| 基于进化规划的BP神经网络学习 |
| |
| 引用本文： | 叶立生,何奉道.基于进化规划的BP神经网络学习[J].西南交通大学学报,2001,36(5):545-548. |
| |
| 作者姓名： | 叶立生 何奉道 |
| |
| 作者单位： | 西南交通大学计算机与通讯工程学院 |
| |
| 基金项目： | 国家高性能计算中心(成都)资助项目 |
| |
| 摘 要： | 通过对将传统的BP算法和遗传算法应用到BP神经网络的学习的研究和分析，指出它们存在的缺陷。提出一个改进的进化规划算法，并将其应用于BP神经网络的权值优化。取XOR问题和4奇偶性问题的实验对传统的进化规划算法和改进的进化规划算法进行实验对比。实验结果表明，本文中提出的改进的进化规划算法优于前2个算法。
|
| 关 键 词： | BP神经网络 进化规划 BP算法 遗传算法 权值优化 反向传播学习算法 |
| 文章编号： | 0258-2724(2001)05-0545-04 |
The Learning of BP Neural Network Based on Evolutionary Programming |
| |
| YE Li sheng,HE Feng dao.The Learning of BP Neural Network Based on Evolutionary Programming[J].Journal of Southwest Jiaotong University,2001,36(5):545-548. |
| |
| Authors: | YE Li sheng HE Feng dao |
| |
| Abstract: | The shortcomings of the traditional methods are point out through the analysis of BP algorithm and genetic algorithm which are commonly applied to BP neural networks. A modified evolutionary programming is proposed to optimize the weight of BP neural network. The simulating results for XOR problem and four parity problem are given through comparison among BP algorithm, traditional evolutionary algorithm and the proposed modified evolutionary algorithm. The result indicates that the modified evolutionary algorithm proposed in this paper is superior to other two algorithms. |
| |
| Keywords: | neural networks algorithms optimization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
