Knowledge-based self-adaptation in evolutionary search

Self-adaptation has been frequently employed in evolutionary computation. A ngeline(1) defined three distinct adaptive levels which are: population, in dividual and component levels. Cultural Algorithms have been shown to provi de a framework in which to model self-adaptation at each of these levels. H ere, we examine the role that different forms of knowledge can play in the self-adaptation process at the population level for evolution-based functio n optimizers. In particular, we compare the relative performance of normati ve and situational knowledge in guiding the search process. An acceptance f unction using a fuzzy inference engine is employed to select acceptable ind ividuals for forming the generalized knowledge in the belief space. Evoluti onary programming is used to implement the population space. The results su ggest that the use of a cultural framework can produce substantial performa nce improvements in execution time and accuracy for a given set of function minimization problems over population-only evolutionary systems.