Jan, I would advise not using the PSO module. I don't trust it yet.
It's next on our list of revisions and fixes but that's not going to
get underway for another week or two at the *earliest*.

If you absolutely need a good PSO framework, I strongly suggest this
one:

http://www.particleswarm.info/standard_pso_2007.c

This is a benchmark pso implementation. Unfortunately it's not in C.

Alternatively you could have a hand in examining and revising the PSO
code in ECJ :-)

Sean

On Jul 30, 2010, at 1:23 PM, Jan-Hendrik Fischer wrote:

> On Wed, 4 Mar 2009 09:51:17 -0500, Sean Luke <[log in to unmask]> wrote:
>
>> A quick note on PSO implementation in ECJ: it's got lots and lots of
>> problems. Don't use it. I wrote a new version of PSO that actually
>> works while at FOGA, but accidentally deleted it yesterday, along
>> with
>> other changes, before committing them. :-( :-( I'm fairly down
>> about
>> that. Until I get that rewritten, I suggest avoiding it.
>
>
> Hey Sean,
>
> is that info up-to-date? I didn't find much in the changelogs on PSO
> and since
> my grades for this project are relying on the results I get from
> ECJ, it's
> important for me to choose the right PSO-framework. :-) Our supervisor
> recommended ECJ, my teammates, who implement the genetic programming
> stuff, are quite pleased, but I can't find much introductory
> material on PSO.
>
> Would you recommend using ECJ-PSO for a hard MLCLSP? Or is it just not
> ready?
>
> Would be great if you could help me!
>
> Sincerely
> Jan-Hendrik
>