0
$\begingroup$

I'm working with genetic programming and let's say I have the following operator:

  • pop_size = 100
  • Crossover ratio = 0.4
  • Mutation Ratio = 0.2
  • Selection Ratio = 0.1

What is exactly the next generation will look like?

  • Select 10% from the last pop with any selection scheme.
  • Fill 40% of the next generation with the crossover between parents.
  • Mutate the new offspring based on that mutation ratio before adding it to the next generation.
  • That will be 50% of the next generation filled up, and we have to fill the remaining 50%, how to do this? by mutating the individuals from the last generation according to the mutation ratio? add some random genes to the next generation?
Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

The remaining will be models selected from the original population based on the best performers (or some other user defined criteria). You don't do anything to those models - no crossover and no mutations - just keep them as they are.

Improve this answer
$\endgroup$
1
  • $\begingroup$ so first of all we gonna select 10% with any selected method, after that, we gonna fill the remaining 50% of the next generation with the old individuals' best performers; if we sum this we gonna find 60% of the last individuals will be added to the next generation? $\endgroup$
    – CTMA
    Commented Nov 1, 2022 at 12:44

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .