###
Journal of Software:2020.31(9):2627-2653

轻量级神经网络架构综述
葛道辉,李洪升,张亮,刘如意,沈沛意,苗启广
(西安市大数据与视觉智能关键技术重点实验室(西安电子科技大学), 陕西 西安 710071;嵌入式技术与视觉处理研究中心(西安电子科技大学), 陕西 西安 710071;嵌入式技术与视觉处理研究中心(西安电子科技大学), 陕西 西安 710071;上海宽带技术及应用工程研究中心, 上海 200436;西安市大数据与视觉智能关键技术重点实验室(西安电子科技大学), 陕西 西安 710071;陕西省区块链与安全计算重点实验室(西安电子科技大学), 陕西 西安 710071)
Survey of Lightweight Neural Network
GE Dao-Hui,LI Hong-Sheng,ZHANG Liang,LIU Ru-Yi,SHEN Pei-Yi,MIAO Qi-Guang
(Xi'an Key Laboratory of Big Data and Intelligent Vision(Xidian University), Xi'an 710071, China;Embedded Technology and Vision Processing Research Center(Xidian University), Xi'an 710071, China;Embedded Technology and Vision Processing Research Center(Xidian University), Xi'an 710071, China;Shanghai Broadband Network Technology and Application Engineering Research Center, Shanghai 200436, China;Xi'an Key Laboratory of Big Data and Intelligent Vision(Xidian University), Xi'an 710071, China;Shaanxi Key Laboratory of Blockchain and Secure Computing(Xidian University), Xi'an 710071, China)
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 3620   Download 3146
Received:July 01, 2019    Revised:August 18, 2019
> 中文摘要: 深度神经网络已经被证明可以有效地解决图像、自然语言等不同领域的问题.同时,伴随着移动互联网技术的不断发展,便携式设备得到了迅速的普及,用户提出了越来越多的需求.因此,如何设计高效、高性能的轻量级神经网络,是解决问题的关键.详细阐述了3种构建轻量级神经网络的方法,分别是人工设计轻量级神经网络、神经网络模型压缩算法和基于神经网络架构搜索的自动化神经网络架构设计;同时,简要总结和分析了每种方法的特点,并重点介绍了典型的构建轻量级神经网络的算法;最后,总结现有的方法,并给出了未来发展的前景.
Abstract:Deep neural network has been proved to be effective in solving problems in different fields such as image, natural language, and so on. At the same time, with the continuous development of mobile Internet technology, portable devices have been rapidly popularized, and users have put forward more and more demands. Therefore, how to design an efficient and high performance lightweight neural network is the key to solve the problem. In this paper, three methods of constructing lightweight neural network are described in detail, which are artificial design of lightweight neural network, compression algorithm of neural network model, and automatic neural network architecture design based on searching of neural network architecture. The characteristics of each method are summarized and analyzed briefly, and the typical algorithms of constructing lightweight neural network are introduced emphatically. Finally, the existing methods are summarized and the prospects for future development are given.
文章编号:     中图分类号:TP183    文献标志码:
基金项目:国家重点研发计划(2018YFC0807500,2019YFB1311600);国家自然科学基金(61772396,61472302,61772392,61902296);西安市大数据与视觉智能关键技术重点实验室课题(201805053ZD4CG37);中央高校基本科研业务费专项资金(JBF180301);陕西省重点研发计划(2018ZDXM-GY-036) 国家重点研发计划(2018YFC0807500,2019YFB1311600);国家自然科学基金(61772396,61472302,61772392,61902296);西安市大数据与视觉智能关键技术重点实验室课题(201805053ZD4CG37);中央高校基本科研业务费专项资金(JBF180301);陕西省重点研发计划(2018ZDXM-GY-036)
Foundation items:National Key Research and Development Program of China (2018YFC0807500, 2019YFB1311600); National Natural Science Foundation of China (61772396, 61472302, 61772392, 61902296); Xi'an Key Laboratory of Big Data and Intelligent Vision (201805053ZD4CG37); Fundamental Research Funds for the Central Universities (JBF180301); Shaanxi Province Key Research and Development Program (2018ZDXM-GY-036)
Reference text:

葛道辉,李洪升,张亮,刘如意,沈沛意,苗启广.轻量级神经网络架构综述.软件学报,2020,31(9):2627-2653

GE Dao-Hui,LI Hong-Sheng,ZHANG Liang,LIU Ru-Yi,SHEN Pei-Yi,MIAO Qi-Guang.Survey of Lightweight Neural Network.Journal of Software,2020,31(9):2627-2653