Fuzzy Recombination for the Breeder Genetic Algorithm
Hans-Michael Voigt, Heinz Mühlenbein, Dragan Cvetković · 1995
A new recombination operator, called fuzzy recombination (FR) is introduced for continuous genes. The performance of the operator is analyzed by means of the equation describing the response to selection. The operator is evaluated according to a new design criterion: maximizing the product of heritability and standard deviation. The breeder genetic algorithm BGA with FR converges linearly for a test suite of benchmark functions. The computational complexity is also computed. We believe that linear convergence is the optimum to be achieved by random search methods. The question remains open: Can a random search method be found which gives the best linear convergence, i.e. the smallest constant for a well-defined class of functions? 1 Introduction Let an optimization problem be given on a domain G ae R n f = f(x ) = min x2G f(x); G ae R n : (1) We make no assumptions concerning the convexity and differentiability of the function f(x). For the minimization a number of algorit...