GeneXproTools 4.0 uses two different learning algorithms for
Logic Synthesis problems. The first – the basic gene expression algorithm
or simply Gene
Expression Programming (GEP) – does not support the direct manipulation of random numerical
constants (0's and 1's in this case),
whereas the second – GEP
with Random Numerical Constants or GEP-RNC
for short – has a facility for handling them directly. So, these
two algorithms search the solution landscape differently and
therefore you might wish to try them both on your problems.
The GEP-RNC algorithm
is slightly more complex than GEP
as it uses an additional gene domain (Dc) for encoding the random
numerical constants. Consequently, this algorithm comes equipped
with an additional set of genetic operators (RNC
mutation, Dc mutation,
Dc inversion, and Dc
IS transposition) especially developed for handling random
numerical constants (if you are not familiar with these operators,
please use the default values by clicking the Default button for
they work very well in all cases).
Taking into consideration not only the slightly higher complexity of
the GEP-RNC algorithm
but also the fact that both these algorithms produce equally elegant
circuits, GEP
is the default learning algorithm in
GeneXproTools 4.0. However, you can activate the GEP-RNC algorithm
in the Settings Panel -> Numerical Constants by checking the Use Random Numerical Constants box.
|