Abstract
Convolutional Neural Networks (CNNs) have demonstrated their superiority in image classification, and evolutionary computation (EC) methods have recently been surging to automatically design the architectures of CNNs to save the tedious work of manually designing CNNs. In this paper, a new hybrid differential evolution (DE) algorithm with a newly added crossover operator is proposed to evolve the architectures of CNNs of any lengths, which is named DECNN. There are three new ideas in the proposed DECNN method. Firstly, an existing effective encoding scheme is refined to cater for variable-length CNN architectures; Secondly, the new mutation and crossover operators are developed for variable-length DE to optimise the hyperparameters of CNNs; Finally, the new second crossover is introduced to evolve the depth of the CNN architectures. The proposed algorithm is tested on six widely-used benchmark datasets and the results are compared to 12 state-of-the-art methods, which shows the proposed method is vigorously competitive to the state-of-the-art algorithms. Furthermore, the proposed method is also compared with a method using particle swarm optimisation with a similar encoding strategy named IPPSO, and the proposed DECNN outperforms IPPSO in terms of the accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Before the conversion, 1 is subtracted from the decimal number because the binary string starts from 0, while the decimal value of the attributes of CNN layers begins with 1.
- 2.
References
Abdel-Hamid, O., Deng, L., Yu, D.: Exploring convolutional neural network structures and optimization techniques for speech recognition. In: Interspeech 2013. ISCA, August 2013. https://www.microsoft.com/en-us/research/publication/exploring-convolutional-neural-network-structures-and-optimization-techniques-for-speech-recognition/
Bruna, J., Mallat, S.: Invariant scattering convolution networks. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1872–1886 (2013). https://doi.org/10.1109/tpami.2012.230
Chan, T.H., Jia, K., Gao, S., Lu, J., Zeng, Z., Ma, Y.: PCANet: a simple deep learning baseline for image classification? IEEE Trans. Image Process. 24(12), 5017–5032 (2015). https://doi.org/10.1109/tip.2015.2475625
Gamperle, R., Muller, S.D., Koumoutsakos, A.: A parameter study for differential evolution. In: NNA-FSFS-EC 2002, vol. 10, pp. 293–298 (2002)
Sohn, K., Zhou, G., Lee, C., Lee, H.: Learning and selecting features jointly with point-wise gated boltzmann machines, June 2013. https://dl.acm.org/citation.cfm?id=3042918
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2014)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017). https://doi.org/10.1145/3065386
Larochelle, H., Erhan, D., Courville, A., Bergstra, J., Bengio, Y.: An empirical evaluation of deep architectures on problems with many factors of variation. In: Proceedings of the 24th International Conference on Machine Learning - ICML 2007 (2007). https://doi.org/10.1145/1273496.1273556
LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989). https://doi.org/10.1162/neco.1989.1.4.541
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceed. IEEE 86(11), 2278–2324 (1998). https://doi.org/10.1109/5.726791
Miller, J., Turner, A.: Cartesian genetic programming. In: Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation, GECCO Companion 2015, pp. 179–198. ACM, New York (2015). https://doi.org/10.1145/2739482.2756571
Price, K.V., Storn, R.M., Lampinen, J.A.: Differential Evolution: A Practical Approach to Global Optimization, pp. 37–42. Springer, Heidelberg (2005). Chapter 2
Rifai, S., Vincent, P., Muller, X., Glorot, X., Bengio, Y.: Contractive auto-encoders: explicit invariance during feature extraction, June 2011. https://dl.acm.org/citation.cfm?id=3104587
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition, April 2015. https://arxiv.org/abs/1409.1556
Sohn, K., Lee, H.: Learning invariant representations with local transformations, June 2012. https://arxiv.org/abs/1206.6418
Storn, R., Price, K.: Differential evolution a simple and efficient heuristic for global optimization over continuous spaces (1997). https://doi.org/10.1023/A:1008202821328
Suganuma, M., Shirakawa, S., Nagao, T.: A genetic programming approach to designing convolutional neural network architectures. CoRR abs/1704.00764 (2017). http://arxiv.org/abs/1704.00764
Sun, Y., Yen, G.G., Yi, Z.: Evolving unsupervised deep neural networks for learning meaningful representations. IEEE Trans. Evol. Comput. (2018). https://doi.org/10.1109/TEVC.2018.2808689
Szegedy, C., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9, June 2015
Wang, B., Sun, Y., Xue, B., Zhang, M.: Evolving deep convolutional neural networks by variable-length particle swarm optimization for image classification. In: IEEE Congress on Evolutionary Computation (July 2018, to appear). https://arxiv.org/abs/1803.06492
Xie, L., Yuille, A.: Genetic CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1388–1397, October 2017. https://doi.org/10.1109/ICCV.2017.154
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, B., Sun, Y., Xue, B., Zhang, M. (2018). A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification. In: Mitrovic, T., Xue, B., Li, X. (eds) AI 2018: Advances in Artificial Intelligence. AI 2018. Lecture Notes in Computer Science(), vol 11320. Springer, Cham. https://doi.org/10.1007/978-3-030-03991-2_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-03991-2_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03990-5
Online ISBN: 978-3-030-03991-2
eBook Packages: Computer ScienceComputer Science (R0)