Information Technology Reference
In-Depth Information
Figure 4.12.
Space-time diagrams describing the evolution of CA states for the
GEP
1
rule. The number of 1's in the IC (
ρ
0
) is shown above each diagram. In both
cases the CA converged correctly to a uniform pattern.
represents the already familiar majority function with three arguments), and
the set of terminals was obviously the same. In this case, a total of 100 unbi-
ased ICs and three-genic chromosomes with sub-ETs linked by IF were used.
The parameters used per run are shown in the second column of Table 4.19.
In this experiment, the fitness function was slightly modified by introduc-
ing a ranking system, in which individuals capable of correctly classifying
between 2 ICs and 3/4 of the ICs received one bonus equal to
C
; if correctly
Table 4.20
Description of two rules discovered by GEP for the density-
classification task. The output bits are given in lexicographic
order starting with 0000000 and finishing with 1111111.
GEP1
00010001 00000000 01010101 00000000
00010001 00001111 01010101 00001111
00010001 11111111 01010101 11111111
00010001 11111111 01010101 11111111
GEP2
00000000 01010101 00000000 01110111
00000000 01010101 00000000 01110111
00001111 01010101 00001111 01110111
11111111 01010101 11111111 01110111
