Knowledge-Based Control of Self-Adaptive Evolutionary Search

Self-adaptation has been frequently employed in evolutionary search. Angeline [1995] defines three distinct levels of self- adaptation which are: population,individual,and component levels. Cultural Algorithms developed by Reynolds[1979] have been shown to provide a framework in which to model self-adaptation at each of these levels.Here, we examine the role that different forms of knowledge can play in the self-adaptation process at the pop- ulation level for evolution-based function optimizers. In particular, we compare the relative performance of normative and situational knowledge in guiding the search process. Properties of functional lanscapes as suggested by Winston [1992] are used to classify the functions associated with 27 different benchmark optimization problems. The results suggest that the type of knowledge used to direct effective search for a given problem depends upon the combination of properties that are found in the associated functional landscape.