Abstract—In recent years, deep neural network has continuously renewed its best performance in tasks such as computer vision and natural language processing, and has become the most concerned research direction. Although the performance of deep network model is remarkable, it is still difficult to deploy to the embedded or mobile devices with a limited hardware due to the large number of parameters, high storage and computing costs. It has been found by relevant studies that the depth model based on convolutional neural network has parameter redundancy, and there are parameters that are useless to the final result in the model, which provides theoretical support for the pruning of depth network model. Therefore, how to reduce the model size under the condition of ensuring the model accuracy has become a hot issue. This paper classifies and summarizes the achievements of domestic and foreign scholars in model pruning in recent years, selects several new pruning algorithm methods in different directions, analyzes their functionality through experiments and discusses the current problems of different models and the development direction of pruning model optimization in the future.

Index Terms—Artificial intelligence, deep learning, deep neural network, network pruning, optimization.

Qidi Song is with International Education College, Changchun University of Technology, Changchun, China. Xuanze Xia is with SHU-UTS SILC Business School, Shanghai University, Shanghai, China.

Cite:Qidi Song, Xuanze Xia, "A Survey on Pruning Algorithm Based on Optimized Depth Neural Network," International Journal of Computer and Communication Engineering vol. 11, no. 2, pp. 10-23, 2022.

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).