1) hypermutation probability
超变异概率
1.
Based on the theory of immune clone,the new algorithm redefines antibody af- finity,introduces concentration and dynamic clonal scale mechanism,and amends the hypermutation probability and operation.
针对目前克隆选择法中存在的训练时间长、收敛速度慢、精度低等缺点,提出一种新克隆选择法,在免疫克隆原理的基础上,重新定义抗体亲和度(与目标函数本身没有关系),在抗体克隆机制中增加浓度的因素,引入克隆规模动态调节机制,改进超变异概率和算子。
2) mutation probability
变异概率
1.
According to the concentrating degree of fitness of the populations,a kind of adaptive crossover probability and mutation probability were designed in terms of three variables of maximal fitness,minimal fitness and average fitness of the populations,whereby the crossover probabilities and mutation probabilities of the whole populations could be ad.
为了改善传统自适应遗传算法的收敛速度以及局部收敛问题,根据种群适应度的集中程度,以种群的最大适应度、最小适应度以及适应度平均值这3个变量为基础,设计了改进的自适应交叉概率和变异概率来调整整个种群的交叉概率和变异概率,提出了一种基于种群适应度集中程度的改进自适应遗传算法。
2.
The influence of mutation probability on the mean first hitting time is analyzed theoretically.
从理论上分析了变异概率对平均首次命中时间的影响。
3.
A new criterion for mutation operator is also proposed,which adjusts the mutation probability adaptively according to the whole generation s closeness.
提出了一种改进的遗传算法,采取了确定性采样选择算子对选择算子进行了改进;明确了非等概率融合单阈值单点交叉算子,对交叉算子进行了改进;同时还提出了一种新的变异算子,它依据一种新的判断群体"集中"与否的准则,根据群体的进化程度自适应地调整变异概率pm的值。
3) hypermutation rate
超变异率
4) overall mutation
全概率变异
1.
In view of the local search ability of simulated annealing algorithm,a new style of optimal algorithm which combined simulated annealing algorithm with pseudo parallel genetic algorithms and adopts real coding,self-adaptive crossover and overall mutation is designed.
借鉴模拟退火算法的局部搜索能力,结合并行计算的思想设计了一种采用模拟退火机制的实数编码自适应交叉、全概率变异伪并行遗传算法,最后用这种方法对典型的多峰值函数求极值,并和基本遗传算法进行比较,结果表明:该算法具有较强的全局搜索能力和局部搜索能力,能够更有效地克服早熟收敛问题。
5) adaptive proportion of mutation
自适应变异概率
6) Variation S-probability rough sets
变异S-概率粗集
补充资料：超超
1.谓超然出尘。 2.高高在上貌。 3.犹绰绰。 4.见"超超玄箸"。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条