Abstract
We propose in this work, a new approach for feature extraction based on deep Self-Organizing Map (SOM) network, named Generalized Unsupervised Deep SOM (G-UDSOM). This work presents an enhancement of the classic unsupervised deep SOM (UDSOM) algorithm in two ways. First, we modify the UDSOM Sub-sampling module in such a way that the image reconstruction phase is applied only in the feature construction phase. Second, the modified sub-sampling module learn feature of different sizes and resolutions through different map and patch sizes, which allows building parallel learning architecture. We add compact reconstruction constraint through the SOM learning based on convolutional auto-encoder. Thus. G-UDSOM allows extracting latent representation through its internal layer, by minimizing cost function. This function is composed of two terms: the cost SOM function mean square error of reconstruction. The second objective of our extended version is to achieve reduced computation time while improving accuracy and generalization capability. Different from the earlier proposed UDSOM architectures, G-UDSOM uses parallel SOMs without any reconstruction in the hidden layers. We evaluate our proposed approach on MNIST and STL-10 datasets. Experiment results show that our proposed approach outperforms deep SOMs models in terms of classification accuracy, training time and computational complexity. Our method is also can be generalized across different dataset without any pre-trained models.
Similar content being viewed by others
Data Availability
The datasets analyzed during the current study are publically available. MNIST: http://yann.lecun.com/exdb/mnist/. STL-10: https://cs.stanford.edu/~acoates/stl10/.AFHQ: https://www.kaggle.com/andrewmvd/animal-faces. USC-SIPI: https://sipi.usc.edu/database/.
References
F.B. Aissa, M. Sakkari, R. Ejbali, M. Zaied, Unsupervised features extraction using a multi-view self organizing map for image classification, in IEEE/ACS 14th International Conference on Computer Systems and Applications (2017), pp. 196–201. https://doi.org/10.1109/AICCSA.2017.104
S. Aly, S. Almotairi, Deep convolutional self-organizing map network for robust handwritten digit recognition. IEEE Access 8, 107035–107045 (2020). https://doi.org/10.1109/ACCESS.2020.3000829
D. Ao, Integration of Unsupervised Feature Learning and Neural Networks Applied to Image Recognition (South China University of Technology, Guangzhou, 2014), pp. 19–37
P. Arena, A. Basile, M. Bucolo, L. Fortuna, An object oriented segmentation on analog CNN chip. IEEE Trans. Circuits Syst. I Fundam. Theory Appl. 50(7), 837–846 (2003). https://doi.org/10.1109/TCSI.2003.813985
B.M. Barbalho, J.A.F. Costa, A.D.D. Neto, M.L.A. Netto, Hierarchical and dynamic SOM applied to image compression, in Proceedings of the International Joint Conference on Neural Networks (2003), pp. 753–758. https://doi.org/10.1109/IJCNN.2003.1223472
J.M. Barbalho, A. Duarte, D. Neto, J.A.F. Costa and M.L.A. Netto, Hierarchical SOM applied to image compression, in International Joint Conference on Neural Networks (2001), pp. 442–447. https://doi.org/10.1109/IJCNN.2001.939060
Y. Bengio, Learning deep architectures for AI. Found. Trends Mach. Learn. 2(1), 1–127 (2009). https://doi.org/10.1561/2200000006
Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle, Greedy layer-wise training of deep networks, in Proceedings of the 19th International Conference on Neural Information Processing Systems (2006), pp. 153–160
L. Bo, X. Ren, D. Fox, Unsupervised feature learning for RGB-D based object recognition, in Experimental Robotics. Springer Tracts in Advanced Robotics, vol. 88, ed. by J. Desai, G. Dudek, O. Khatib, V. Kumar (Springer, Heidelberg, 2013). https://doi.org/10.1007/978-3-319-00065-7_27
J. Bruna, S. Mallat, Invariant scattering convolution networks. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1872–1886 (2013). https://doi.org/10.1109/TPAMI.2012.230
T. Chan, K. Jia, S. Gao, J. Lu, Z. Zeng, Y. Ma, PCANet: a simple deep learning baseline for image classification? IEEE Trans. Image Process. 24(12), 5017–5032 (2015). https://doi.org/10.1109/TIP.2015.2475625
R. Collobert, J. Weston, A unified architecture for natural language processing: deep neural networks with multitask learning, in Proceedings of the 25th International Conference on Machine Learning (2008), pp. 160–167. https://doi.org/10.1145/1390156.1390177
A. Dosovitskiy, J.T. Springenberg, T. Brox, Unsupervised feature learning by augmenting single images, in International Conference on Learning Representations (2013)
H. Dozono, M. Tanaka, Application of self organizing map to preprocessing input vectors for convolutional neural network, in International Conference on Artificial Neural Networks ICANN, vol. 11728, pp. 96-100 (2019). https://doi.org/10.1007/978-3-030-30484-3_8
A. Dundar, J. Jin, E. Culurciello, Convolutional clustering for unsupervised learning. arXiv:1511.06241 (2015)
H. Elmannai, M. Hamdi, A. AlGarni, Deep learning models combining for breast cancer histopathology image classification. Int. J. Comput. Intell. Syst. 14(1), 1003–1013 (2021). https://doi.org/10.2991/ijcis.d.210301.002
H. Elmannai, M.S. Naceur, M.A. Loghmari, A. AlGarni, A new feature extraction approach based on non linear source separation. Int. J. Electr. Comput. Eng. 11(5), 4082–4094 (2021). https://doi.org/10.11591/ijece.v11i5.pp4082-4094
F. Forest, M. Lebbah, H. Azzag, J. Lacaille, Deep architectures for joint clustering and visualization with self-organizing maps, in Trends and Applications in Knowledge Discovery and Data Mining, Lecture Notes in Computer Science, vol. 11607 (2019)
S. Furao, O. Segawa, An incremental network for on-line unsupervised classification and topology learning. Neural Netw. 19(1), 90–106 (2006). https://doi.org/10.1016/j.neunet.2005.04.006
S. Furao, T. Ogura, O. Hasegawa, An enhanced self-organizing incremental neural network for online unsupervised learning. Neural Netw. 20(8), 893–903 (2007). https://doi.org/10.1016/j.neunet.2007.07.008
R. Gens, P. Domingos, Discriminative learning of sum-product networks, in Advances in Neural Information Processing Systems (2012), pp. 3239–3247
Y. Guo, Y. Liu, A. Oerlemans, S. Lao, S. Wu, M.S. Lew, Deep learning for visual understanding: a review. Neurocomputing 187, 27–48 (2016). https://doi.org/10.1016/j.neucom.2015.09.116
M. Hamdi, H. Bouhamed, A. AlGarni, H. Elmannai, S. Meshoul, Deep learning and uniform LBP histograms for position recognition of elderly people with privacy preservation. Int. J. Comput. Commun. Control (2021). https://doi.org/10.15837/ijccc.2021.5.42562
G.E. Hinton, S. Osindero, Y.W. Teh, A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006). https://doi.org/10.1162/neco.2006.18.7.1527
G.E. Hinton, R.R. Salakhutdinov, Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006). https://doi.org/10.1126/science.1127647
A.V. Joshi, Unsupervised learning in machine, in Learning and Artificial Intelligence. ed. by A.V. Joshi (Springer, Cham, 2020), pp. 133–140
T. Kohonen, E. Oja, O. Simula, A. Visa, J. Kangas, Engineering applications of the self-organizing map. Proc. IEEE 84(10), 1358–1384 (1996). https://doi.org/10.1109/5.537105
N. Liu, J. Wang, A. Gong, Deep self-organizing map for visual classification, in International Joint Conference on Neural Networks (2015), pp. 1–6. https://doi.org/10.1109/IJCNN.2015.7280357
B. Miclut, Committees of deep feedforward networks trained with few data, in German Conference on Pattern Recognition (2014), pp. 736–742
H. Nakayama, Efficient discriminative convolution using fisher weight map, in British Machine Vision Conference (2013), pp. 1–11
G. Qian, L. Zhang, A simple feedforward convolutional conceptor neural network for classification. Appl. Soft Comput. 70, 1034–1041 (2018). https://doi.org/10.1016/j.asoc.2017.08.016
M.A. Ranzato, M. Szummer, Semi-supervised learning of compact document representations with deep networks, in 25th International Conference on Machine Learning (2008), pp. 792–799. https://doi.org/10.1145/1390156.1390256
X. Ren, H. Guo, S. Li, S. Wang, J. Li, A novel image classification method with CNN-XGBoost model, in: C. Kraetzer, Y. Shi, J. Dittmann, H. Kim (eds.), Digital Forensics and Watermarking. Lecture Notes in Computer Science, 10431 (2014). https://doi.org/10.1007/978-3-319-64185-0_28
S. Rifai, P. Vincent, X. Muller, X. Glorot, Y. Bengio, Contractive auto-encoders: explicit invariance during feature extraction, in International Conference on International Conference on Machine Learning (2011), pp. 833–840
M. Sakkari, R. Ejbali, M. Zaied, Deep SOMs for automated feature extraction and classification from big data streaming, in Proceedings of the Ninth International Conference on Machine Vision. International Society for Optics and Photonics, vol. 10341 (2017). https://doi.org/10.1117/12.2269082
M. Sakkari, M. Zaied, A convolutional deep self-organizing map feature extraction for machine learning. Multimedia Tools Appl 79, 19451–19470 (2020). https://doi.org/10.1007/s11042-020-08822-9
F. Shen, O. Hasegawa, A fast nearest neighbor classifier based on self-organizing incremental neural network. Neural Netw. 21(10), 1537–1547 (2008). https://doi.org/10.1016/j.neunet.2008.07.001
F. Shen, O. Hasegawa, Self-organizing incremental neural network and its application, in Artificial Neural Networks. ICANN 2010. Lecture Notes in Computer Science, vol. 6354, ed. by K. Diamantaras, W. Duch, L. Iliadis (Springer, Berlin, 2010). https://doi.org/10.1007/978-3-642-15825-4_74
F. Sapuppo, M. Intaglietta, M. Bucolo, Bio-microfluidics real-time monitoring using CNN technology. IEEE Trans. Biomed. Circuits Syst. 2(2), 78–87 (2008). https://doi.org/10.1109/TBCAS.2008.925642
A. Voulodimos, N. Doulamis, A. Doulamis, E. Protopapadakis, Deep learning for computer vision: a brief review. Comput. Intell. Neurosci. 2018, 1–13 (2018). https://doi.org/10.1155/2018/7068349
S. Walczak, Artificial neural networks, in Advanced Methodologies and Technologies in Artificial Intelligence, Computer Simulation, and Human-Computer Interaction, pp. 40–53. IGI Global (2019). https://doi.org/10.4018/978-1-5225-7368-5
C.S. Wickramasinghe, K. Amarasinghe, M. Manic, Deep self-organizing maps for unsupervised image classification. IEEE Trans. Ind. Inf. 15(11), 5837–5845 (2019). https://doi.org/10.1109/TII.2019.2906083
J.J. Winston, G.F. Turker, U. Kose, D.J. Hemanth, Novel optimization based hybrid self-organizing map classifiers for iris image recognition. Int. J. Comput. Intell. Syst. 13(1), 1048–1058 (2020). https://doi.org/10.2991/ijcis.d.200721.001
H. Zihang, Mnist_transformation_test_dataset, IEEE Dataport. https://ieee-dataport.org/documents/mnisttransformationtestdataset (2018). Accessed June 2019. https://doi.org/10.21227/r1jn-zf11
Acknowledgements
This research project was funded by the Deanship of Scientific Research, Princess Nourah bint Abdulrahman University, through the Program of Research Project Funding After Publication, grant No. (41-PRF-A-P-13)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sakkari, M., Hamdi, M., Elmannai, H. et al. Feature Extraction-Based Deep Self-Organizing Map. Circuits Syst Signal Process 41, 2802–2824 (2022). https://doi.org/10.1007/s00034-021-01914-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-021-01914-3