The neural networks described in this chapter are perhaps the most complex entities created with gene expression programming. Therefore, it would be interesting to see if the evolutionary dynamics of these systems exhibit the same kind of pattern observed in other less complex systems.
As shown in Figure 5.8, GEP-NN systems exhibit the same kind of dynamics found on other, less complex GEP systems. The particular dynamics shown in
Figure 5.8 was obtained for a successful run of the experiment summarized in the second column of
Table 5.3. Note the characteristic oscillatory pattern on average fitness and that the best fitness is considerably above average fitness.
Figure 5.8. Evolutionary dynamics found in complex GEP systems, specifically, on run 4 of the experiment summarized in the second column of
Table 5.3.
The ubiquity of these dynamics suggests that, most probably, all healthy genotype/phenotype evolutionary systems are ruled by them.
The dynamics of gene expression programming will be explored further in
chapter 7 but, before that, let’s analyze yet another modification to the basic gene expression algorithm in order to solve scheduling problems.
|