3D Convolutional Neural Network based on memristor for video recognition
文献类型：期刊论文
| 作者 | Liu, Jiaqi2,3; Li, Zhenghao1,2; Tang, Yongliang2; Hu, Wei4; Wu, Jun1
|
| 刊名 | PATTERN RECOGNITION LETTERS
 |
| 出版日期 | 2020-02-01 |
| 卷号 | 130页码:116-124 |
| 关键词 | 3D Convolution Basic memristor array Behavior recognition Memristors Neuromorphic network |
| ISSN号 | 0167-8655 |
| DOI | 10.1016/j.patrec.2018.12.005 |
| 通讯作者 | Li, Zhenghao(lizhenghao@cqu.edu.cn) |
| 英文摘要 | Memristors have emerged as a potential tool to implement the training and operation of an integrated neural network, because of its current-voltage curve of the hysteresis loop and unique pulse regulation resistance method. However, most of the existing neural networks implemented on memristors are relatively basic architecture, and the processing functions are limited to the recognition of the simple signal and image models. In this paper, we propose a 3D Convolutional Neural Network based on memristor to recognize and classify the behaviors of human in the video with 6 main actions. As an extension of 2D Convolutional Neural Networks, 3D Convolutional Neural Networks have attracted attention for video information processing, since it introduces the time dimension innovatively on the basis of spatial dimensions to capture the contextual information between the different frames in the video. Accordingly, we use the 3D Convolution to construct our proposed neural network based on memristors. Besides, we use the basic 3 x 3 memristor arrays to construct the larger functional memristor arrays and form the 3D convolutional layers of our network by considering that the 3 x 3 basic memristor array has excellent flexibility and anti-jamming capability. With this strategy, we can make full use of the hardware structure to improve accuracy while reducing hardware noise. Finally, we implemented network obtain more than 70% accuracy on the Weizmann video dataset. This demonstration is an important step that memristors can implement the much larger and more complex neural networks for processing the more complex applications. (C) 2018 Elsevier B.V. All rights reserved. |
| 资助项目 | Key Research and Development Projects in Chongqing[cstc2017rgzn-zdyfX0025] ; Chongqing Postdoctoral Science Foundation[Xm2015014] ; Opening Fund of Key Laboratory of Inland Waterway Regulation Engineering (Chongqing Jiaotong University), Ministry of Communications[NHHD-201503] ; Key Research Projects in Guangxi, China[AA17129002] ; Visiting Scholar Foundation of Key Laboratory of Optoelectronic Technology & Systems (Chongqing University), Ministry of Education |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000512878600015 |
| 出版者 | ELSEVIER |
| 源URL | [http://119.78.100.138/handle/2HOD01W0/10410]  |
| 专题 | 中国科学院重庆绿色智能技术研究院 |
| 通讯作者 | Li, Zhenghao |
| 作者单位 | 1.Chongqing Jiaotong Univ, Key Lab Inland Waterway Regulat Engn, Minist Commun, Chongqing 400016, Peoples R China 2.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing 400714, Peoples R China 3.Nanjing Univ, Coll Engn & Appl Sci, Nanjing 210093, Jiangsu, Peoples R China 4.Chongqing Univ, Coll Optoelect Engn, Key Lab Optoelect Technol & Syst, Minist Educ, Chongqing 400044, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liu, Jiaqi,Li, Zhenghao,Tang, Yongliang,et al. 3D Convolutional Neural Network based on memristor for video recognition[J]. PATTERN RECOGNITION LETTERS,2020,130:116-124. |
| APA | Liu, Jiaqi,Li, Zhenghao,Tang, Yongliang,Hu, Wei,&Wu, Jun.(2020).3D Convolutional Neural Network based on memristor for video recognition.PATTERN RECOGNITION LETTERS,130,116-124. |
| MLA | Liu, Jiaqi,et al."3D Convolutional Neural Network based on memristor for video recognition".PATTERN RECOGNITION LETTERS 130(2020):116-124. |
入库方式： OAI收割
来源：重庆绿色智能技术研究院
浏览0
下载0
收藏0
其他版本
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。