Information Technology Reference
In-Depth Information
Table 6.3
Performance and parameters for the odd-
n
-parity problem with ADFs.
Odd-2
Odd-3
Odd-4
Number of runs
100
100
100
Number of generations
50
10000
100000
Population size
30
30
30
Number of fitness cases
4
8
16
Function set of ADFs
A O N
A O N
A O N
Terminal set
a b
a b c
a b c d
Head length
7
7
10
Gene length
15
15
21
Number of genes/ADFs
2
2
2
Function set of homeotic genes
A O N
A O N
A O N
Terminal set of homeotic genes
ADFs 0-1
ADFs 0-1
ADFs 0-1
Number of homeotic genes/cells
3
3
3
Head length of homeotic genes
7
7
7
Length of homeotic genes
15
15
15
Chromosome length
75
75
87
Mutation rate
0.044
0.044
0.044
Inversion rate
0.1
0.1
0.1
IS transposition rate
0.1
0.1
0.1
RIS transposition rate
0.1
0.1
0.1
One-point recombination rate
0.3
0.3
0.3
Two-point recombination rate
0.3
0.3
0.3
Gene recombination rate
0.3
0.3
0.3
Gene transposition rate
0.1
0.1
0.1
Mutation rate in homeotic genes
0.044
0.044
0.044
Inversion rate in homeotic genes
0.1
0.1
0.1
RIS transposition rate in homeotic genes
0.1
0.1
0.1
IS transposition rate in homeotic genes
0.1
0.1
0.1
Fitness function
Eq. (3.8)
Eq. (3.8)
Eq. (3.8)
Success rate
100%
97%
44%
again, that each ADF is called twice from the main program. In (c), the ADFs
designed by the system are both of them functions of three arguments. And
both these functions are called twice from different places in the main pro-
gram. These are just some examples of the variety of building blocks the
system is able to invent and then immediately use to build modular solutions
to the problem at hand.
In Figure 6.11 is shown a small sample of modular solutions to the more
complex odd-4-parity function designed with the cellular system. For
