Newsgroups: comp.ai.fuzzy
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!pipex!uunet!zib-berlin.de!uni-paderborn.de!urmel.informatik.rwth-aachen.de!newsserver.rrzn.uni-hannover.de!news
From: mackw@bytex.com
Subject: Fuzzy Processors
Content-Type: TEXT/PLAIN; charset=US-ASCII
Message-ID: <1994Dec8.135332.25215@newsserver.rrzn.uni-hannover.de>
Sender: news@newsserver.rrzn.uni-hannover.de (News Service)
Organization: RRZN
X-Newsreader: NEWTNews & Chameleon -- TCP/IP for MS Windows from NetManage
References: <D0ECLF.17J@hasler.uucp>
     
Mime-Version: 1.0
Date: Thu, 8 Dec 1994 15:36:14 GMT
Lines: 25


In article <D0ECLF.17J@hasler.uucp>, <root@hasler.uucp> writes:
> Wojtech Bourbaki writes:
> > How is a fuzzy chip different from a regular chip?
> None.  It's just an Intel Pentium executing FDIV instructions. :) :) :)

Actually, it depends on the chip.  

Omron Corp. produces a digital fuzzy processor (FP-3000), which I believe 
implements fuzzy operations as the basic instruction set (ie. internally 
microcoded) and operates as an external peripheral to a standard 
microprocessor, much like a math coprocessor or an ADC (analog to digital 
converter circuit).

Other approaches have implemented fuzzy processors as analogue 
processors.  Here, I believe, degree of truth is represented by voltage 
levels instead of a numeric value.

These differences are primarily internal and externally should appear 
similar, except for possible differences in speed and precision.

Has anyone worked with any fuzzy chips who could provide some more info?

Wayne Mack

