神经网络剪枝技术研究综述  

Review of Neural Network Pruning Techniques

作　　者：姜晓勇 李忠义[1] 黄朗月 彭孟乐 徐书杨 JIANG Xiaoyong;LI Zhongyi;HUANG Langyue;PENG Mengle;XU Shuyang(School of Mechanical and Energy Engineering,Zhejiang University of Science and Technology,Hangzhou 310023,Zhejiang,China;Schoo of Mechanical Engineering,Zhejiang University,Hangzhou 310058,Zhejiang,China)

机构地区：[1]浙江科技学院机械与能源工程学院,浙江杭州310023 [2]浙江大学机械工程学院,浙江杭州310058

出　　处：《应用科学学报》2022年第5期838-849,共12页Journal of Applied Sciences

摘　　要：本文梳理了神经网络剪枝技术的起源与研究进展,将其分为对权重参数稀疏化的非结构化剪枝和粗粒度的结构化剪枝,分别介绍了两者近年来具有代表性的方法。由于剪枝减少了模型参数,压缩了模型大小,使得深度模型能应用于嵌入式设备,表现出剪枝在深度学习模型压缩领域中的重要性。针对现有剪枝技术,阐述了一些在实际应用和衡量标准上存在的问题,并对未来的研究发展方向进行了展望。This paper summaries the origin and research progress of neural network pruning technologies, divides them into two categories of unstructured pruning with sparse weight parameters and coarse-grained structured pruning, and introduces the representative methods of the two categories in recent years. Because pruning reduces model parameters and compresses the model size, depth models can be applied to embedded devices,showing the importance of pruning in the field of deep learning model compression. In view of the existing pruning technologies, this paper expounds the problems existing in practical applications and measurement standards, and prospects the research and development tendency in the future.

关 键 词：深度卷积神经网络 深度学习 模型压缩 剪枝 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]