Forums before death by AOL, social media and spammers... "We can't have nice things"
|    comp.ai.fuzzy    |    Fuzzy logic... all warm and fuzzy-like    |    1,275 messages    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
|    Message 760 of 1,275    |
|    Dmitry A. Kazakov to Carmel    |
|    Re: complex rules    |
|    19 Feb 08 09:40:41    |
      b83d6fb7       From: mailbox@dmitry-kazakov.de              On Mon, 18 Feb 2008 02:05:03 -0800 (PST), Carmel wrote:              > I am trying to build a machine that should be able to process fuzzy       > rules with complex antecedents of the type       >       > If (A is a and B is b) or (C is c) then D is d       >       > or similar. At the moment I am considering only simple consequents.       >       > I am thinking about processing the antecedent bit in an RPN like       > processor that will be able to handle operators like AND, OR, NOT and       > possibly fuzzy hedges.       >       > Is someone aware of similar implementations and if there is some       > material where this problem was investigated?              I have an implementation of an extended variant of the fuzzy control       language which has similar rules with and, or, xor, not, in, not in etc.       The extension is intuitionistic. The rules are compiled into a training       set. The set is trained on to create a classifier. The classifier does       inference.              I am not sure which problem you refer to. Nested expressions like (x and y)       or z? I convert the rules into a conjunctive normal form using de Morgan's       rules. The right parts are converted to a disjunctive normal form,       disjuncts become independent rules.              --       Regards,       Dmitry A. Kazakov       http://www.dmitry-kazakov.de              --- SoupGate-Win32 v1.05        * Origin: you cannot sedate... all the things you hate (1:229/2)    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
(c) 1994, bbs@darkrealms.ca