Circuit Design of On- Chip BP Learning Neural Networkwith Programmable Neuron Characteristics

作     者：卢纯 石秉学 陈卢 

作者机构：清华大学 北京 100084 

基　　金：Project Supported by National N atural Science Foundation of China!( U nder Grant No.696360 30 ) 

出 版 物：《Journal of Semiconductors》 (半导体学报（英文版）)

年 卷 期：2000年第21卷第12期

页      码：1164-1169页

摘      要：A circuit system of on\|chip BP(Back\|Propagation) learning neural network with programmable neurons has been designed,which comprises a feedforward network,a n error back\|propagation network and a weight updating *** has the merit s of simplicity,programmability,speediness,low power\|consumption and high densi ty.A novel neuron circuit with programmable parameters has been *** gene rates not only the sigmoidal function but also its *** simulations are done to a neuron circuit with level 47 transistor models as a standard 1 2 μm CMOS *** results show that both functions are matched with their res pective ideal functions very *** non\|linear partition problem is used to v erify the operation of the *** simulation result shows the superior perf ormance of this BP neural network with on\|chip learning.

主 题 词：人工神经网络 电路设计 专用集成电路 

学科分类：080903[080903] 12[管理学] 1201[管理学-管理科学与工程类] 0809[工学-计算机类] 081104[081104] 08[工学] 0835[0835] 0811[工学-水利类] 0812[工学-测绘类] 

核心收录：

D　O　I：10.3969/j.issn.1674-4926.2000.12.004

馆 藏 号：203170767...