Re: Adaptative fuzzy systems and classification

david_olmsted@my-dejanews.com
Mon, 21 Sep 1998 20:44:13 +0200 (MET DST)

In article <32D6847A.9A97A1BA@kant.dcs.fi.uva.es>,
fuzzy-mail@dbai.tuwien.ac.at wrote:
> Hello:
> Im making my end of career project about using adaptative fuzzy
> systems in classification tasks.
> I had to implement the Algorithm of Dr. Li Xin Wang "Training of fuzzy
> logic systems using a table-lookup scheme" as it comes in his book
> "Adaptative
> fuzzy systems and control. Design and stability analysis".
> The algorithm is originaly designed to be used as a fuzzy controler,
> but Im tryng to use it in classification.
> The training data is numerical and has the output class information
> codified in a "1 of n" way. I tried using one output space for each
> class
> with one only fuzzy set in each one, and with two,(I use a triangular
> membership
> function), but it doesnt work very well. Does somebody have a better
> idea? What kind of input-output, fuzzy sets and membership function
> configuration
> can i use?
>
> thanks to everybody:
> Javi
>
> ############################################################################
> 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
>
>
Javi,

Using multivalued logic instead of fuzzy logic will solve your problem since
multivalued logic has a fundamental level conditional operation where fuzzy
logic does not. For an example of a multivalued logic circuit used in pattern
classification see the circuit proposed for the tectum at
http://www.neurocomputing.org

sincerely,
David Olmsted

-----== Posted via Deja News, The Leader in Internet Discussion ==-----
http://www.dejanews.com/rg_mkgrp.xp Create Your Own Free Member Forum

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