引用本文: | 莫鸿强,罗 飞,侯小梅,毛宗源.常见遗传多层前馈神经网络实数编码的不合理性分析和改进[J].控制理论与应用,2001,18(2):281~284.[点击复制] |
MO Hong-qiang,LUO Fei,HOU Xiao-mei,MAO Zong-yuan.An Analysis and Improvement of the Shortcomings of the Common Real Number Coding Scheme in Genetic Multilayer Feedforward Neural Networks[J].Control Theory and Technology,2001,18(2):281~284.[点击复制] |
|
常见遗传多层前馈神经网络实数编码的不合理性分析和改进 |
An Analysis and Improvement of the Shortcomings of the Common Real Number Coding Scheme in Genetic Multilayer Feedforward Neural Networks |
摘要点击 1194 全文点击 1635 投稿时间:1999-10-26 修订日期:2000-06-28 |
查看全文 查看/发表评论 下载PDF阅读器 |
DOI编号 |
2001,18(2):281-284 |
中文关键词 遗传算法 多层前馈神经网络 编码 模式 |
英文关键词 genetic algorithms multilayer feedforward neural networks coding scheme schema |
基金项目 国家自然科学基金(69864001)资助项目. |
|
中文摘要 |
对遗传多层前馈神经网络常见的实数编码中不适合于优化权值大小、不利于交叉算子发挥作用等问题, 进行了理论分析, 提出了“最小模式”等概念, 并据此对编码方式做了改进, 通过一个实例的仿真结果表明改进后的编码方式具有较好的寻优效果. |
英文摘要 |
This paper theoretically analyses the problems in the common real number coding scheme in genetic multilayer feedforward neural networks, such as being unsuitable for the optimization of the weights, influencing the function of crossing operators, and so on. A concept named as “minimal schema” is proposed, based on which the coding scheme is improved. The simulation results of an example show that the improving coding is effective in optimization. |
|
|
|
|
|