Abstract
This paper proposes a novel activation function to promote robustness to the outliers of the training samples. Data samples in the decision boundaries are weighted more by adding the derivatives of the sigmoid function outputs to avoid drastic update of the network weights. Therefore, the network becomes more robust to outliers and noisy patterns. We also present appropriate backpropagation learning algorithm for the convolutional neural networks. We evaluate the performance improvement by the proposed method on a face recognition task, and proved that it outperformed the state of art face recognition methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
LeCun, Y., Kavukcuoglu, K., Farabet, C.: Convolutional networks and applications in vision. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE (2010)
LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series. In: The Handbook of Brain Theory and Neural Networks, vol. 3361, pp. 310 (1995)
Bouchain, D.: Character recognition using convolutional neural networks. In: Institute for Neural Information Processing, vol. 2007 (2006)
LeCun, Y., Huang, F.J., Bottou, L.: Learning methods for generic object recognition with invariance to pose and lighting. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2004. IEEE (2004)
Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: 2013 12th International Conference on Document Analysis and Recognition. IEEE Computer Society (2003)
Khalajzadeh, H., Mansouri, M., Teshnehlab, M.: Hierarchical structure based convolutional neural network for face recognition. Int. J. Comput. Intell. Appl. 12(03), (2013)
Mamalet, F., Garcia, C.: Simplifying convnets for fast learning. In: Villa, A.E., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds.) ICANN 2012, Part II. LNCS, vol. 7553, pp. 58–65. Springer, Heidelberg (2012)
Hebb, D.O: The Organization of Behavior. Wiley, New York (1949, 1968)
Soo-Young, L., Dong-Gyu, J.: Merging back-propagation and hebbian learning rules for robust classifications. Neural Netw. Official J. Int. Neural Netw. Soc. 9(7), 1213–1222 (1996)
Shih, F., Fu, C., Zhang, K.: Multi-view face identification and pose estimation using B-spline interpolation. Inf. Sci. 169(3), 189–204 (2005)
Rinky, B., Mondal, P., Manikantan, K., Ramachandran, S.: DWT based feature extraction using edge tracked scale normalization for enhanced face recognition. Procedia Technol. 6, 344–353 (2012)
Zuiderveld, K.: Contrast limited adaptive histogram equalization. In: Graphics Gems IV. Academic Press Professional, Inc. (1994)
Acknowledgements
The research was partly supported by ‘Basic Science Research Program’, through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and future Planning (2013R1A2A2A01068687) (50%) and by the Industrial Strategic Technology Development Program (10044009) funded by the Ministry of Trade, Industry and Energy (MOTIE, Korea) (50 %).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Jalali, A., Jang, G., Kang, JS., Lee, M. (2015). Convolutional Neural Networks Considering Robustness Improvement and Its Application to Face Recognition. In: Arik, S., Huang, T., Lai, W., Liu, Q. (eds) Neural Information Processing. ICONIP 2015. Lecture Notes in Computer Science(), vol 9492. Springer, Cham. https://doi.org/10.1007/978-3-319-26561-2_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-26561-2_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26560-5
Online ISBN: 978-3-319-26561-2
eBook Packages: Computer ScienceComputer Science (R0)