CSpace  > 中国科学院计算技术研究所期刊论文  > 英文
A High-Speed Low-Cost VLSI System Capable of On-Chip Online Learning for Dynamic Vision Sensor Data Classification
He, Wei1; Huang, Jinguo1; Wang, Tengxiao1; Lin, Yingcheng1; He, Junxian1; Zhou, Xichuan1,2; Li, Ping1,2; Wang, Ying3; Wu, Nanjian4; Shi, Cong1,2
2020-09-01
发表期刊SENSORS
卷号20期号:17页码:18
摘要This paper proposes a high-speed low-cost VLSI system capable of on-chip online learning for classifying address-event representation (AER) streams from dynamic vision sensor (DVS) retina chips. The proposed system executes a lightweight statistic algorithm based on simple binary features extracted from AER streams and a Random Ferns classifier to classify these features. The proposed system's characteristics of multi-level pipelines and parallel processing circuits achieves a high throughput up to 1 spike event per clock cycle for AER data processing. Thanks to the nature of the lightweight algorithm, our hardware system is realized in a low-cost memory-centric paradigm. In addition, the system is capable of on-chip online learning to flexibly adapt to different in-situ application scenarios. The extra overheads for on-chip learning in terms of time and resource consumption are quite low, as the training procedure of the Random Ferns is quite simple, requiring few auxiliary learning circuits. An FPGA prototype of the proposed VLSI system was implemented with 9.5 similar to 96.7% memory consumption and <11% computational and logic resources on a Xilinx Zynq-7045 chip platform. It was running at a clock frequency of 100 MHz and achieved a peak processing throughput up to 100 Meps (Mega events per second), with an estimated power consumption of 690 mW leading to a high energy efficiency of 145 Meps/W or 145 event/mu J. We tested the prototype system on MNIST-DVS, Poker-DVS, and Posture-DVS datasets, and obtained classification accuracies of 77.9%, 99.4% and 99.3%, respectively. Compared to prior works, our VLSI system achieves higher processing speeds, higher computing efficiency, comparable accuracy, and lower resource costs.
关键词address-event representation (AER) Random Ferns object classification neuromorphic hardware online learning on-chip learning
DOI10.3390/s20174715
收录类别SCI
语种英语
资助项目Key Project of Chongqing Science and Technology Foundation[cstc2019jcyj-zdxmX0017] ; Chongqing Talents Plan for Yong Talents[CQYC201905015] ; Open Research Funding from the State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences[CARCH201908]
WOS研究方向Chemistry ; Engineering ; Instruments & Instrumentation
WOS类目Chemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS记录号WOS:000569758500001
出版者MDPI
引用统计
被引频次:5[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/2XEOYT63/15545
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Shi, Cong
作者单位1.Chongqing Univ, Sch Microelect & Commun Engn, Chongqing 400044, Peoples R China
2.Chongqing Univ, Minist Educ, Key Lab Dependable Serv Comp Cyber Phys Soc, Chongqing 400044, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100190, Peoples R China
4.Chinese Acad Sci, Inst Semicond, State Key Lab Superlattices & Microstruct, Beijing 100083, Peoples R China
推荐引用方式
GB/T 7714
He, Wei,Huang, Jinguo,Wang, Tengxiao,et al. A High-Speed Low-Cost VLSI System Capable of On-Chip Online Learning for Dynamic Vision Sensor Data Classification[J]. SENSORS,2020,20(17):18.
APA He, Wei.,Huang, Jinguo.,Wang, Tengxiao.,Lin, Yingcheng.,He, Junxian.,...&Shi, Cong.(2020).A High-Speed Low-Cost VLSI System Capable of On-Chip Online Learning for Dynamic Vision Sensor Data Classification.SENSORS,20(17),18.
MLA He, Wei,et al."A High-Speed Low-Cost VLSI System Capable of On-Chip Online Learning for Dynamic Vision Sensor Data Classification".SENSORS 20.17(2020):18.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[He, Wei]的文章
[Huang, Jinguo]的文章
[Wang, Tengxiao]的文章
百度学术
百度学术中相似的文章
[He, Wei]的文章
[Huang, Jinguo]的文章
[Wang, Tengxiao]的文章
必应学术
必应学术中相似的文章
[He, Wei]的文章
[Huang, Jinguo]的文章
[Wang, Tengxiao]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。