Re: Typical Genetic Algorithm Example
- From: Erik Max Francis <max@xxxxxxxxxxx>
- Date: Wed, 23 Apr 2008 00:07:03 -0700
sotnet wrote:
Now that you explained, that in case of a bad mutation the offspring
will be thrown away, it does not make any difference!
(I just opposed to claim that mutation in Gray code would results in
small change)
The important point to consider here is that small differences in genotype can result in quite significant differences in phenotype. When people are talking about mutations making small changes, they tend to mean small changes in the genotype, not necessarily small ones in the phenotype. Real biological evolution is so complicated that the distinction tends to be reduced (but not nonexistent); but in artificial examples, the difference tends to be far more pronounced. After all, if you have only a handful of bits of the genotype to mutate, then mutating any given one is likely to result in a very different result in the phenotype (the integral value that bit representation translates to).
--
Erik Max Francis && max@xxxxxxxxxxx && http://www.alcyone.com/max/
San Jose, CA, USA && 37 18 N 121 57 W && AIM, Y!M erikmaxfrancis
Some mistakes we must carry with us.
-- Speaker-to-Animals
.
- References:
- Typical Genetic Algorithm Example
- From: sotnet
- Re: Typical Genetic Algorithm Example
- From: Esmail
- Re: Typical Genetic Algorithm Example
- From: sotnet
- Re: Typical Genetic Algorithm Example
- From: Erik Max Francis
- Re: Typical Genetic Algorithm Example
- From: sotnet
- Typical Genetic Algorithm Example
- Prev by Date: Re: Typical Genetic Algorithm Example
- Next by Date: crossover probability doesn't really matter (w/ 2pt crossover?)
- Previous by thread: Re: Typical Genetic Algorithm Example
- Next by thread: crossover probability doesn't really matter (w/ 2pt crossover?)
- Index(es):
Relevant Pages
|
|