Sensing and Imaging

, 20:6 | Cite as

K-Means Clustering Optimizing Deep Stacked Sparse Autoencoder

  • Yandong Bi
  • Peng Wang
  • Xuchao Guo
  • Zhijun Wang
  • Shuhan ChengEmail author
Original Paper


Because of the large structure and long training time, the development cycle of the common depth model is prolonged. How to speed up training is a problem deserving of study. In order to accelerate training, K-means clustering optimizing deep stacked sparse autoencoder (K-means sparse SAE) is presented in this paper. First, the input features are divided into K small subsets by K-means clustering, then each subset is input into corresponding autoencoder model for training, which only has fewer nodes in the hidden layer than traditional models. After training, each autoencoder’s trained weights and biases is merged to obtain the next layer’s input features by feedforward network. The above steps are repeated till the softmax layer, then fine-tuning is carried out. Using MNIST-Rotation datasets to train the network that has three hidden layers and each layer has 800 nodes, the improved model has higher classification accuracy and shorter training time when K = 10. With K increasing, the training time is reduced to almost the same as the fine-tuning time but the recognition ability is descended. Compared with the recently stacked denoising sparse autoencoder, the recognition accuracy is improved by 1%, not only the noise factor is not selected but also the training speed is significantly increased. The trained filters from the improved model is also used to train convolutional autoencoder, and it performs better than traditional models. We find that pre-training stage doesn’t need large samples simultaneously, and small samples parallel training reduces the probability of falling into the local minimum.


K-means clustering Sparse autoencoder Convolutional autoencoder Training method 



The work is supported by National Key Technology Research and Development Program of China No.2011BAD21B0601


  1. 1.
    Alain, G., & Bengio, Y. (2012). What regularized auto-encoders learn from the data generating distribution. Computer Science, 15(1), 3563–3593.MathSciNetzbMATHGoogle Scholar
  2. 2.
    Bell, A. J. (1996). Edges are the ’independent components’ of natural scenes. In: Advances in neural information processing system (pp. 831–837).Google Scholar
  3. 3.
    Bellinger, C., Drummond, C., & Japkowicz, N. (2017). Manifold-based synthetic oversampling with manifold conformance estimation. Machine Learning, 1, 1–33.zbMATHGoogle Scholar
  4. 4.
    Chandra, B., & Sharma, R. K. (2014). Adaptive noise schedule for denoising autoencoder. In: International conference on neural information processing (pp. 535–542).Google Scholar
  5. 5.
    Cheng, X., Liu, H., Xu, X., & Sun, F. (2016). Denoising deep extreme learning machine for sparse representation. Memetic Computing, 9(3), 1–14.Google Scholar
  6. 6.
    Das, R., & Walia, E. (2017). Partition selection with sparse autoencoders for content based image classification. Neural Computing & Applications, 4, 1–16.Google Scholar
  7. 7.
    Glorot, X., Bordes, A., & Bengio, Y. (2012). Deep sparse rectifier neural networks. Jmlr W & Cp, 15, 315–323.Google Scholar
  8. 8.
    Gupta, K., & Majumdar, A. (2017). Imposing class-wise feature similarity in stacked autoencoders by nuclear norm regularization. Neural Processing Letters, 2, 1–15.Google Scholar
  9. 9.
    Hinton, G. E., Osindero, S., & Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527–1554. Scholar
  10. 10.
    Hong, C., Yu, J., You, J., Yu, Z., & Chen, X. (2017). Three-dimensional image-based human pose recovery with hypergraph regularized autoencoders. Multimedia Tools & Applications, 2016(1), 1–19.Google Scholar
  11. 11.
    Imakura, A., Inoue, Y., Sakurai, T., & Futamura, Y. (2018). Parallel implementation of the nonlinear semi-NMF based alternating optimization method for deep neural networks. Neural Processing Letters, 47(3), 815–827.CrossRefGoogle Scholar
  12. 12.
    Le, Q. V. (2013). Building high-level features using large scale unsupervised learning. In: IEEE international conference on acoustics, speech and signal processing (pp. 8595–8598).Google Scholar
  13. 13.
    Lemme, A., Reinhart, R. F., & Steil, J. J. (2010). Efficient online learning of a non-negative sparse autoencoder. In: Esann 2010, European symposium on artificial neural networks, Bruges, Belgium, April 28–30, 2010 Proceedings.Google Scholar
  14. 14.
    Li, B., & Chen, C. (2017). First-order sensitivity analysis for hidden neuron selection in layer-wise training of networks. Neural Processing Letters, 7, 1–17.Google Scholar
  15. 15.
    Li, R., & Xu, H. (2017). Parallel stacked autoencoder and its application in process modeling. Journal of Electronic Measurement & Instrumentation, 31, 264–271.Google Scholar
  16. 16.
    Li, Z., Fan, Y., & Liu, W. (2015). The effect of whitening transformation on pooling operations in convolutional autoencoders. Eurasip Journal on Advances in Signal Processing, 2015(1), 37.CrossRefGoogle Scholar
  17. 17.
    Makhzani, A., & Frey, B. (2014). k-sparse autoencoders. In ICLR.
  18. 18.
    Meng, L., Ding, S., Zhang, N., & Zhang, J. (2018). Research of stacked denoising sparse autoencoder. Neural Computing & Applications, 30(7), 2083–2100.CrossRefGoogle Scholar
  19. 19.
    Meng, Q., Catchpoole, D., Skillicom, D., & Kennedy, P. J. (2017). Relational autoencoder for feature extraction. In: International joint conference on neural networks (pp. 364–371).Google Scholar
  20. 20.
    Rifai, S., Vincent, P., Muller, X., Glorot, X., & Bengio, Y. (2011). Contractive auto-encoders: Explicit invariance during feature extraction. In: ICML.Google Scholar
  21. 21.
    Schlkopf, B., Platt, J., & Hofmann, T. (2006). Efficient learning of sparse representations with an energy-based model. In: Advances in neural information processing systems (pp. 1137–1144).Google Scholar
  22. 22.
    Schlkopf, B., Platt, J., & Hofmann, T. (2006). Greedy layer-wise training of deep networks. In: International conference on neural information processing systems (pp. 153–160).Google Scholar
  23. 23.
    Shu, Z., Wu, X.J., & Hu, C. (2018). Structure preserving sparse coding for data representation. Neural Processing Letters, 48(3), 1705–1719.CrossRefGoogle Scholar
  24. 24.
    Singhal, V., & Majumdar, A. (2017). Majorization minimization technique for optimally solving deep dictionary learning. Neural Processing Letters, 3, 1–16.Google Scholar
  25. 25.
    Zeng, N., Zhang, H., Song, B., Liu, W., Li, Y., & Dobaie, A. M. (2017). Facial expression recognition via learning deep sparse autoencoders. Neurocomputing, 273, 643–649.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.College of Information Science And EngineeringShandong Agricultural UniversityTai’anChina

Personalised recommendations