning through spatial contrasting. arXiv."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"19451","DOI":"10.1007\/s11042-020-08822-9","article-title":"A Convolutional Deep Self-Organizing Map Feature extraction for machine learning","volume":"79","author":"Sakkari","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"1734","DOI":"10.1109\/TPAMI.2015.2496141","article-title":"Discriminative unsupervised feature learning with exemplar convolutional neural networks","volume":"38","author":"Dosovitskiy","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_61","unstructured":"Dundar, A., Jin, J., and Culurciello, E. (2015). Convolutional clustering for unsupervised learning. arXiv."},{"key":"ref_62","unstructured":"Paine, T.L., Khorrami, P., Han, W., and Huang, T.S. (2014). An analysis of unsupervised pre-training in light of recent advances. arXiv."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1016\/j.patcog.2016.06.001","article-title":"Unsupervised feature learning with C-SVDDNet","volume":"60","author":"Wang","year":"2016","journal-title":"Pattern Recognit."},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Miclut, B. (2014, January 2\u20135). Committees of deep feedforward networks trained with few data. Proceedings of the German Conference on Pattern Recognition, M\u00fcnster, Germany.","DOI":"10.1007\/978-3-319-11752-2_62"},{"key":"ref_65","unstructured":"Dosovitskiy, A., Springenberg, J., and Brox, T. (2014). Unsupervised feature learning by augmenting single images. arXiv."},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"Bo, L., Ren, X., and Fox, D. (2013). Unsupervised feature learning for RGB-D based object recognition. Experimental Robotics, Springer.","DOI":"10.1007\/978-3-319-00065-7_27"},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Nakayama, H. (2013, January 9\u201313). Efficient Discriminative Convolution Using Fisher Weight Map. Proceedings of the BMVC, Bristol, UK.","DOI":"10.5244\/C.27.100"},{"key":"ref_68","doi-asserted-by":"crossref","unstructured":"Ji, X., Henriques, J.F., and Vedaldi, A. (2019, January 27\u201328). Invariant information clustering for unsupervised image classification and segmentation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea.","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref_69","doi-asserted-by":"crossref","unstructured":"Haeusser, P., Plapp, J., Golkov, V., Aljalbout, E., and Cremers, D. (2018, January 9\u201312). Associative deep clustering: Training a classification network with no labels. Proceedings of the German Conference on Pattern Recognition, Stuttgart, Germany.","DOI":"10.1007\/978-3-030-12939-2_2"},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"Chang, J., Wang, L., Meng, G., Xiang, S., and Pan, C. (2017, January 22\u201329). Deep adaptive image clustering. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.626"},{"key":"ref_71","unstructured":"Xie, J., Girshick, R., and Farhadi, A. (2016, January 19\u201324). Unsupervised deep embedding for clustering analysis. Proceedings of the International Conference on Machine Learning, New York, NY, USA."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/3\/4\/44\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:30:00Z","timestamp":1760167800000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/3\/4\/44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,14]]},"references-count":71,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["make3040044"],"URL":"https:\/\/doi.org\/10.3390\/make3040044","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,14]]}}}