Information Technology Reference
In-Depth Information
section 2.1, GEP chromosomes can have different structural organizations
and, therefore, the individuals encoded in those structures have obviously
different degrees of complexity. The simplest individuals we have encountered
so far are encoded in a single gene, and the “organism” is, in this case, the
product of one gene - an ET composed of only one subunit. In other cases,
the “organism” is a multi-subunit ET in which the different subunits are linked
together by a particular linking function. And in other cases, the “organism”
is composed of different sub-ETs in which the different sub-ETs are respon-
sible for a particular facet of the problem at hand. In this section we will
discuss different aspects of the expression of the genetic information in gene
expression programming, drawing attention to the different levels of
phenotypic complexity.
2.2.1 Information Decoding: Translation
From the simplest individual to the most complex, the expression of the ge-
netic information in gene expression programming starts with translation or,
in other words, with the construction of all the sub-ETs.
Consider the following chromosome composed of just one gene (the tail
is shown in bold):
0123456789012345
NIAbO bbaaaabaabb
(2.10)
The symbols {A, O, N, I} represent, respectively, the Boolean functions AND,
OR, NOT, and IF (if a = 1, then b ; else c ), where the first two functions take
two arguments, NOT takes one argument, and the IF function takes three
arguments. In this case, the product of translation is the following expression
tree with nine elements:
N
A
b
O
a
a
b
b
which, as you can easily check, is a perfect, albeit rather verbose, solution to
the NOR function.
Search WWH ::




Custom Search