###
DOI:
Journal of Software:1997.8(4):252-258

多层反馈神经网络的FP学习和综合算法
张铃,张钹
(安徽大学人工智能研究所,合肥,230039; 智能技术与系统国家重点实验室,北京,100084;清华大学计算机系,北京,100084;智能技术与系统国家重点实验室,北京,100084)
A FORWARD PROPAGATION LEARNING ALGORITHM OF MULTILAYERED NEURAL NETWORKS WITH FEEDBACK CONNECTIONS
ZHANG Ling,ZHANG Bo
()
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 2465   Download 3026
    Revised:April 16, 1996
> 中文摘要: 本文给出多层反馈神经网络的FP学习和综合算法,并讨论此类网络的性质,指出将它应用于聚类分析能给出不粒度的聚类,且具有收敛速度快(是样本个数的线性函数)、算法计算量少(是样本个数和输入、输出维数的双线性函数)、网络元件个数少、权系数简单(只取3个值)、网络容易硬件实现等优点.作为聚类器的神经网络的学习和综合问题已得到较圆满地解决.
Abstract:A forward propagation learning algorithm(FP)of multilayered neural networks with feedback connections is presented in this paper.And the properties of cluster networks are discussed.A cluster with different grain-sizes can be obtained by applying FP to cluster.Its convergent speed is just a linear function of sample size.Its computational complexity is a bilinear function of simple size and the dimension of imput vectors.The network constructed by the algorithm uses a comparatively fewer number of elements and its weight simply has one of three values,i.e.,一1,0,1.Thus,it can be easily implemented into electronic circuits.The authors also discuss the properties of the network and show it is an ideal pattern classifier.
文章编号:     中图分类号:    文献标志码:
基金项目:本文研究得到国家攀登计划基金和国家自然科学基金资助. 本文研究得到国家攀登计划基金和国家自然科学基金资助.
Foundation items:
Reference text:

张铃,张钹.多层反馈神经网络的FP学习和综合算法.软件学报,1997,8(4):252-258

ZHANG Ling,ZHANG Bo.A FORWARD PROPAGATION LEARNING ALGORITHM OF MULTILAYERED NEURAL NETWORKS WITH FEEDBACK CONNECTIONS.Journal of Software,1997,8(4):252-258