Re: Adding more evidence


Subject: Re: Adding more evidence
From: Larry Serflaten (serflaten@usinternet.com)
Date: Sat Jan 22 2000 - 12:52:00 MET


I would have to take exception with your second calculation. My
calculations follow:

IF OutsideGreen AND InsideRed THEN Watermellon

It looks to me like both conditions must be true, and both have a 50%
chance of being the correct value to pass the test. In other words,
not knowing anything, there is a (.5 * .5) 25% chance that any friut we
pick up will be the watermellon. (This results from limiting the universe
of fruits to only 4 different kinds as was done by the AND expression)

If we know that there is a 60% chance that the one of the tests will pass
then that changes the equation: .6 * .5 or, 30% chance that we have the
watermellon.

After that, if the other fact has a 40% chance of being the correct value,
that yeilds a different equation: .6 * .4 or, 24% chance.

When you increase the chance that one of the facts would be true, you
obviously increase the outcome in that favor. I did not understand
how you could change the probability of one of the operands, and still
have the same probability for the result.

The first test you gave, removed one of the operands completely:

IF OutsideGreen THEN Watermellon

That really alters the equation, reducing it to that single value. (.6)

When you add in new evidence, your 40% factor, you return the equation to
two operands:
 
IF OutsideGreen AND InsideRed THEN Watermellon

Using a different equation, .6 * .4 (24%)
 
Not knowing anything about it, gives you a 25% chance, and after all the facts
are collected you get a 24% chance.

By my calculations, after adding the evidence, he has actually decreased his
possibility of finding the watermellon by 1%

The variable that is fuzzy here is the number of tests you're going to apply.

If you have a URL/reference to implementing fuzzy logic in (Visual) Basic, I
would enjoy the read....

LFS

Will Dwinnell wrote:
>
> Kami ROUSSEAU wrote:
> "For my M.Sc. in computer science, my subject is the development of an
> expert system. I wanted to use fuzzy logic, but my director said that fuzzy
> rules do not take added evidence into account. Here is the exemple that he
> gave me:
> (assume that the AND operator is defined as "maximum")
> IF outsideIsGreen AND insideIsRed THEN objectIsWatermelon
>
> Suppose we only have 1 fact:
> a certain fruit's outside is 60% green.
> we can conclude that the fruit is a watermelon with possibility 60%
>
> Suppose we add the following evidence:
> the fruit's inside is red at 40%.
> after recomputing the truth value of the rule, we still get 60%.
>
> My director says that the possibility should have increased, but it did not,
> so fuzzy logic is not appropriate for this kind of reasoning.
>
> What do you think of his argument?"
>
> It assumes very simplistic (and strange) rules. A fuzzy system like this
> involves both rules and facts. His rules are obviously of the form "IF
> antecedent is X true, THEN conclusion is X true". Besides, fuzzy logic is
> not limited to min/max operators. See Earl Cox's first book on fuzzy logic
> for a slew of alternatives.
>
> Will Dwinnell
> predictor@compuserve.com

############################################################################
This message was posted through the fuzzy mailing list.
(1) To subscribe to this mailing list, send a message body of
"SUB FUZZY-MAIL myFirstName mySurname" to listproc@dbai.tuwien.ac.at
(2) To unsubscribe from this mailing list, send a message body of
"UNSUB FUZZY-MAIL" or "UNSUB FUZZY-MAIL yoursubscription@email.address.com"
to listproc@dbai.tuwien.ac.at
(3) To reach the human who maintains the list, send mail to
fuzzy-owner@dbai.tuwien.ac.at
(4) WWW access and other information on Fuzzy Sets and Logic see
http://www.dbai.tuwien.ac.at/ftp/mlowner/fuzzy-mail.info
(5) WWW archive: http://www.dbai.tuwien.ac.at/marchives/fuzzy-mail/index.html



This archive was generated by hypermail 2b25 : Thu Apr 06 2000 - 15:59:39 MET DST