Information Technology Reference
In-Depth Information
subjected to the constraints:
10
d
p
,...,
p
d
10
(8.8b)
1
5
The global maximum of this function is not known and, consequently, we
won't be able to compare the performance of the algorithms in terms of suc-
cess rate; consequently, we will use the average best-of-run output and the
best-of-experiment output for that purpose.
As shown in Table 8.4, at this task, the GEP-PO algorithm performs slightly
better than the simpler HZero system, with average best-of-run output of
Table 8.4
Performance and settings for the five-parameter function optimization
problem using the HZero algorithm and the GEP-PO algorithm.
HZero
GEP-PO
Number of runs
100
100
Number of generations
20,000
20,000
Population size
30
30
Function set
--
+ - * /
Terminal set
?
?
Random constants array length
10
10
Random constants type
Rational
Rational
Random constants range
[-10, 10]
[-2, 2]
Head length
0
6
Gene length
2
20
Number of genes
5
5
Chromosome length
10
100
Mutation rate
--
0.025
Inversion rate
--
0.1
IS transposition rate
--
0.1
RIS transposition rate
--
0.1
One-point recombination rate
0.3
0.3
Two-point recombination rate
0.3
0.3
Gene recombination rate
0.3
0.3
Gene transposition rate
0.1
0.1
Random constants mutation rate
0.35
0.01
Dc-specific mutation rate
0.01
0.025
Dc-specific inversion rate
--
0.1
Dc-specific transposition rate
--
0.1
Average best-of-run output
2.748712187
2.748801579
Best-of-experiment output
2.749120718
2.749128143
