Masters Outline
When dealing with genetic algorithms and artificial life, the single most important factor is evolution. For evolution to occur, the representation of the "solution" or "organism", its ''genetic language'', must be able to change from one form into another. The purpose of this project is to attempt to determine what features and properties of a language affect its evolution, and perhaps begin to establish a "theory of evolvability" that is applicable to genetic algorithm systems.
Notes and directions on this:
- Start at the low level, Gray code
- Look at the higher level, Permutation encoding
- Explain how all this ties in to genotype <-> phenotype mapping
- Extract various properties (orthogonality, etc.)
- Test the various properties as individually as possible.
Page last modified on January 12, 2005, at 02:50 AM