XIII. Recommendations


Parameters of GA

This chapter should give you some basic recommendations if you have decided to implement your genetic algorithm. These recommendations are very general. You will probably want to experiment with your own GA for a specific problem, because there is no general theory available that would help you to tune GA parameters for any problem.

Recommendations are often results of empiric studies of GAs that were often performed on binary encoding only.



Applications of GA

Genetic algorithms have been used for difficult problems (such as NP-hard problems), for machine learning and also for evolving simple programs. They have been also used for some art, for evolving pictures and music.

The advantage of GAs is in their parallelism. GA is travelling in a search space using more individuals (and with genotype rather than phenotype) so that they are less likely to get stuck in a local extreme like the other methods.

They are also easy to implement. Once you have the basic GA algorithm implemented, you have just to write a new chromosome (just one object) to solve another problem. With the same encoding you just change the fitness function - and you are done. However, for some problems, choosing and implementation of encoding and fitness function can be difficult.

The disadvantage of GAs is in the computational time. GAs can be slower than other methods. But sice we can terminate the computation in any time, the longer run is acceptable (especially with faster and faster computers).

To get an idea about some problems solved by GAs, here is a short list of some applications:

More information can be found through links in the appendix.


           
(c) Marek Obitko, 1998