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

Yulin Zhao,Donghui Wang,Peng Liu,Leiou Wang

doi:10.3390/a11100159

Abstract

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.

Highlights

Deep convolutional neural networks have achieved remarkable improvements in image and video processing [1,2,3]
The computational complexity of convolutional neural networks is an urgent problem for realin layer7, when the batch size is 1, we cannot partition the matrix to use the Strassen algorithm, time applications
The algorithm reduces the computational complexity of convolutional neural networks, the cost is an increased

Summary

Introduction

Deep convolutional neural networks have achieved remarkable improvements in image and video processing [1,2,3]. The computational complexity of these networks has increased significantly. Since the prediction process of the networks used in real-time applications requires very low latency, the heavy computational burden is a major problem with these systems. The success of convolutional neural networks in these applications is limited by their heavy computational burden. There have been a number of studies on accelerating the efficiency of convolutional neural networks. Denil et al [6] indicate that there are significant redundancies in the parameterizations of neural networks. Han et al [7] and Guo et al [8] use certain training strategies to compress these neural network models without significantly weakening their performance. Some researchers [9,10,11]

Objectives

Results

Conclusion