🚀 go-pugleaf

In article <2624@blue.cis.pitt.edu> genetic+@pitt.edu (David M. Tate) writes:

   chang@pecan.cns.udel.edu (Liang-Wen Chang) said:

   >I haven't figured
   >out the statistic nature of such variable radius w.r.t. particular
   >encoding.  The recent 'uniform crossover' method is more of multi-bit
   >mutation than crossover.  

   Not at all.  Mutation is disruptive, replacing alleles from the parents with
   alleles that do *not* occur in either parent.  Uniform crossover is perfectly
   conservative, recombining alleles from the parents.  Just because it doesn't
   use *contiguous* alleles from one parent doesn't make it "multi-bit
   mutation". There's not necessarily anything sacred about the particular
   sequence the genes are encoded in.

   As I see it, the role of breeding (be it crossover or some other operator) is
   to rearrange alleles you've got hanging around already, and the role of 
   mutation is to introduce (or re-introduce) alleles you'd *like* to have
   around, but don't.  Viewed this way, uniform crossover is clearly unlike
   mutation, and clearly like crossover.

I think you're pretty close here.  Its more a matter of _conservation_ of
genetic material in crossover.  Crossovers _preserve_ all of the genetic
material that came into the operator so that you can find all of the material
represented somewhere in the offspring after the operator.  However, mutation
does not preserve this criterion of conservation.  Heuristic: if you've got an
operator that doesn't conserve the genetic material, its not crossover but a
form of mutation, regardless of what else it does.  Notice that this doesn't go
the other direction, i.e. just because all genetic material is preserved
doesn't mean its crossover, it could be inversion.  But uniform crossover is
clearly NOT mutation.

-pete angeline

-------------------------------------------------------------------------------
Peter J. Angeline            ! Laboratory for AI Research (LAIR)
Graduate Research Assistant  ! THE Ohio State University, Columbus, Ohio 43210
ARPA: pja@cis.ohio-state.edu ! "Nature is more ingenious than we are."



-- 
-------------------------------------------------------------------------------
Peter J. Angeline            ! Laboratory for AI Research (LAIR)
Graduate Research Assistant  ! THE Ohio State University, Columbus, Ohio 43210
ARPA: pja@cis.ohio-state.edu ! "Nature is more ingenious than we are."