什么是交叉概率和交叉概率遗传算法或遗传编程中的突变概率？
什么是交叉概率和交叉概率遗传算法或遗传编程中的突变概率？有人可以从实施的角度解释一下吗！
What is Crossover Probability & Mutation Probability in Genetic Algorithm or Genetic Programming ? Could someone explain them from implementation perspective!
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（4）
突变概率（或比率）基本上是衡量染色体的随机元素被翻转成其他东西的相似程度的指标。例如，如果您的染色体被编码为长度为 100 的二进制字符串，如果您的突变概率为 1%，则意味着随机挑选的 100 位（平均）中的 1 位将被翻转。
交叉基本上模拟了有性基因重组（如人类繁殖），并且在遗传算法中通常有多种实现方式。有时，交叉在 GA 中的应用会有所节制（因为它会破坏对称性，这并不总是好的，而且你也可能会盲目），因此我们讨论交叉概率来指示有多少对的比率被挑选进行交配（它们通常是根据以下选择标准来挑选的 - 但那是另一个故事）。
这是一个短篇故事 - 如果您想要长篇故事，您必须付出努力并点击 Amber 发布的链接。或者做一些谷歌搜索 - 我上次检查的也是一个不错的选择:)
Mutation probability (or ratio) is basically a measure of the likeness that random elements of your chromosome will be flipped into something else. For example if your chromosome is encoded as a binary string of lenght 100 if you have 1% mutation probability it means that 1 out of your 100 bits (on average) picked at random will be flipped.
Crossover basically simulates sexual genetic recombination (as in human reproduction) and there are a number of ways it is usually implemented in GAs. Sometimes crossover is applied with moderation in GAs (as it breaks symmetry, which is not always good, and you could also go blind) so we talk about crossover probability to indicate a ratio of how many couples will be picked for mating (they are usually picked by following selection criteria - but that's another story).
This is the short story - if you want the long one you'll have to make an effort and follow the link Amber posted. Or do some googling - which last time I checked was still a good option too :)
根据 Goldberg（搜索、优化和机器学习中的遗传算法），交叉概率是在特定交配中发生交叉的概率；也就是说，并非所有交配都必须通过交叉繁殖，但可以选择 Pc=1.0。
突变概率根据 JohnIdol。
According to Goldberg (Genetic Algorithms in Search, Optimization and Machine Learning) the probability of crossover is the probability that crossover will occur at a particular mating; that is, not all matings must reproduce by crossover, but one could choose Pc=1.0.
Probability of Mutation is per JohnIdol.
它显示了交叉时从父母那里继承的特征的数量！
It's shows the quantity of features which inherited from the parents in crossover!
这里可能对这两个概率有一个很好的解释：
http://www.optiwater.com/optiga /ga.html
Johnldol 关于突变概率的回答正是该网站所说的：
“通过生成 0 到 1 之间的随机数来检查每条染色体中的每个位是否存在可能的突变，如果该数字小于或等于等于给定的突变概率，例如 0.001，则位值发生变化。”
对于交叉概率来说，也许就是交叉操作所诞生的下一代人口的比例。而其他人……也许是之前的选择
或者你可以将其定义为最适合的幸存者
Here might be a little good explanation on these two probabilities:
http://www.optiwater.com/optiga/ga.html
Johnldol's answer on mutation probability is exactly words that the website is saying:
"Each bit in each chromosome is checked for possible mutation by generating a random number between zero and one and if this number is less than or equal to the given mutation probability e.g. 0.001 then the bit value is changed."
For crossover probability, maybe it is the ratio of next generation population born by crossover operation. While the rest of population...maybe by previous selection
or you can define it as best fit survivors