
An Introduction to Creative Evolutionary Systems
Unless the genetic operators are very badly designed, an EA will always
"home in" on these areas. The same is true, to some extent, of
local search meth-
ods, which navigate the space one solution at a time, in the way we saw illustrated
by Figure 1.1. It is easy to imagine, however, that such a process might soon get
stuck at a so-called
local optimum---a solution that is far from best, but whose im-
mediate neighbors in the space are all even worse. Part of the power and success
of EAs lies in the fact that the insistence on maintaining a population