吉林大学学报(信息科学版) ›› 2019, Vol. 37 ›› Issue (2): 127-133.

• • 上一篇    下一篇

忆阻神经网络图像处理综述

高宏宇1a,1b,黄文丽1a,1b,董宏丽1a,1b,李佳慧1a,1b,吴宇墨2   

  1. 1. 东北石油大学a. 复杂系统与先进控制研究院; b. 黑龙江省网络化与智能控制重点实验室,黑龙江大庆163318;
    2. 东北师范大学数学与统计学院,长春130024
  • 收稿日期:2018-09-14 出版日期:2019-03-25 发布日期:2019-06-10
  • 作者简介:高宏宇( 1979— ) ,女,黑龙江大庆人,东北石油大学副教授,硕士生导师,主要从事智能控制与复杂网络系统滤波研究,(Tel) 86-13936997593( E-mail) 4501419@ qq. com; 董宏丽( 1977— ) ,女,黑龙江克山人,东北石油大学教授,博士生导师,主要从事智能控制和网络化控制研究,( Tel) 86-459-6503373( E-mail) shiningdhl@ vip. 126. com。
  • 基金资助:
    国家自然科学基金资助项目( 61873058) ; 中国博士后基金资助项目( 2017M621242 ) ; 黑龙江省自然基金资助项目
    (F2018005)

Review for Image Processing of Memristive Neural Networks

GAO Hongyu1a,1b,HUANG Wenli1a,1b,DONG Hongli1a,1b,LI Jiahui1a,1b,WU Yumo2   

  1. 1a. Institute of Complex Systems and Advanced Control; 1b. Heilongjiang Provincial Key Laboratory of
    Networking and Intelligent Control,Northeast Petroleum University,Daqing 163318,China;
    2. School of Mathematics and Statistics,Northeast Normal University,Changchun 130024,China
  • Received:2018-09-14 Online:2019-03-25 Published:2019-06-10

摘要: 忆阻神经网络能有效改善传统神经网络电路复杂、不易集成以及能耗大等不足。概述了忆阻器与忆阻神经网络,以及目前忆阻神经网络在图像处理方面的应用。基于忆阻特性,实现神经网络突触的动态可变,使忆阻神经网络比传统神经网络在图像处理领域具备更多优势且应用范围更广。同时,展望了忆阻神经网络未来发展前景。

关键词: 忆阻器, 忆阻神经网络, 图像处理

Abstract: Memristive neural networks can effectively improve the complexity of traditional neural network circuits,the difficulty of integration and high energy consumption. Membrane,memristive neural networks and the application of current memristive neural networks in image processing are summarized. Based on the memristive property,the dynamic variable of the neural network synapse is realized,which makes the memristive neural networks having more advantages and wider application range than the traditional neural networks in the field of image processing. The future development prospects of memristive neural networks are forecasted.

Key words: memristor, memristor neural network, image processing

中图分类号: 

  • TP83