Over the last few years, Deep learning has begun to play an important role in analytics solutions of big data. Deep learning is one of the most active research fields in machine learning community. It has gained unprecedented achievements in fields such as computer vision, natural language processing and speech recognition. The ability of deep learning to extract high-level complex abstractions and data examples, especially unsupervised data from large volume data, makes it attractive a valuable tool for big data analytics. In this paper, we review the deep learning architectures which can be used for big data processing. Next, we focus on the analysis and discussions about the challenges and possible solutions of deep learning for big data analytics. Finally, have been outlined several open issues and research trends.
- Alguliyev, R. "Big Data" phenomenon: Challenges and Opportunities. - Problems of Information Technology, vol. 10, no. 2, 2014, pp. 3-16. (Alguliyev R., M. Hajirahimova)
- Alguliyev, R. Current scientific and theoretical problems of big data. - Problems of Information Society, vol. 10, no. 2, 2016, pp. 34-45. (Alguliyev R., M. Hajirahimova. A. Aliyeva)
- Chen, W. Big Data Deep Learning: Challenges and Perspectives. - Access IEEE, vol. 2, 2014, pp. 514-525, (Chen W., X. Lin)
- Najafabadi, M. Deep Learning applications and challenges in Big Data analytics. - Journal of Big Data, vol.2, no.1, 2015, pp.2- 21. (Najafabadi M., F. Villanustre, T. Khoshgoftaar, N. Seliya,)
- N. M. Elaraby, M. Elmogy, and Sh. Barakat, “Deep Learning: Effective Tool for Big Data Analytics.” International Journal of Computer Science Engineering, vol.5, no.5, pp. 254-262, 2016.
- Jan, B. Deep learning in big data Analytics: A comparative studym. - Computers and Electrical Engineering, vol.7, no. 24, 2017, pp. 1-13. (Jan B., H. Farman, M. Khan, M. Imran)
- Zhang, Q. A survey on deep learning for big data. - Information Fusion, vol. 42, 2018. pp. 146–157. (Zhang Q., L.Yang, Z. Chen)
- Liu G. A Stacked Autoencoder-Based Deep Neural Network for Achieving Gearbox Fault Diagnosis. - Mathematical Problems in Engineering, 2018, no. 5, pp. 1-10. 2018. (Liu G., H. Bao, B. Han)
- Hinton, G. A fast learning algorithm for deep belief nets. - Neural computation, vol. 18, no. 7, pp. 1527–1554, 2006. (Hinton G., S. Osindero, Y.-W. Teh)
- Wang, X. Learning from Uncertainty for Big Data: Future Analytical Challenges and Strategies. - IEEE Systems, Man., & Cybernetics Magazine, April 2016, pp.26-32 ( Wang, X., Y. He)
- Zheng, Y. Urban Computing, Cambridge, The MİT Press, 2018, 609 p. (Zheng, Y.)
- Ngiam, J. Multimodal deep learning. - 28th Inter. Conference on Machine Learning. ACM, June 28 - July 2, 2011, pp. 689–696.
- Srivastava, N. Multimodal learning with deep boltzmann machines. - Advances in Neural Information Processing Systems, MIT, 2012, vol. 25, pp. 2231–2239.
- Ouyang, W. Multi-source deep learning for human pose estimation. - IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2014, pp. 2337–2344.
- Zhang, Q. Deep computation model for unsupervised feature learning on big data. - IEEE Transactions on Services Computing, vol. 9, 2016, pp. 161–171. (Zhang Q., L.Yang, Z. Chen,)
- Chen, M. Marginalized denoising autoencoders for domain adaptation. - 29th International Conference in Machine Learning, Edingburgh, 2012, Scotland
- Zhang, J. Semi-supervised tensor learning for image classification. - Multimedia Syst., vol. 23, no. 1, 2017, pp. 63-73. (Zhang J., Y. Han, J. Jiang)
- Krizhevsky, A. Imagenet classification with deep convolutional neural networks. - Advances in Neural Information Processing Systems. Curran Associates, Inc. 2012, vol. 25. pp 1106–1114.
- Maggiori, Y. Convolutional neural networks for large-scale remote-sensing image classification. - IEEE Trans. Geosci. Remote Sens., vol.55, no.2, 2017, pp. 645–657. (Maggiori Y., G.Tarabalka, P. Charpiat)
- Jia, Z. Beyond data and model parallelism for deep neural networks. - arXiv:1807.05358v1 [cs.DC] 14 Jul 2018, pp.1-15. (Jia, Z., M. Zaharia, A. Aiken)
- Dean, J. Large scale distributed deep networks. - Proceedings of NIPS, 2012, pp. 1232–1240.
- Sun, P. Optimizing Network Performance for Distributed DNN Training on GPUClusters: ImageNet/AlexNet Training in 1.5 Minutes. - arXiv preprint arXiv:1902.06855, 2019. (Sun P., W. Feng, R. Han, S. Yan, Y. Wen)
- Coats, A. Deep learning with COTS HPC systems. - J. Mach. Learn. Res., vol.28, 2013, pp. 1337–1345. (A. Coats A., B. Huval, T. Wng, D. Wu, A. Wu)
- Novikov, A. Tensorizing neural netwroks. - Advances in Neural Information Processing Systems, MIT, 2015, pp. 442–450.
- Zhou, G. Online incremental feature learning with denoising autoencoders. - International Conference on Artificial Intelligence and Statistics. JMLR.org. 2012, pp 1453–1461.
- Calandra, R, Learning deep belief networks from non-stationary streams. - Artificial Neural Networks and Machine Learning– ICANN 2012. Springer, Berlin Heidelberg. 2012, pp. 379–386.
- Li,Y. Online Real-Time Analysis of Data Streams Based on an Incremental High-Order Deep Learning Model.- IEEE Access, vol, 6, 2018, pp. 77615 – 77623, ( Li Y., M. Zhang, W. Wang)
- Wang, R. Non-local auto-encoder with collaborative stabilization for image restoration. - IEEE Transactions on Image Processing, vol. 25, no. 5, 2016, pp. 2117–2129. (Wang, R., D. Tao)
- Mao, X. Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections - Advances in Neural Information Processing Systems, vol. 29, 2016, pp. 2802–2810.
- Zhang, K. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. - IEEE Transactions on Image Processing, vol. 26, no. 7, 2017, pp. 3142 – 31555, 2017. (Zhang K., W. Zuo, Y. Chen, D. Meng, L. Zhang)
- Valsesia, D. Image denoising with graph-Convolutional Neural Networks. - 2019 IEEE International Conference on Image Processing (ICIP), 22-25 Sept. 2019, pp. 2399 - 2403.