[1]叶 涛,朱学峰.关于过程神经元网络的理论探讨[J].智能系统学报,2007,2(05):1-6.
 YE Tao,ZHU Xue-feng.Theoretical discussion on the process neural network the ory[J].CAAI Transactions on Intelligent Systems,2007,2(05):1-6.
点击复制

关于过程神经元网络的理论探讨(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第2卷
期数:
2007年05期
页码:
1-6
栏目:
学术论文—智能系统
出版日期:
2007-10-25

文章信息/Info

Title:
Theoretical discussion on the process neural network the ory
文章编号:
1673- 4785(2007)05-0001-06
作者:
叶  涛 朱学峰
华南理工大学自动化科学与工程学院,广东广州510641
Author(s):
YE Tao ZHU Xue-feng
College of Automation Science and Engineering, South China University of Technol ogy, Guangzhou 510641, China
关键词:
人工神经网络过程神经元函数正交基傅里叶级数特征扩展
Keywords:
artificial neural networks process neuron function orthogonal basis Fourier s eries feature expansion
分类号:
TP183
文献标志码:
A
摘要:
过程神经元网络是一种适合于处理过程式信号输入的网络,其基本单元是过程神经元——新近出现的神经元模型.过程神经元和传统神经元有着本质的区别,但二者之间也存在着紧密的联系,前者可用后者以任意精度无限逼近.文中给出2个定理及其详细证明,分别论述了过程神经元的2种传统神经元逼近模型:时域特征扩展模型和正交分解特征扩展模型. 基于第2个定理,给出了过程神经元网络相关的2个推论.最后,针对过程神经元网络面临的主要问题进行讨论,指出了一些具有前景的研究方向.文中得到的结果对过程神经元模型及其网络的研究具有一定的理论意义.
Abstract:
Process neural networks (PNNs) are networks suitable for processing signal input , whose elementary unit is the process neuron, a newly developed neuron model. T he process neuron is different from traditional neurons in nature, but there is an inherent relationship between them. The former can be infinitely approached b y the latter with arbitrary precision. Two theorems are presented and proved in this paper, giving two models for approaching corresponding process neurons:the timedomain feature expansion model and the orthogonal decomposition feature e xpansion model. And two corollaries are given based on the second theorem. Final ly, some problems with PNNs are discussed and several research topics suggested. The conclusions are significant to theoretical research on process neurons and PNNs.

参考文献/References:

[1】 HAGAN M T, DEMUTH H B, BEALE M. Neural network design [M]. Boston: PWS P ublishing Company, 1996.
[2]HORNIK K M,STINCHCOMBE M,WHITE H.Multilayer feedforward networks are un iversal approximators [J]. Neural Networks, 1989, 2(5): 359-366.
[3]何新贵,梁久祯. 过程神经元网络的若干理论问题[J]. 中国工程科学, 200 0, 2(12): 40-44.
 HE Xingui, LIANG Jiuzhen. Some theoretical issues on procedure neural networks [J]. Engineering Science, 2000, 2(12): 40-44.
[4]许少华,何新贵. 基于函数正交基展开的过程神经网络学习算法[J]. 计算机学报, 2004, 27(5): 645-650.
 XU Shaohua, HE Xingui. Learning algorithms of process neural networks based on o rthogonal function basis expansion [J]. Chinese Journal of Computers, 2004, 27 (5): 645-650.
[5]丁 刚,钟诗胜. 基于过程神经网络的热平衡温度预测研究[J]. 宇航学报, 2006, 27(3): 489-492.
 DING Gang, ZHONG Shisheng. Thermal equilibrium temperature prediction based on p rocess neural network [J]. Journal of Astronautics, 2006, 27(3): 489-492.
 [6]何新贵,许少华. 输入输出均为时变函数的过程神经网络及应用[J]. 软件学报, 2003, 14(4): 764-769.
 HE Xingui, XU Shaohua. Process neural network with timevaried input and output functions and its applications [J]. Journal of Software, 2003, 14(4): 764-769.
[7]柳重堪. 正交函数及其应用[M]. 北京: 国防工业出版社, 1982.
[8]赵录怀,高金峰,刘崇新,等. 信号与系统分析[M]. 北京: 高等教育出版社, 2003 .
[9]何新贵,许少华. 一类反馈过程神经元网络模型及其学习算法[J]. 自动化学报, 2004, 30(6): 801-806.
 HE Xingui, XU Shaohua. A feedback process neural network model and its learning algorithm [J]. Acta Automatica Sinica, 2004, 30(6): 801-806
[10]何新贵,许少华. 过程神经元网络及其在时变信息处理中的应用[J]. 智能系统学报, 2006, 1(1): 1-8.
 HE Xingui, XU Shaohua. Process neural networks and its applications in timevar y ing information processing [J]. CAAI Trans on Intelligent Systems, 2006, 1(1) : 1-8.
[11]许少华,何新贵,刘 坤,等. 关于连续过程神经元网络的一些理论问题[J ]. 电子学报, 2006, 34(10): 1838-1841.
XU Shaohua, HE Xingui, LIU Kun,et al. Some theoretical issues on continuous pro c ess neural networks [J]. Acta Electronica Sinica, 2006, 34(10): 1838-1841.
[12]胡广书. 现代信号处理教程[M]. 北京: 清华大学出版社, 2004.

相似文献/References:

[1]李 洋,钟诗胜,张 艳.连续小波过程神经网络及其仿真研究[J].智能系统学报,2007,2(06):77.
 LI Yang,ZHONG Shi-sheng,ZHANG Yan.Research and simulation of a continuous wavelet process neural network[J].CAAI Transactions on Intelligent Systems,2007,2(05):77.
[2]李洋,钟诗胜.多分辨小波过程神经网络及其应用研究[J].智能系统学报,2008,3(03):211.
 LI Yang,ZHONG Shi-sheng.Research on multi-resolution wavelet process neural networks and applications[J].CAAI Transactions on Intelligent Systems,2008,3(05):211.
[3]夏琳琳,张健沛,初妍.计算智能在移动机器人路径规划中的应用综述[J].智能系统学报,2011,6(02):160.
 XIA Linlin,ZHANG Jianpei,CHU Yan.An application survey on computational intelligence for path planning of mobile robots[J].CAAI Transactions on Intelligent Systems,2011,6(05):160.

备注/Memo

备注/Memo:
收稿日期:2007-01-08.
基金项目:国家自然科学基金资助项目(60274033, 6 0404013).
作者简介:
叶 涛,男,1976年生,博士研究生,主要研究方向为智能检测与智能控制、数据挖掘、机器学习、远程数据采集和监控.已发表论文7篇,其中EI检索4篇,ISTP检索1篇. E-mail: towerye@21cn.com. 
 朱学峰,男,1940年生,教授、博士生导师,中国自动化学会理事、广州市自动化学会理事长. 主要研究方向为过程先进控制策略、智能控制与智能检测、软测量技术等. 曾获教育部科技二等奖和广东省科技二等奖.发表论文近200篇. E-mail: xfzhu@scut.edu.cn.
更新日期/Last Update: 2009-05-07