Information Technology Reference
In-Depth Information
a.
012345678901234
+*?+?*+a??aaa??
56789012
09081345
b.
Dc
0
?
9
0
?
8
1
a
a
??
3
4
5
Figure 2.9. Translation of chromosomes with an additional domain for handling
random numerical constants. a) The chromosome composed of a conventional
head/tail domain and an extra domain (Dc) encoding random numerical constants
represented by the numerals 0-9 (shown in bold). b) The sub-ETs codified by each
domain. The one-element sub-ETs encoded in Dc are placed apart together. “?”
represents the random numerical constants encoded in the numerals of Dc. How all
these sub-ETs interact will be explained in chapter 5.
weights of the connections and the thresholds of the neurons must be as-
signed posttranslationally. In chapter 10, Design of Neural Networks, we
will learn the rules of their complete development and how populations of
these complex individuals evolve, finding solutions to problems in the form
of adaptive neural networks totally encoded in linear genomes.
2.5 Karva Language: The Language of GEP
We have already seen that each gene codes for a particular sub-ET, and that
each sub-ET corresponds to a specific K-expression or open reading frame.
Due to the simplicity and elegance of this correspondence, K-expressions
are, per se, extremely compact, intelligible computer programs. We have
already seen how multi-subunit expression trees can be easily converted into
linear K-expressions, and this can be easily done for any algebraic or Boolean
Search WWH ::




Custom Search