I am studying how GA works. It is known that GA obtains the optimal solution by iteration through the the process of reproduction, crossover, and mutation.
When crossover and mutation, the probability numbers ($P_c$ and $P_m$) have to be specified.
My question is:
At each iteration, how does GA know when to crossover or mutation if we specify $P_c$ = 0.8 and $P_m$ = 0.7?
Could you give me suggestions or reference ?
Best Answer
The probabilities for crossover and mutation doesn't need to be complementary. Usually the crossover is performed first (crossing two individuals with probability $P_c$) and then the mutation is applied to the resulting individuals (with probability $P_m$).
So, in your example, $80\%$ crossovers are performed and then $70\%$ of the resulting offsprings are mutated.