Abstract
In this work an adaptive learning rate algorithm for Convolutional Neural Networks is presented. Harvesting already computed first order information of the gradient vectors of three consecutive iterations during the training phase, an adaptive learning rate is calculated. The learning rate is increasing proportionally to the similarity of the direction of the gradients in an attempt to accelerate the convergence and locate a good solution. The proposed algorithm is suitable for the time-consuming training of the Convolutional Neural Networks, alleviating the exhaustive and critical for the performance of trained network heuristic search for a suitable learning rate. The experimental results indicate that the proposed algorithm produces networks having good classification accuracy, regardless the initial learning rate value. Moreover, the training procedure is similar or better to the gradient descent algorithm with fixed heuristically chosen learning rate.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The code is available on https://github.com/Georgakopoulos-Sp/.
References
Almeidaa, L.B., Langloisa, T., Amaral, J.D., Plakhov, A.: Parameter adaptation in stochastic optimization. In: On-line Learning in Neural Networks, pp. 111–134. Cambridge University Press (1998)
Ba, J., Kingma, D.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)
Bottou, L.: On-line learning and stochastic approximations. In: On-line Learning in Neural Networks, pp. 9–42. Cambridge University Press (1998)
Delibasis, K.K., Georgakopoulos, S.V., Kottari, K., Plagianakos, V.P., Maglogiannis, I.: Geodesically-corrected zernike descriptors for pose recognition in omni-directional images. Integr. Comput.-Aided Eng. 23(2), 185–199 (2016)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR 2009 (2009)
Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121–2159 (2011)
Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)
Georgakopoulos, S.V., Iakovidis, D.K., Vasilakakis, M., Plagianakos, V.P., Koulaouzidis, A.: Weakly-supervised convolutional learning for detection of inflammatory gastrointestinal lesions. In: 2016 IEEE International Conference on Imaging Systems and Techniques (IST), pp. 510–514, October 2016
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates, Inc. (2012)
LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Magoulas, G., Plagianakos, V., Vrahatis, M.: Adaptive stepsize algorithms for on-line training of neural networks. Nonlinear Anal.: Theory Methods Appl. 47(5), 3425–3430 (2001)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Fnkranz, J., Joachims, T. (eds.) Proceedings of 27th International Conference on Machine Learning (ICML-2010), pp. 807–814. Omnipress (2010)
Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Is object localization for free? - weakly-supervised learning with convolutional neural networks. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 685–694, June 2015
Plagianakos, V.P., Magoulas, G.D., Vrahatis, M.N.: Global learning rate adaptation in on-line neural network training. In: Proceedings of 2nd International ICSC Symposium on Neural Computation (NC 2000), Berlin, Germany (2000)
Torralba, A., Fergus, R., Freeman, W.T.: 80 million tiny images: a large data set for nonparametric object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 30(11), 1958–1970 (2008). http://dx.doi.org/10.1109/TPAMI.2008.128
Wilcoxon, F.: Individual comparisons by ranking methods. Biom. Bull. 1(6), 80–83 (1945)
Zeiler, M.D.: ADADELTA: an adaptive learning rate method. CoRR abs/1212.5701 (2012)
Acknowledgments
We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X Pascal GPU used for this research. This work was partially supported by a Hellenic Artificial Intelligence Society (EETN) scholarship.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Georgakopoulos, S.V., Plagianakos, V.P. (2017). A Novel Adaptive Learning Rate Algorithm for Convolutional Neural Network Training. In: Boracchi, G., Iliadis, L., Jayne, C., Likas, A. (eds) Engineering Applications of Neural Networks. EANN 2017. Communications in Computer and Information Science, vol 744. Springer, Cham. https://doi.org/10.1007/978-3-319-65172-9_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-65172-9_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-65171-2
Online ISBN: 978-3-319-65172-9
eBook Packages: Computer ScienceComputer Science (R0)