Fittest Chromosome

[manolakis]

Hi there!!!

I was wondering if there is any way after finding a fittest chromosome in a population which might not have absolutely perfect fitness to use a GA to alter its genes in such a way that we will achieve a better solution.

Thanks for your time
manolakis

[Klaus Meffert-5]

Manolakis,

isn't this done by crossing over?
Please notice: it is never guaranteed that a best solution can be found!

Best

Klaus
----- original Nachricht --------

Betreff: [jgap-users]  Fittest Chromosome
Gesendet: So, 11. Mai 2008
Von: manolakis<agnostos_7@...>

>
> Hi there!!!
>
> I was wondering if there is any way after finding a fittest chromosome in a
> population which might not have absolutely perfect fitness to use a GA to
> alter its genes in such a way that we will achieve a better solution.
>
> Thanks for your time
> manolakis
> --
> View this message in context:
> http://www.nabble.com/Fittest-Chromosome-tp17169140p17169140.html
> Sent from the jgap-users mailing list archive at Nabble.com.
>
>
> -------------------------------------------------------------------------
> This SF.net email is sponsored by the 2008 JavaOne(SM) Conference
> Don't miss this year's exciting event. There's still time to save $100.
> Use priority code J8TL2D2.
> http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javao
> ne
> _______________________________________________
> jgap-users mailing list
> jgap-users@...
> https://lists.sourceforge.net/lists/listinfo/jgap-users
>

--- original Nachricht Ende ----


-------------------------------------------------------------------------
This SF.net email is sponsored by the 2008 JavaOne(SM) Conference
Don't miss this year's exciting event. There's still time to save $100.
Use priority code J8TL2D2.
http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone
_______________________________________________
jgap-users mailing list
jgap-users@...
https://lists.sourceforge.net/lists/listinfo/jgap-users

[Florian Hafner]

Manolakis,

unless I am misunderstanding the question, isn't the whole point of the JGAP GA to find the fittest possible solution in the first place? The algorithm should at first quickly and then later slowly produce incrementally better solutions. So if you want a better solution, just let JGAP run faster.

Some of the operators for crossover are very good for quickly converging to better solutions. Other operators including some mutation ones may be better used to fine-tune your results to get even better fitnesses. But the JGAP algorithm should do all of this...

Unless I misunderstood the question..

Florian

On Mon, May 12, 2008 at 11:49 AM, Klaus Meffert <jgap@...> wrote:

Manolakis,

isn't this done by crossing over?
Please notice: it is never guaranteed that a best solution can be found!

Best

Klaus
----- original Nachricht --------

Betreff: [jgap-users]  Fittest Chromosome
Gesendet: So, 11. Mai 2008
Von: manolakis<agnostos_7@...>

>
> Hi there!!!
>
> I was wondering if there is any way after finding a fittest chromosome in a
> population which might not have absolutely perfect fitness to use a GA to
> alter its genes in such a way that we will achieve a better solution.
>
> Thanks for your time
> manolakis
> --
> View this message in context:
> http://www.nabble.com/Fittest-Chromosome-tp17169140p17169140.html
> Sent from the jgap-users mailing list archive at Nabble.com.
>
>
> -------------------------------------------------------------------------
> This SF.net email is sponsored by the 2008 JavaOne(SM) Conference
> Don't miss this year's exciting event. There's still time to save $100.
> Use priority code J8TL2D2.
> http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javao
> ne
> _______________________________________________
> jgap-users mailing list
> jgap-users@...
> https://lists.sourceforge.net/lists/listinfo/jgap-users
>

--- original Nachricht Ende ----

-------------------------------------------------------------------------
This SF.net email is sponsored by the 2008 JavaOne(SM) Conference
Don't miss this year's exciting event. There's still time to save $100.
Use priority code J8TL2D2.
http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone
_______________________________________________
jgap-users mailing list
jgap-users@...
https://lists.sourceforge.net/lists/listinfo/jgap-users

-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2008.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/
_______________________________________________
jgap-users mailing list
jgap-users@...
https://lists.sourceforge.net/lists/listinfo/jgap-users