Creators Of Genetic Algorithms--- those that, over time, move to an optimal solution by randomly mutating or intermixing the data they operate on --want to reach the best solutions as fast as possible. A Hansung University(Seoul, South Korea) researcher decided this might be better achieved by having the data breed only with the best, and reproduce like bees rather than birds. just as the queen bee is the only bee in a hive that breeds with the others, the best solution in the pool of solutions is selected to crossbreed with a random set of others. Thus the algorithm aims to retain the best solutions in the "gene pool," and achieve a better answer. This differs from the traditional approach, which selects both parents randomly from the whole poll.
Queen-Bee Evolution for genetic algorithm.
Author : Robin
Administrator
Post a Comment