Advertisement

Matrix-Variate Restricted Boltzmann Machine Classification Model

  • Jinghua LiEmail author
  • Pengyu Tian
  • Dehui Kong
  • Lichun Wang
  • Shaofan Wang
  • Baocai Yin
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 295)

Abstract

Recently, Restricted Boltzmann Machine (RBM) has demonstrated excellent capacity of modelling vector variable. A variant of RBM, Matrix-variate Restricted Boltzmann Machine (MVRBM), extends the ability of RBM and is able to model matrix-variate data directly without vectorized process. However, MVRBM is still an unsupervised generative model, and is usually used to feature extraction or initialization of deep neural network. When MVRBM is used to classify, additional classifiers are necessary. This paper proposes a Matrix-variate Restricted Boltzmann Machine Classification Model (ClassMVRBM) to classify 2D data directly. In the novel ClassMVRBM, classification constraint is introduced to MVRBM. On one hand, the features extracted by MVRBM are more discriminative, on the other hand, the proposed model can be directly used to classify. Experiments on some publicly available databases demonstrate that the classification performance of ClassMVRBM has been largely improved, resulting in higher image classification accuracy than conventional unsupervised RBM, its variants and Restricted Boltzmann Machine Classification Model (ClassRBM).

Keywords

ClassMVRBM MVRBM RBM 

Notes

Acknowledgments

This research is supported by NSFC (No.61772049, 61602486), BJNSF (No.4162009), Beijing Educational Committee (No. KM201710005022) and Beijing Key Laboratory of Computational Intelligence and Intelligent System.

References

  1. 1.
    Wang, H., Wang, J.: 2DPCA with L1-norm for simultaneously robust and sparse modelling. Neural Netw. 46(10), 190–198 (2013)CrossRefGoogle Scholar
  2. 2.
    Ju, F., Sun, Y., Gao, J., Hu, Y., Yin, B.: Image outlier detection and feature extraction via L1-norm-based 2D probabilistic PCA. IEEE Trans. Image Process. 24(12), 4834–4846 (2015)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Li, M., Yuan, B.: 2D-LDA: a statistical linear discriminant analysis for image matrix. Pattern Recogn. Lett. 26(5), 527–532 (2005)CrossRefGoogle Scholar
  4. 4.
    Wang, J., Wang, W., Wang, R., Gao, W.: Image classification using RBM to encode local descriptors with group sparse learning. In: Proceedings of International Conference on Image Processing, pp. 912–916. IEEE, Canada (2015)Google Scholar
  5. 5.
    Dahl, G.E., Dong, Y., Li, D., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30–42 (2011)CrossRefGoogle Scholar
  6. 6.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning, Israel, pp. 807–814 (2010)Google Scholar
  7. 7.
    Cho, K., Ilin, A., Raiko, T.: Improved learning of Gaussian-Bernoulli restricted Boltzmann machines. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds.) ICANN 2011. LNCS, vol. 6791, pp. 10–17. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-21735-7_2CrossRefGoogle Scholar
  8. 8.
    Nguyen, T., Tran, T., Phung, D., Venkatesh, S.: Tensor-variate restricted Boltzmann machines. In: Proceedings of the Twenty-Ninth National Conference on Artificial Intelligence, pp. 2887–2893. AAAI, USA (2015)Google Scholar
  9. 9.
    Larochelle, H., Mandel, M., Pascanu, R., et al.: Learning algorithms for the classification restricted Boltzmann machine. J. Mach. Learn. Res. 13(1), 643–669 (2012)MathSciNetzbMATHGoogle Scholar
  10. 10.
    Peng, X., Gao, X., Li, X.: An infinite classification RBM model for radar HRRP recognition. In: International Joint Conference on Neural Networks, pp. 1442–1448, IEEE, USA (2017)Google Scholar
  11. 11.
    Qi, G., Sun, Y., Gao, J., Hu, Y., Li, J.: Matrix variate restricted Boltzmann machine. In: The proceeding of 2016 International Joint Conference on Neural Networks, pp. 389–395. IEEE, Canada (2016)Google Scholar
  12. 12.
    Liu, S., Sun, Y., Hu, Y., Gao, J., Ju, F., Yin, B.: Matrix variate RBM model with Gaussian distributions. In: The proceeding of 2017 International Joint Conference on Neural Networks, pp. 808–815. IEEE, USA (2017)Google Scholar
  13. 13.
    Gao, J., Guo, Y., Wang, Z.: Matrix neural networks. In: Cong, F., Leung, A., Wei, Q. (eds.) ISNN 2017. LNCS, vol. 10261, pp. 313–320. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-59072-1_37CrossRefGoogle Scholar
  14. 14.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  15. 15.
    Wang, Y., Mori, G.: Human action recognition by semilatent topic models. IEEE Trans. Pattern Anal. Mach. Intell. 31(10), 1762 (2009)CrossRefGoogle Scholar
  16. 16.
    Leibe, B., Schiele, B.: Analyzing appearance and contour based methods for object categorization. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–7. IEEE, USA (2003)Google Scholar
  17. 17.
    Tenenbaum, J., Silva, V., Langford, J.: A global geometric framework for nonlinear dimensionality reduction. Science 290(5500), 2319–2323 (2000)CrossRefGoogle Scholar
  18. 18.
    Nene, S., Nayar, S., Murase, H.: Columbia object image library (COIL-20). Technical report CUCS-005-96, USA (1996)Google Scholar
  19. 19.
    Qi, N., Shi, Y., Sun, X., Wang, J., Yin, B., Gao, J.: Multi-dimensional sparse models. IEEE Trans. Pattern Anal. Mach. Intell. 40(1), 163–178 (2018)CrossRefGoogle Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2019

Authors and Affiliations

  • Jinghua Li
    • 1
    Email author
  • Pengyu Tian
    • 1
  • Dehui Kong
    • 1
  • Lichun Wang
    • 1
  • Shaofan Wang
    • 1
  • Baocai Yin
    • 2
  1. 1.Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information TechnologyBeijing University of TechnologyBeijingChina
  2. 2.College of Computer Science and Technology, Faculty of Electronic Information and Electrical EngineeringDalian University of TechnologyDalianChina

Personalised recommendations