| 归一化RBF网络的结构优化策略 |
| |
| 引用本文： | 祖家奎,赵淳生,戴冠中. 归一化RBF网络的结构优化策略[J]. 南京航空航天大学学报(英文版), 2003, 20(1): 73-78 |
| |
| 作者姓名： | 祖家奎 赵淳生 戴冠中 |
| |
| 作者单位： | 南京航空航天大学超声电机研究中心,南京,210016,中国;西北工业大学自动控制系,西安,710072,中国 |
| |
| 摘 要： | 针对归一化RBF网络,利用基于山峰函数的减法聚类算法构造归一化RBF网络的初始结构,采用奇异值分解(SVD)算法分析了网络隐含层节点与奇异值、累积贡献率以及索引向量的关系,并对归一化RBF网络的结构进行了优化。最后,对该优化策略的可行性和有效性进行了仿真验证和性能比较。
|
| 关 键 词： | RBF网络 减法聚类 奇异值分解 结构优化 |
STRUCTURE OPTIMIZATION STRATEGY OF NORMALIZED RBF NETWORKS |
| |
| ZU Jia-kui,ZHAO Chun-sheng,DAI Guan-zhong. STRUCTURE OPTIMIZATION STRATEGY OF NORMALIZED RBF NETWORKS[J]. Transactions of Nanjing University of Aeronautics & Astronautics, 2003, 20(1): 73-78 |
| |
| Authors: | ZU Jia-kui ZHAO Chun-sheng DAI Guan-zhong |
| |
| Abstract: | Aimed at studying normali zed radial basis function network (NRBFN), this paper introduces the subtractiv e clustering based on a mountain function to construct the initial structure of NR BFN, adopts singular value decomposition (SVD) to analyze the relationship betwe en neural nodes of the hidden layer and singular values, cumulative contribution ratio, index vector, and optimizes the structure of NRBFN. Finally, simulation and performance comparison show that the algorithm is feasible and effective. |
| |
| Keywords: | radial basis function n etworks subtractive clustering singular value decomposition structure optimiz ation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
