Distributed Reduced Convolution Neural Networks
-
Published:2021-07-30
Issue:
Volume:
Page:26-29
-
ISSN:
-
Container-title:Mesopotamian Journal of Big Data
-
language:
-
Short-container-title:MJBD
Author:
Alajanbi Mohammad1ORCID, Malerba Donato2, Liu He3
Affiliation:
1. Faculty of Computing, University Malaysia Pahang, Gambang, Malaysia 2. Department of Computer Science, College of Computer Science, Italy 3. Global Energy Interconnection Research Institute, Beijing, China
Abstract
The fields of pattern recognition and machine learning frequently make use of something called a Convolution Neural Network, or CNN for short. The kernel extension of CNN, often known as KCNN, offers a performance that is superior to that of conventional CNN. When working with a large-size kernel matrix, the KCNN takes a lot of time and requires a lot of memory, despite the fact that it is capable of solving difficult nonlinear problems. The implementation of a reduced kernel approach has the potential to significantly lower the amount of computational burden and memory consumption. However, since the total quantity of training data continues to expand at an exponential rate, it becomes impossible for a single worker to store the kernel matrix in an efficient manner. This renders centralized data mining impossible to implement. A distributed reduced kernel approach for training CNN on decentralized data, which is referred to as DRCNN, is proposed in this study. In the DRCNN, we will arbitrarily distribute the data to the various nodes. The communication between nodes is static and does not depend on the amount of training data stored on each node; instead, it is determined by the architecture of the network. In contrast to the reduced kernel CNN that is already in use, the DRCNN is a completely distributed training technique that is based on the approach of alternating direction multiplier (ADMM). Experimentation with the large size data set reveals that the distributed technique can produce virtually the same outcomes as the centralized algorithm, and it even requires less time to a significant amount. It results in a significant decrease in the amount of time needed for computation.
Publisher
Mesopotamian Academic Press
Subject
Library and Information Sciences,Health Informatics,Education,Medicine (miscellaneous),General Medicine,General Medicine,General Psychology,Biomedical Engineering,General Medicine,Bioengineering,General Medicine,Education,General Medicine,Psychiatry and Mental health,Health Policy,General Medicine,General Medicine
Reference1 articles.
1. [1]K. O'Shea and R. Nash, "An introduction to convolutional neural networks," arXiv preprint arXiv:1511.08458, 2015.[2]S. Albawi, T. A. Mohammed, and S. Al-Zawi, "Understanding of a convolutional neural network," in 2017 international conference on engineering and technology (ICET), 2017, pp. 1-6: Ieee.[3]G. Bebis and M. Georgiopoulos, "Feed-forward neural networks," IEEE Potentials, vol. 13, no. 4, pp. 27-31, 1994.[4]R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, "Convolutional neural networks: an overview and application in radiology," Insights into imaging, vol. 9, no. 4, pp. 611-629, 2018.[5]J. Chen, K. Li, K. Bilal, K. Li, and S.Y. Philip, "A bi-layered parallel training architecture for large-scale convolutional neural networks," IEEE transactions on parallel and distributed systems, vol. 30, no. 5, pp. 965-976, 2018.[6]D.-X. Zhou, "Deep distributed convolutional neural networks: Universality," Analysis and applications, vol. 16, no. 06, pp. 895-919, 2018.[7]S. Q. Zhang, J. Lin, and Q. Zhang, "Adaptive distributed convolutional neural network inference at the network edge with ADCNN," in 49th International Conference on Parallel Processing-ICPP, 2020, pp. 1-11.
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|