| 基于遗传算法的神经网络两阶段学习方案 |
| |
| 引用本文： | 张栋,蔡开元.基于遗传算法的神经网络两阶段学习方案[J].系统仿真学报,2003,15(8):1088-1090. |
| |
| 作者姓名： | 张栋 蔡开元 |
| |
| 作者单位： | 北京航空航天大学自动化学院自动控制系,北京,100083 |
| |
| 基金项目： | 国家自然科学基金(60274057)，国家自然青年科学基金(60204011)。 |
| |
| 摘 要： | 一种两阶段学习方案被提出用于神经网络的训练。在第一阶段，让实数编码的遗传算法来代替人解决神经网络结构的选择和初始参数的设定，称之为结构辨识阶段。在第二阶段，让传统的优化算法来解决参数的学习，称之为参数辨识阶段。在整个学习过程，神经网络的复杂度、逼近精度和泛化能力之间得到了满意综合。
|
| 关 键 词： | 神经网络 网络拓扑 遗传算法 LM算法 |
| 文章编号： | 1004-731X(2003)08-1088-03 |
| 修稿时间： | 2002年9月25日 |
A Genetic-Algorithm-based Two-Stage Learning Scheme for Neural Networks |
| |
| ZHANG Dong,CAI Kai-yuan.A Genetic-Algorithm-based Two-Stage Learning Scheme for Neural Networks[J].Journal of System Simulation,2003,15(8):1088-1090. |
| |
| Authors: | ZHANG Dong CAI Kai-yuan |
| |
| Abstract: | A two-stage learning scheme for neural networks is proposed in this paper. In the first stage, which is called structure identification stage, the selection of network structure and initial parameters is carried out by float genetic algorithm instead of human. In the second stage, which is called parameter identification stage, the conventional optimization method is adopted to make refinements of parameters. Through the entire process, compromise is satisfactorily made among the network complexity, approximation accuracy and generalization ability. |
| |
| Keywords: | neural network network topology genetic algorithm LM algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
