AW: some questions

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view

AW: some questions

Klaus Meffert

Hello Camellia,

the answer to your first question is: yes, there should be no problem in using just one supergene. You could also use a CompositeGene instead if the genes inside the supergene are not correlated directly (i.e. if gene 0 has value x, gene 1 can have only values a or b...).

Could you explain a bit more what you mean in your second question with "is called just once"? One explanation I could give is that for genes not being mutated their fitness value needs no recomputation and thus the fitness function is not called for them.



hi ,
I'am a beginner using JGAP. I have encounter some problems.
1- is it ok using a chromose having just one supergene?. such as :
  MySuperGene[] sampleGenes = new MySuperGene[1]; // MySuperGene extends 
                                                                                  // abstractSupergene
  integerGene[] genes = new IntegerGene[2];
  genes[0] = new IntegerGene(0,numOfTasks);
  genes[0].setAllele(new Integer(1));
  genes[1] = new IntegerGene(0,numOfTasks);
  genes[1].setAllele(new Integer(2));
  sampleGenes[0] = new MySuperGene(genes);
  Chromosome myChromosome = new Chromosome(sampleGenes);
2. why fitness function is called just once when evolving population with size more than one ?
waiting fir reply.
tanx alot.
camellia :)

Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around

------------------------------------------------------- This email is sponsored by: Splunk Inc. Do you grep through log files for problems? Stop! Download the new AJAX search engine that makes searching your log files as easy as surfing the web. DOWNLOAD SPLUNK! _______________________________________________ jgap-users mailing list [hidden email]