W. B. Langdon and R. Poli
There is some connection between bloat and complexity. Perhaps bloat
highlights a difficulty, in that we are generating huge programs with
the same fitness and identical behaviour. Should we define the
complexity of such bloated programs as being the same as a shorter one
which does the same thing?
We are only using the ant problem as an example of bloat. Much shorter
solutions can be evolved if need be.
Bill
W. B. Langdon, Phone +44 121-414-4791
School of Computer Science, Fax +44 121-414-4281
University of Birmingham,
Birmingham. B15 2TT United Kingdom
http://www.cs.bham.ac.uk/~wbl/