Information Technology Reference
In-Depth Information
Table 5.8
Performance and settings used in the “V” function problem.
GEA-B
GEP-NC
GEP-RNC
Number of runs
100
100
100
Number of generations
5000
5000
5000
Population size
30
30
30
Number of fitness cases
10 (Table 5.7)
10 (Table 5.7)
10 (Table 5.7)
Function set
+ - * / Q L E S C
+ - * / Q L E S C
+ - * / Q L E S C
Terminal set
a
a 1 2 3 4 5
a ?
Random constants array length
--
--
10
Random constants type
--
--
Rational
Random constants range
--
--
[-2, 2]
Head length
6
6
6
Gene length
13
13
20
Number of genes
5
5
5
Linking function
+
+
+
Chromosome length
65
65
100
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
Dc-specific mutation rate
--
--
0.044
Dc-specific inversion rate
--
--
0.1
Dc-specific transposition rate
--
--
0.1
Random constants mutation rate
--
--
0.01
Fitness function
Eq. (3.5)
Eq. (3.5)
Eq. (3.5)
Average best-of-run fitness
895.167
714.658
812.840
Average best-of-run R-square
0.9960392190
0.9893241183
0.9936233497
5.6.2 Sequence Induction
For the sequence induction problem, a very simple function set composed of
the basic arithmetic operators was chosen for all the three algorithms, that is,
F = {+, -, *, /}. For the GEA-B algorithm, the set of terminals consists obvi-
ously of the independent variable
n
, thus giving T = {n}. For the GEP-NC
algorithm, besides the independent variable, four different integer constants
represented by the numerals 0-3 were used, thus giving T = {n, 0, 1, 2, 3},
where each numeral represents its namesake integer constant. For the GEP-
RNC algorithm, the set of terminals consists obviously of the independent
variable plus the ephemeral random constant “?”, thus giving T = {n, ?}.
