Newsgroups: sci.stat.math,comp.ai.neural-nets,comp.ai.genetic
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!news.mathworks.com!news.kei.com!nntp.coast.net!harbinger.cc.monash.edu.au!news.uwa.edu.au!DIALix!sydney.DIALix.oz.au!quasar!telford
From: telford@threetek.dialix.oz.au (Telford Tendys)
Subject: Re: More fiddling with GA-NN
In-Reply-To: thantos@runic.mind.org's message of Sat, 30 Dec 1995 11:36:09 GMT
Message-ID: <1996Jan3.222733.22531@threetek.dialix.oz.au>
Organization: 3Tek Systems Pty Ltd., N.S.W., Australia
Date: Wed, 3 Jan 1996 22:27:33 GMT
Lines: 14
Xref: glinda.oz.cs.cmu.edu sci.stat.math:8618 comp.ai.neural-nets:29034 comp.ai.genetic:7614

> an interesting way to `speciate' in your environ, if you don't mind the
> /large/ increase in mating time it'll take, is to take the organisms
> you're picking mating partners for and, at the time of the pick,
> rate the other organisms not only in terms of their fitness for the
> task at hand, but `genetic similarity' to the mating organism.

This process sounds a bit like inbreeding.

Many fancy species of pets were bred for show using exactly the techniques
you describe. The breeders could only observe phenotype but have still
managed to generate highly inbred cats, fish, dogs, etc. with all
sorts of bizarre shapes and colours.

	- Tel
