# Re: Roulette selection as fuzzy logic??

Earl Cox (ecox@metus.com)
Wed, 16 Jun 1999 15:30:38 +0200 (MET DST)

Fuzzy Logic? Sure, why not! Apparently fuzzy logic has now come to mean
_anything_ that is not absolutely one hundred percent certifiably precise.
So any system that uses fractions, real numbers, interval arithmetic,
proportions, ratios, random numbers, rankings, percentages, or
spin-the-wheel probabilities must be some kind of fuzzy logic. All of us who
spend time writing easily available books about fuzzy logic -- myself, Ron
Yager, George Klir, Bart Kosko, et alia -- should just realize that we have
been wasting our time.

<grumble>
Earl

Matthew Stanfield wrote in message <376668DB.2DD77F2D@Dial.Pipex.com>...
>Hi,
>
>I am writing a music program that -among other things- classifies each CD
>(my CD collection is now almost converted to MP3) into a category
>Jazz/Rock/etc and gives each song a ranking between 1 and 10 (10 is best).
>
>The latest feature will be an autoplay of a particular type of music. A
>list is first created of all the songs within the category. Then a random
>integer is selected between 0 and n, n being the total of each of the
>songs in the list's rankings. Then the rankings total is re-calculated but
>when the random integer is exceeded then that song is chosen to be added
>to the actual play list. Another random integer is then chosen and the
>process repeats until the desired number of songs has been chosen.
>
>This is a form of roulette selection used in genetic algorithms. Each song
>has a chance of being selected for the play list and this is in direct
>proportion to its ranking.
>
>It struck me that this is a kind of de-facto fuzzy logic but I am not
>sure. Is it?
>
>Thanks and regards,
>
>..matthew

############################################################################
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