Cultural swarms
Bin Peng, Robert G. Reynolds, J.J. Brewster · 2004
In the previous work it was observed that certain problem solving phases emerged during the optimization process for a real-valued functional surface within a cone-world environment using a cultural algorithm. The cultural algorithm was configured using five knowledge sources in the belief space, and evolutionary programming model in the population space (Reynolds and Saleem, 2003). It turned out that the five knowledge sources exhibited a swarming behavior at the meta level while solving the problem (Iacoban and Reynolds, 2003). In this paper we investigate whether this swarming behavior at the meta level induces swarming at the population level. Our results show that each knowledge source can control interacting flock of individuals in the population space.