文件名称:AGA.rar
-
所属分类:
- 标签属性:
- 上传时间:2012-09-04
-
文件大小:5.93kb
-
已下载:0次
-
提 供 者:
-
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--下载内容来自于网络,使用问题请自行百度
采用了保优的选择遗传算法
终止条件的判断是:到达一定的代数。可改进为:相邻若干代的种群平均适应值的变化来判断。若相邻若干代的种群平均适应值为变化或者是变化小于某一阈值,表示算法已经收敛,则退出算法。
选择算子:轮盘赌选择;
交叉算子:单点交叉,随机选择计算此适应度值,若大于当前最佳适应度值则降低交叉概率,否则不变;
变异算子:模板,对于优势个体,除采用低概率变异外,变异位置应采取权值越大,变异概率越小的原则,而对劣势个体则相反.,Paul used the choice of excellent conditions for the termination of genetic algorithm to determine is: a certain algebra. Could be improved as follows: adjacent to the average number of generations of populations to adapt to the changes to determine the value. Adjacent to several generations if the population average fitness for the change or changes in less than a threshold, that the algorithm has been convergence, then from the algorithm. Selection operator: roulette wheel selection crossover: single-point crossover, randomly selected to calculate the fitness value, if greater than the current best fitness value to reduce the probability of crossover, otherwise remain unchanged mutation operator: the template for advantage of the individual, with the exception of the use of low-probability variation, the variation of the location of the greater weight should be taken, the smaller the mutation probability principle, and that the opposite is true for the inferior individual.
终止条件的判断是:到达一定的代数。可改进为:相邻若干代的种群平均适应值的变化来判断。若相邻若干代的种群平均适应值为变化或者是变化小于某一阈值,表示算法已经收敛,则退出算法。
选择算子:轮盘赌选择;
交叉算子:单点交叉,随机选择计算此适应度值,若大于当前最佳适应度值则降低交叉概率,否则不变;
变异算子:模板,对于优势个体,除采用低概率变异外,变异位置应采取权值越大,变异概率越小的原则,而对劣势个体则相反.,Paul used the choice of excellent conditions for the termination of genetic algorithm to determine is: a certain algebra. Could be improved as follows: adjacent to the average number of generations of populations to adapt to the changes to determine the value. Adjacent to several generations if the population average fitness for the change or changes in less than a threshold, that the algorithm has been convergence, then from the algorithm. Selection operator: roulette wheel selection crossover: single-point crossover, randomly selected to calculate the fitness value, if greater than the current best fitness value to reduce the probability of crossover, otherwise remain unchanged mutation operator: the template for advantage of the individual, with the exception of the use of low-probability variation, the variation of the location of the greater weight should be taken, the smaller the mutation probability principle, and that the opposite is true for the inferior individual.
相关搜索: AGA
(系统自动生成,下载前可以参看下载内容)
下载文件列表
AGA.txt
本网站为编程资源及源代码搜集、介绍的搜索网站,版权归原作者所有! 粤ICP备11031372号
1999-2046 搜珍网 All Rights Reserved.