Dear Moussa Kamal,
Correct me if I am wrong but in a GA optimisation you set a criterion so that the value of the function does not deviate from the objective value by a significant amount,then why would you want to change the objective function by change of variable ?
Soumitra K Mallick
for Soumitra K Mallick, Nick Hamburger, Sandipan Mallick
If you provide more details it might make answering the question simpler. But generally the power of the GA lies in its randomness. If you constrain it, it won't be as effective. Also, how do you enforce a step size when two random individuals are used in a cross-over function? I don't think it's possible.
That said, it will also depend on your implementation of the GA. I use Python and DEAP, and that gives me a lot of control over the mutation and cross-over functions. Something similar to fixed step sizes are easy to enforce in mutation functions, but not in cross-over functions.
Dear Soumitra K Mallick
Thanks for your answer. Well, my purpose is to specify a predefined controlled step for the variables at each GA iteration. In fact, this shall decrease the computation time which is something I look to.
Kind regards.
Moussa KAFAL
- Badges
- Science topic
- Similar topics
- Linguistics
- Composition Studies
- Publication