A Quantitative Exploration of Collaborative Pruning and Approximation Computing Towards Energy Efficient Neural Networks

doi:10.1109/MDAT.2019.2943575

	A Quantitative Exploration of Collaborative Pruning and Approximation Computing Towards Energy Efficient Neural Networks
	He, Xin 1; Yan, Guihai 2; Lu, Wenyan 3; Zhang, Xuan 4; Liu, Ke 5
	2020-02-01
发表期刊	IEEE DESIGN & TEST
ISSN	2168-2356
卷号	37 期号:1 页码:36-45
摘要	Editor's note: This work has the goal of minimizing digital neural network computation energy consumption with little loss in accuracy. The authors describe a Dynamic Network Surgery based approach to network pruning, after which weights are incrementally selected for approximate multiplication. Considering which network components are necessary and determining the needed level of accuracy for them enables greater energy savings than solving either problem independently. - Robert P. Dick, University of Michigan
关键词	Resilience Energy consumption Approximate computing Collaboration Computational modeling Artificial neural networks Optimization Neural network Energy efficient computing Network pruning Approximate computing
DOI	10.1109/MDAT.2019.2943575
收录类别	SCI
语种	英语
资助项目	National Science Foundation (NSF)[CNS-1739643] ; National Natural Science Foundation of China[61872336] ; National Natural Science Foundation of China[61572470] ; Youth Innovation Promotion Association, Chinese Academy of Science[Y404441000]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic
WOS记录号	WOS:000515556300005
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/14535
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	He, Xin
作者单位	1.Univ Michigan, Ann Arbor, MI 48109 USA 2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing, Peoples R China 4.Washington Univ, St Louis, MO 63110 USA 5.Washington Univ, Elect & Syst Engn Dept, St Louis, MO 63110 USA
推荐引用方式 GB/T 7714	He, Xin,Yan, Guihai,Lu, Wenyan,et al. A Quantitative Exploration of Collaborative Pruning and Approximation Computing Towards Energy Efficient Neural Networks[J]. IEEE DESIGN & TEST,2020,37(1):36-45.
APA	He, Xin,Yan, Guihai,Lu, Wenyan,Zhang, Xuan,&Liu, Ke.(2020).A Quantitative Exploration of Collaborative Pruning and Approximation Computing Towards Energy Efficient Neural Networks.IEEE DESIGN & TEST,37(1),36-45.
MLA	He, Xin,et al."A Quantitative Exploration of Collaborative Pruning and Approximation Computing Towards Energy Efficient Neural Networks".IEEE DESIGN & TEST 37.1(2020):36-45.