Multiple Crossover Per Couple in genetic algorithms

Conventional approaches to crossover apply the operator only once on the selected pair of parents, to create precisely two offspring. Multiple Crossover Per Couple (MCPC) is an alternative, recently proposed (S. Esquivel et al., 1995), approach under which more than one crossover operation for each mating pair is allowed. The paper shows the empirical results obtained with genetic algorithms allowing MCPC when searching for minimum global values for a set of hard functions.