Re: Fuzzy vs. Probability: Just give it to me in plain English

Gleb Beliakov (gleb@maths.mu.oz.au)
Fri, 3 May 1996 13:04:11 +0200


ortech@neosoft.com (Edgar L. Dohmann) wrote:

>
>3. Fuzziness describes event ambiguity -- probability describes event
>occurrence. Whether an event occurs is random. The degree to which it
>occurs is fuzzy.
>
>As an example, consider the range of height from 0 to 12 feet. We might
>say that anything over 7 feet is definitely tall and that anything under 5
>feet is definitely not tall. Therefore anything between 5 feet and 7 feet
>is somewhat tall (i.e. a fuzzy subset).
>
>The degree of belief in the set tall assigned to a particular height, say
>5.5 feet will never change -- it is a function of the particular choice
>(expert experience) in the membership function used to describe our
>somewhat tall membership function.
>
My question is: wherefrom does the expert get the experience to define his/her
membership function? Isn't this experience the statistical data processed
by the brain and returned in the form of knowledge? If not, try to define a
membership function for a problem where you have no experience. For instance, define
a membership function for the "tall" and "short" giraffes.
After you have analysed some particular cases, that is, have accumulated some statistics,
you may however successfully define membership functions.
Isn't our experience a way to represent statistical data?

Gleb