Information Technology Reference
In-Depth Information
weight are kept in an array and are retrieved as necessary. For simplicity, the
number represented by the numeral in Dw indicates the order in the array.
Let's now analyze a simple neural network encoding a well-known Boolean
function, the exclusive-or. Consider, for instance, the chromosome below
with
h
= 3 and a domain encoding the weights with
d
w
= 6:
0123456
789012
DDDabab
752393
Its translation results in the following neural network:
D
3
9
D
D
7
5
2
3
a
b
a
b
And for the set of weights:
W = {-1.978, 0.514, -0.465, 1.22, -1.686, -1.797, 0.197, 1.606, 0, 1.753}
the neural network above gives:
D
D
D
a
b
a
b
which is a perfect solution to the exclusive-or function.
10.2 Special Genetic Operators
The efficient evolution of such complex entities composed of different do-
mains and different alphabets requires a special set of genetic operators. The
operators of the basic gene expression algorithm are easily transposed to
neural-net encoding chromosomes, and all of them can be used as long as the
boundaries of each domain are maintained and the different alphabets are
used within the confines of the corresponding domain.
