Newsgroups: comp.ai.genetic
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!europa.eng.gtefsd.com!howland.reston.ans.net!news.sprintlink.net!EU.net!sun4nl!news.nic.surfnet.nl!utciva.civ.utwente.nl!usenet
From: "Albert van Breemen" <s9101799@mail.student.utwente.nl>
Subject: About Hollands book 'Adaptation in ...'
Message-ID: <71639.s9101799@mail.student.utwente.nl>
X-Minuet-Version: Minuet1.0_Beta_17A
Sender: usenet@Utwente.NL ((UT-utciva)USENET News System)
X-Popmail-Charset: English
Reply-To: <a.j.n.vanbreemen@student.utwente.nl>
Organization: University of Twente, Enschede, The Netherlands
Date: Mon, 28 Nov 1994 22:46:22 GMT
Lines: 47

Introducing me: Albert van Breemen, student with the Department of Electrical 
                Engineerinf, University of Twente, the Netherlands
Interest:       AI, at the moment specially GA

Problem:

I've read the most of Hollands book 'Adaptation in natural and 
artificial systems'. While reading the book the following question 
did arise: GA works only good if their is some correlation between f(c) and
c, with c a structure of A. If their is no correlation then the search is
just random (This is just mine opinion which I have not proved or neither 
I've read any prove, but I want this to prove mathematicaly soon). If their 
is some correlation then I mean:

        Take f(c0) as een global optimum of. If f(c) is 'close' (euclidian)
        to f(c0), then c MUST be close to c0. This distance between c0 and
        c I have defined as de number of different atributes at the same
        positions of c and c0. Example: the distance between 00100101 and
        10100101 is 1.

I cannot find a formal definition in the book of this. Does anyone know about 
some paper or book witch describe this?
Wel their is also a dependance between atributes of a structure. An example:

        We want to optimize f(c)=f(x,y)=x*y, with x=[-100,100] and 
        y=[-100,100], c=(x,y). The schema h=(*,97) is only a good schema
        if x>0, otherwise solution of h=(*,97) and x<0 will be negative (f<0).

The only thing I've read about this in the book is given in chapter 8 'Adap-
tation of Codings and Representation". Holland introduce a 'broadcast 
language" to increase the correlation between f(c) and c. What I doesnot read
is if this works. Their are no simulation of this. Does anyone know if the
'broadcast language' works with GA and has someone done some experiments 
with it? Mayby their are some papers or books about this?

Thanx



================================================
A.J.N. van Breemen
lipperkerkstr 128
7511 DD  ENSCHEDE, The Netherlands
tel: 053-317819
email: a.j.n.vanbreemen@student.utwente.nl
================================================
       
