Hi,
> > It's ok, I'm not disappointed :) > My main reason for coding the module is for learning. I think I will > learn more by coding and trying to figure out why my module behaves the > way it is, than by simply reading about the subject or running some one > else's code. In fact, I did learn already the significance of mutation > in diversifying the genetic population by turning mutation on and off > and analyzing the results. > Mutation is the main variation operator in GAs, but there are many kind of mutation operators; turning it off will probably do away with finding the solution, but you can try changing the proportion of mutation/crossover. The ideal is supposed to be ~ 20/80, but some purists say it should be ~ 1/99. Genetic programming, actually, uses only some very specific kind of mutations, and sparingly at that; it makes up for lost diversity by creating a huge and diverse initial population. > Yes, I did a quick search before, and all I find where programs that > utilize genetic algorithms to do certain tasks. I didn't find any > generic modules to do the job. > There's none, right. OPEAL comes closest to it, if only I find the time to upload it. > > Great. I'll have a look at it once my experience in this field grows a > bit more. Perhaps I can contribute code/ideas to your module. > That would be just great. Thanks! J -- PPSN2002 => http://ppsn2002.ugr.es Home => http://geneura.ugr.es/~jmerelo Tutorial Perl => http://granavenida.com/perl
