Abstract
One of the most important and challenging areas of
research in evolutionary algorithms is to investigate
ways to successfully apply evolutionary algorithms to
larger and more complicated problems. One approach to
make a given problem more tractable is to discover
problem representations automatically. Koza (1993) uses
the even-n-parity problem to demonstrate extensively
that his approach of Automatic Function Definition
(ADF) can facilitate the solution of the problem.
Unfortunately, the solutions found by GP with ADF can
only solved the problem for a particular value of n. If
a different value of n is used, GP with ADF must be
used again to find other programs that can solve the
new even-n-parity problem. Clearly, the solution found
is not general enough to solve all even-n-parity
problem for n greater than or equal to zero. In this
paper, we apply GGP (Generic Genetic Programming) to
evolve general recursive functions for the
even-n-parity problem. GGP is very flexible and
programs in various programming languages can be
acquired. Moreover, it is powerful enough to represent
context-sensitive information and domain-dependent
knowledge. This knowledge can be used to accelerate the
learning speed and/or improve the quality of the
programs induced. A number of experiments have been
performed to determine the impact of domain-specific
knowledge on the speed of learning.
Users
Please
log in to take part in the discussion (add own reviews or comments).