| 多层反馈神经网络的FP学习和综合算法 |
| |
| 引用本文： | 张铃,张钹.多层反馈神经网络的FP学习和综合算法[J].软件学报,1997,8(4):252-258. |
| |
| 作者姓名： | 张铃 张钹 |
| |
| 作者单位： | 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 |
| |
| 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. |
| |
| 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.
|
| 关 键 词： | 多层反馈神经网络 学习算法 聚类 |
| 修稿时间： | 1996/4/16 0:00:00 |
A FORWARD PROPAGATION LEARNING ALGORITHM OF MULTILAYERED NEURAL NETWORKS WITH FEEDBACK CONNECTIONS |
| |
| ZHANG Ling and ZHANG Bo.A FORWARD PROPAGATION LEARNING ALGORITHM OF MULTILAYERED NEURAL NETWORKS WITH FEEDBACK CONNECTIONS[J].Journal of Software,1997,8(4):252-258. |
| |
| Authors: | ZHANG Ling and ZHANG Bo |
| |
| 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., -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. |
| |
| Keywords: | Multilayered neural network with feedback connections learning algorithm clustering |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《软件学报》浏览原始摘要信息 |
|
点击此处可从《软件学报》下载全文 |
|
