首页 | 官方网站   微博 | 高级检索  
     

STUDIES ON PROGRAMMING FEATURES AND METHODS OF FLOATING GATE MOSFET AS ANALOG MEMORY FOR SYNAPTIC WEIGHTS IN NEURAL NETWORKS
作者姓名:王阳  李志坚  石秉学
作者单位:Institute of Microelectronics Tsinghua University,Beijing 100084,Institute of Microelectronics,Tsinghua University,Beijing 100084,Institute of Microelectronics,Tsinghua University,Beijing 100084
基金项目:the Natural Science Foundation of China.
摘    要:The features of the floating gate devices as analog memory have been investigatedexperimentally.Programming properties of the devices,compatibility and endurance of program-ming,and programming methods are presented in this paper.The results illustrate that thedevice can be used to store the analog weights for the neural networks,and the method that thestored value is adjusted continuously to approach to a given analog values is a rather practicalmethod for storing weights of neural networks.


Studies on programming features and methods of floating gate mosfet as analog memory for synaptic weights in neural networks
Wang Yang,Li Zhijian,Shi Bingxue.STUDIES ON PROGRAMMING FEATURES AND METHODS OF FLOATING GATE MOSFET AS ANALOG MEMORY FOR SYNAPTIC WEIGHTS IN NEURAL NETWORKS[J].Journal of Electronics,1992,9(4):350-357.
Authors:Wang Yang  Li Zhijian  Shi Bingxue
Affiliation:(1) Institute of Microelectronics, Tsinghua University, 100084 Beijing
Abstract:The features of the floating gate devices as analog memory have been investigated experimentally.Programming properties of the devices,compatibility and endurance of program- ming,and programming methods are presented in this paper.The results illustrate that the device can be used to store the analog weights for the neural networks,and the method that the stored value is adjusted continuously to approach to a given analog values is a rather practical method for storing weights of neural networks.
Keywords:Neural network  Floating gate MOSFET  Analog memory  Synaptic weight  Programming
本文献已被 CNKI SpringerLink 等数据库收录!
点击此处可从《电子科学学刊(英文版)》浏览原始摘要信息
点击此处可从《电子科学学刊(英文版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号