| 利用进化规划和逐步二次规划实现前馈神经网络的结构优化 |
| |
| 引用本文： | 金聪.利用进化规划和逐步二次规划实现前馈神经网络的结构优化[J].系统工程理论与实践,2003,23(2):106-110. |
| |
| 作者姓名： | 金聪 |
| |
| 作者单位： | 湖北大学数学与计算机科学学院 |
| |
| 基金项目： | 湖北大学重点基金资助 ( A0 0 0 1 ) |
| |
| 摘 要： | 用进化规划与逐步二次规划来实现前馈神经网络的结构优化问题 ,并提出了一个相应的学习算法 .针对进化规划与逐步二次规划各自的特点 ,进行了组合 ,使算法不仅具有随机全局搜索能力 ,而且还具有更好的全局收敛能力 ,并与环境有更强的自适应能力 .最后通过仿真和应用实验证实了算法的有效性.
|
| 关 键 词： | 前馈神经网络 进化规划 结构优化 逐步二次规划 |
| 文章编号： | 1000-6788(2003)02-0106-05 |
| 修稿时间： | 2001年8月22日 |
Structure Optimization for Feed-forward Neural Networks Based on Evolutionary Programming and Sequential Quadratic Programming |
| |
| JIN Cong.Structure Optimization for Feed-forward Neural Networks Based on Evolutionary Programming and Sequential Quadratic Programming[J].Systems Engineering —Theory & Practice,2003,23(2):106-110. |
| |
| Authors: | JIN Cong |
| |
| Institution: | College of Mathematics and Computer Science,Hubei University |
| |
| Abstract: | In this paper, when evolutionary programming and sequential quadratic programming are applied to the structure optimization of feed-forward neural networks, a learning algorithm is proposed. The new algorithm retains the ability of stochastic global searching. It has better global convergence and very strong self-adaptive ability with environment. The efficiency of research work mentioned above has been shown by simulation and applications. |
| |
| Keywords: | feed-forward neural networks evolutionary programming structure optimization sequential quadratic programming |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《系统工程理论与实践》浏览原始摘要信息 |
| 点击此处可从《系统工程理论与实践》下载免费的PDF全文 |
