Abstract
Neural networks (NN) have achieved great successes in pattern recognition and machine learning. However, the success of a NN usually relies on the provision of a sufficiently large number of data samples as training data. When fed with a limited data set, a NN’s performance may be degraded significantly. In this paper, a novel NN structure is proposed called a memory network. It is inspired by the cognitive mechanism of human beings, which can learn effectively, even from limited data. Taking advantage of the memory from previous samples, the new model achieves a remarkable improvement in performance when trained using limited data. The memory network is demonstrated here using the multi-layer perceptron (MLP) as a base model. However, it would be straightforward to extend the idea to other neural networks, e.g., convolutional neural networks (CNN). In this paper, the memory network structure is detailed, the training algorithm is presented, and a series of experiments are conducted to validate the proposed framework. Experimental results show that the proposed model outperforms traditional MLP-based models as well as other competitive algorithms in response to two real benchmark data sets.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Ruck DW, Rogers SK, Kabrisky M, Oxley ME, Suter BW. The multilayer perceptron as an approximation to a bayes optimal discriminant function. IEEE Trans Neural Netw 1990;1(4):296–298.
Zhang S, Huang K. Learning from few samples with memory network. International Conference on Neural Information Processing. Springer; 2016. p. 606–614.
Gao F, Zhang Y, Wang J, Sun J, Yang E, Hussain A. Visual attention model based vehicle target detection in synthetic aperture radar images: a novel approach. Cogn Comput 2015;7(4):434–444.
Girshick R. Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision; 2015. p. 1440–1448.
Iandola FN, Han S, Moskewicz M, Ashraf K, Dally WJ, Keutzer K. 2016. Squeezenet: alexnet-level accuracy with 50x fewer parameters and 0.5 mb model size. arXiv:1602.07360.
Lawrence S, Giles CL, Tsoi AC, Back AD. Face recognition: a convolutional neural-network approach. IEEE Trans Neural Netw 1997;8(1):98–113.
Lyu C, Huang K, Liang H-N. A unified gradient regularization family for adversarial examples. 2015 IEEE International Conference on Data Mining (ICDM). IEEE; 2015. p. 301–309.
Oquab M, Bottou L, Laptev I, Sivic J. Learning and transferring mid-level image representations using convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2014. p. 1717–1724.
Sun Y, Liang D, Wang X, Tang X. 2015. Deepid3: face recognition with very deep neural networks. arXiv:1502.00873.
Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Cogn Model 1988;5(3):1.
Cambria E, Hussain A, Vol. 1. Sentic computing: a common-sense-based framework for concept-level sentiment analysis. Berlin: Springer; 2015.
Chu H, Huang K, Zhang R, Hussian A. Sdrnf: generating scalable and discriminative random nonlinear features from data. Big Data Anal 2016;1(1):10.
Malik Z, Hussain A, Wu J. 2015. Extracting online information from dual and multi-data streams (in press). Neural Computation and Applications.
Huang K, Yang H, King I, Lyu MR. Machine learning: modeling data locally and globally. Berlin: Springer; 2008.
Huang K, Yang H, King I, Lyu MR. Local learning vs. global learning: an introduction to maxi-min margin machine. Support Vector Machines: Theory and Applications. Springer; 2005. p. 113–131.
Yang H, Huang K, King I, Lyu MR. Maximum margin semi-supervised learning with irrelevant data. Neural Netw 2015;70:90–102.
Wang H, Yeung D-Y. 2016. Towards bayesian deep learning: a survey. arXiv:1604.01662.
Tao D, Li X, Wu X, Maybank SJ. Geometric mean for subspace selection. IEEE Trans Pattern Anal Mach Intell 2009;31(2):260–274.
Liu W, Zha ZJ, Wang Y, Lu K, Tao D. p-laplacian regularized sparse coding for human activity recognition. IEEE Trans Ind Electron 2016;63(8):5120–5129.
Gourier N, Hall D, Crowley J. Estimating face orientation from robust detection of salient facial features. International conference on pattern recognition (ICPR); 2004.
Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE 1998;86(11):2278–2324.
Zhang X-Y, Huang K, Liu C-L. Pattern field classification with style normalized transformation. International joint conference on artificial intelligence (IJCAI); 2011. p. 1621– 1626.
Jolliffe I. Principal component analysis. Oxford: Wiley Online Library; 2002.
Tenenbaum JB, Freeman WT. Separating style and content with bilinear models. Neural Comput 2000;12(6):1247–1283.
Sarkar P, Nagy G. Style consistent classification of isogenous patterns. IEEE Trans Pattern Anal Mach Intell Jan 2005;27(1):88–98.
Grother PJ. Nist special database 19 handprinted forms and characters database. Maryland: National Institute of Standards and Technology; 1995.
Acknowledgements
The paper was supported by National Science Foundation of China (NSFC 61473236), and Jiangsu University Natural Science Research Programme (14KJB520037).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with human participants performed by any of the authors.
Informed Consent
Informed consent was obtained from all individual participants included in the study.
Rights and permissions
About this article
Cite this article
Zhang, S., Huang, K., Zhang, R. et al. Learning from Few Samples with Memory Network. Cogn Comput 10, 15–22 (2018). https://doi.org/10.1007/s12559-017-9507-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12559-017-9507-z