Information Technology Reference
In-Depth Information
As its expression shows, this program matches exactly the target sequence
(5.14) (the contribution of each gene is shown in brackets):
(5.16b)
a
n
(
n
3
2
n
2
)
(
n
)
(
n
3
n
2
)
(
n
3
n
2
)
(
4
n
4
)
4
n
4
3
n
3
2
n
2
n
Note how the algorithm creates all the necessary constants from scratch by
performing simple arithmetical operations.
The first perfect solution created by the GEP-NC algorithm was discov-
ered in generation 39 of run 1. Its chromosome is shown below (the sub-ETs
are linked by addition):
0123456789012
*+*++*nn101n1
n1n23nn112311
*+*++*nnn12nn
*+*+-*nnn12nn
0/321+n31331n
(5.17a)
As its expression shows, this program matches perfectly the target sequence
(5.14) (the contribution of each gene is shown in brackets):
a
n
(
n
3
2
n
2
)
(
n
)
(
2
n
4
3
n
3
)
(
2
n
4
n
3
)
(
0
4
n
4
3
n
3
2
(5.17b)
n
2
n
Note how the algorithm makes use of the ready-made constants, not only by
integrating them directly into the sub-ETs but also by combining them to
create new ones.
The first perfect solution designed by the GEP-RNC algorithm was dis-
covered in generation 59 of run 0. Its genes and their respective arrays of
random numerical constants are shown below (the sub-ETs are linked by
addition):
Gene 1: *+--*?n??nn??7886912
C
1
: {3, 2, 2, 1, 0, 0, 1, 3, 1, 1}
Gene 2: ?*+++*?n???n?9797539
C
2
: {1, 3, 3, 0, 0, 0, 2, 3, 3, 0}
Gene 3: ----*-?n?nnn?9736635
C
3
: {1, 3, 2, 3, 0, 2, 2, 3, 1, 0}
Gene 4: ****++nnn???n0247720
C
4
: {2, 2, 2, 1, 1, 2, 0, 0, 1, 0}
Gene 5: +/n/??nnn?n??1407127
C
5
: {1, 3, 0, 3, 0, 2, 0, 2, 1, 0}
(5.18a)
