On classification tools for genetic algorithms
Stefan Kotowski, Witold Kosiński, Zbigniew Michalewicz, Piotr Synak, Łukasz Brocki · Proceedings of the International Multiconference on Computer Science and Information Technology · 2008
Some tools to measure convergence properties of genetic algorithms are introduced. A classification procedure is proposed for genetic algorithms based on a conjecture: the entropy and the fractal dimension of trajectories produced by them are quantities that characterize the classes of the algorithms. The role of these quantities as invariants of the algorithm classes is discussed together with the compression ratio of points of the genetic algorithm.