文件名称:yichuansuanfaC
- 所属分类：
- 人工智能/神经网络/遗传算法
- 资源属性：
- [WORD]
- 上传时间：
- 2012-11-26
- 文件大小：
- 9kb
- 下载次数：
- 0次
- 提 供 者：
- ma***
- 相关连接：
- 无
- 下载说明：
- 别用迅雷下载，失败请重下，重下不扣分！
介绍说明－－下载内容均来自于网络，请自行研究使用
遗传算法是模拟达尔文的遗传选择和自然淘汰的生物进化过程的计算模型.
生存+检测的迭代搜索过程是它的核心.
具体分成五部,其中每步就是程序实现过程:
参数编码(实际问题编码到遗传基因),初始群体设定(祖先),适应度函数的设计(生存选择),遗传操作设计(遗传+变异),控制参数设计(交叉率0.2-0.99,变异率0.001-0.1).
-Genetic algorithms are simulated Darwinian natural selection of genetic selection and biological evolution of the computational model. Survival+ testing iterative search process is its core. Concrete into five, each of which is the process step implementation process: parameter code (the actual problem encoded genes), the initial group setting (ancestors), the design of fitness function (survival selection), design of genetic manipulation (genetic+ variation), the control design parameters (crossover rate of 0.2-0.99, mutation rate 0.001-0.1) .
生存+检测的迭代搜索过程是它的核心.
具体分成五部,其中每步就是程序实现过程:
参数编码(实际问题编码到遗传基因),初始群体设定(祖先),适应度函数的设计(生存选择),遗传操作设计(遗传+变异),控制参数设计(交叉率0.2-0.99,变异率0.001-0.1).
-Genetic algorithms are simulated Darwinian natural selection of genetic selection and biological evolution of the computational model. Survival+ testing iterative search process is its core. Concrete into five, each of which is the process step implementation process: parameter code (the actual problem encoded genes), the initial group setting (ancestors), the design of fitness function (survival selection), design of genetic manipulation (genetic+ variation), the control design parameters (crossover rate of 0.2-0.99, mutation rate 0.001-0.1) .
(系统自动生成,下载前可以参看下载内容)
下载文件列表
遗传算法C.doc