On Tue, 25 Feb 2014 21:31:33 -0500, Sean Luke <[log in to unmask]> wrote:
>On Feb 25, 2014, at 8:48 PM, Raymond Shpeley <[log in to unmask]>
>> I'm looking into another option that I find easier to wrap my brain around
>> GE. The thing is it's going to require mods to Initializer, Breeder, Evaluator,
>> probably stats if not more. The option is to use permutation trees that in
>> essence act as a virtual population for the known permutations of the data.
>> One instance can create the full range of permutations if selected. The
>> permutations are defined by indices, making crossover easier. In my case all
>> indices should be integers. A permutation tree is atomic to its type (such as
>> timeslot), which forms a natural crossover boundary. It's sort of a
>> leafpile which, as a subtree, can be plugged into other subtrees. Along with
>> permutation tree is a collection which holds the other relevant data
>> by an index value. This is used by reports and possibly stats to find out
>> the heck was being worked on. Currently the permutation tree is a binary
>> since it's easier to work out the selection mechanism with it.
>> So any advice on this one? Do overloading as much as possible? What about
>> the scope of the work? Any particular examples that seem to fit my case?
>There's not much. This is not an ECJ issue, but an EC one: it's a one of you
needing a custom representation for your problem. You'll need to think hard
about how you'd really represent this problem in a way that makes sense from
a breeding point of view. I think the actual ECJ implementation is the least of
Ok, so just dig into it. Yeah, I've got an idea of how breeding should work. I'll
see if it pans out when I get there. Thanks.