Abstract
In recent years, deep learning has made great progress in image classification and detection. Popular deep learning algorithms rely on deep networks and multiple rounds of back-propagations. In this paper, we propose two approaches to accelerate deep networks. One is expanding the width of every layer. We reference to the Extreme Learning Machine, setting big number of convolution kernels to extract features in parallel. It can obtain multiscale features and improve network efficiency. The other is freezing part of layers. It can reduce back-propagations and speed up the training procedure. From the above, it is a random convolution architecture that network is proposed for image classification. In our architecture, every combination of random convolutions extracts distinct features. Apparently, we need a lot of experiments to choose the best combination. However, centralized computing may limit the number of combinations. Therefore, a decentralized architecture is used to enable the use of multiple combinations.
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
References
Xing, H., Zhang, G., Shang, M.J.I.J.o.S.C.: Deep learning 10(03), 417–439 (2016)
Huang, G.-B., Zhu, Q.-Y., Siew, C.-K.: Extreme learning machine: theory and applications. Neurocomputing 70(1–3), 489–501 (2006)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Szegedy, C.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Zhang, M., Wen, Y., Chen, J., Yang, X., Gao, R., Zhao, H.: Pedestrian dead-reckoning indoor localization based on OS-ELM. IEEE Access 6, 6116–6129 (2018)
King, J.L.: Centralized versus decentralized computing: organizational considerations and management options. ACM Comput. Surv. (CSUR) 15(4), 319–349 (1983)
Nakamoto, S.: Bitcoin: a peer-to-peer electronic cash system, pp. 1–9 (2008)
Buterin, V.: A next-generation smart contract and decentralized application platform, pp. 1–36 (2014)
Hossain, S.A.: Blockchain computing: prospects and challenges for digital transformation. In: 2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), pp. 61–65. IEEE (2017)
Acknowledgments
This study is supported by National Natural Science Foundation of China (Nos. 61272315, 61602431, 61701468, 61572164, 61877015 and 61850410531), International Cooperation Project of Zhejiang Provincial Science and Technology Department (Nos. 2017C34003), the Project of Zhejiang Provincial Natural Science Foundation (LY19F020016), and the Project of Zhejiang Provincial Science and Technology Innovation Activities for College Students University (Nos. 2019R409030) and Student research project of China Jiliang university (2019X22030).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, Y., Lu, H., Ye, M., Yan, K., Gao, Z., Jin, Q. (2019). Random Convolutional Neural Network Based on Distributed Computing with Decentralized Architecture. In: Milošević, D., Tang, Y., Zu, Q. (eds) Human Centered Computing. HCC 2019. Lecture Notes in Computer Science(), vol 11956. Springer, Cham. https://doi.org/10.1007/978-3-030-37429-7_50
Download citation
DOI: https://doi.org/10.1007/978-3-030-37429-7_50
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37428-0
Online ISBN: 978-3-030-37429-7
eBook Packages: Computer ScienceComputer Science (R0)