Newsgroups: sci.stat.math,comp.ai.fuzzy
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!Germany.EU.net!Munich.Germany.EU.net!thoth.mch.sni.de!news.sni.de!uni-paderborn.de!urmel.informatik.rwth-aachen.de!newsserver.rrzn.uni-hannover.de!news
From: mackw@bytex.com
Subject: Re: Fuzzy theory or probability theory? 
Content-Type: TEXT/PLAIN; charset=US-ASCII
Message-ID: <1994Dec1.145728.7877@newsserver.rrzn.uni-hannover.de>
Sender: news@newsserver.rrzn.uni-hannover.de (News Service)
Organization: RRZN
X-Newsreader: NEWTNews & Chameleon -- TCP/IP for MS Windows from NetManage
References: <3bdcgn$15jm@hearst.cac.psu.edu>
     
Mime-Version: 1.0
Date: Thu, 1 Dec 1994 16:21:04 GMT
Lines: 41
Xref: glinda.oz.cs.cmu.edu sci.stat.math:3418 comp.ai.fuzzy:3507


In article <3bdcgn$15jm@hearst.cac.psu.edu>, <caj@jerry.psu.edu> writes:
> I personally have never attempted to estimate a chance probability 
using
> fuzzy logig theory.  Those that do, do not have my support.

Let me agree with Mr. Janes; anyone who uses fuzzy logic to play hands 
in poker, please contact me immediately, I have some Christmas shopping 
to do ;-)  Now, I would like to address this discussion from the view 
point of an engineer who tries to make use of both fuzzy theory and 
probability theory.

Fuzzy theory and probability theory are different things.  They may 
overlap, but still they address different types of situations.  As an 
analogy compare geometry and calculus.  Both are used to find area, but 
I would not use geometry to find the area under a complex curve nor use 
calculus to find the area within a complex shape.  I *could* do either, 
but why would I want to?

I find statistics and probability extremely useful in describing the 
distribution of a characteristic throughout a population and defining 
the liklihood that one item will have a specific value of this 
characteristic.

I find fuzzy logic extremely useful in applying a metric to a conceptual 
characteristic.  When working with concepts, fuzzy logic allows the 
transformation into a form which can be handled by mathmatics.  How else 
can I compare, combine, or manipulate concepts such as "redness," 
"roundness," or "tallness?"

There are also some areas which fall into the middle ground.  In these 
cases it may be equally as valid to assign a probability of membership 
as to assign a degree of membership.  In these cases, it doesn't matter 
which set of tools are applied to the problem.  Use whatever you are 
personally most comfortable with.

In short, it is not "fuzzy theory (exclusive) or probability theory," 
but "fuzzy logic *and* probability theory."

Wayne Mack

