Next Article in Journal
Modeling and Evaluation of Power-Aware Software Rejuvenation in Cloud Systems
Previous Article in Journal
Incremental Learning for Classification of Unstructured Data Using Extreme Learning Machine
Article

A Faster Algorithm for Reducing the Computational Complexity of Convolutional Neural Networks

by 1,2,3,*, 1,2, 1,2 and 1,2,3
1
Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China
2
Key Laboratory of Information Technology for Autonomous Underwater Vehicles, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China
3
University of Chinese Academy of Sciences, Beijing 100049, China
*
Author to whom correspondence should be addressed.
Algorithms 2018, 11(10), 159; https://doi.org/10.3390/a11100159
Received: 10 September 2018 / Revised: 4 October 2018 / Accepted: 16 October 2018 / Published: 18 October 2018
Convolutional neural networks have achieved remarkable improvements in image and video recognition but incur a heavy computational burden. To reduce the computational complexity of a convolutional neural network, this paper proposes an algorithm based on the Winograd minimal filtering algorithm and Strassen algorithm. Theoretical assessments of the proposed algorithm show that it can dramatically reduce computational complexity. Furthermore, the Visual Geometry Group (VGG) network is employed to evaluate the algorithm in practice. The results show that the proposed algorithm can provide the optimal performance by combining the savings of these two algorithms. It saves 75% of the runtime compared with the conventional algorithm. View Full-Text
Keywords: convolutional neural network; Winograd; minimal filtering; Strassen; fast; complexity convolutional neural network; Winograd; minimal filtering; Strassen; fast; complexity
Show Figures

Figure 1

MDPI and ACS Style

Zhao, Y.; Wang, D.; Wang, L.; Liu, P. A Faster Algorithm for Reducing the Computational Complexity of Convolutional Neural Networks. Algorithms 2018, 11, 159. https://doi.org/10.3390/a11100159

AMA Style

Zhao Y, Wang D, Wang L, Liu P. A Faster Algorithm for Reducing the Computational Complexity of Convolutional Neural Networks. Algorithms. 2018; 11(10):159. https://doi.org/10.3390/a11100159

Chicago/Turabian Style

Zhao, Yulin, Donghui Wang, Leiou Wang, and Peng Liu. 2018. "A Faster Algorithm for Reducing the Computational Complexity of Convolutional Neural Networks" Algorithms 11, no. 10: 159. https://doi.org/10.3390/a11100159

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop