Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!bb3.andrew.cmu.edu!nntp.sei.cmu.edu!news.cis.ohio-state.edu!math.ohio-state.edu!howland.reston.ans.net!newsfeed.internetmci.com!in1.uu.net!news.interpath.net!sas!newshost.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: Fuzzy RULES in FUZZY ART???
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <DsnLCy.M92@unx.sas.com>
Date: Fri, 7 Jun 1996 23:31:46 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References: <4ok8f7$c0q@brachio.zrz.TU-Berlin.DE> <31AF202E.41C67EA6@escmail.orl.mmc.com> <DsE5KI.2v3@unx.sas.com> <rsjohnso-0606960329570001@vixen.cso.uiuc.edu>
Organization: SAS Institute Inc.
Lines: 31


In article <rsjohnso-0606960329570001@vixen.cso.uiuc.edu>, rsjohnso@students.uiuc.edu (Me2) writes:
|> In article <DsE5KI.2v3@unx.sas.com>, saswss@hotellng.unx.sas.com (Warren
|> Sarle) wrote:
|> 
|> >In article <31AF202E.41C67EA6@escmail.orl.mmc.com>, Gregory Harrison
|> <harrison@escmail.orl.mmc.com> writes:
|> >|> I would consider that the application of fuzzy theory to Fuzzy ART
|> >|> and to the ARTa side of a Fuzzy ARTMAP system deals primarily with the
|> >|> acqusition and comparison of patterns whose members can contain
|> >|> fuzzy values (i.e. falling in the range between 0 and 1).
|> >
|> >True. But by that reasoning, any garden-variety "backprop" net is
|> >a neurofuzzy net.
|> 
|> And your point?  Are you criticising Gregory Harrison or Gail
|> Carpenter/Stephen Grossberg?

If I read myself correctly, I was agreeing with Gregory Harrison.  And I
don't see any criticism of Carpenter, Grossberg, et al. above, but if
you really want one, here goes: the term "fuzzy" in "Fuzzy ART" is pure
hype, since Fuzzy ART is no fuzzier than a typical backprop net and
Fuzzy ART does not even yield fuzzy classifications like fuzzy c-means.
If that's not enough criticism, see "Why Statisticians Should Not FART"
in ftp://ftp.sas.com/pub/neural/fart.doc .

-- 

Warren S. Sarle       SAS Institute Inc.   The opinions expressed here
saswss@unx.sas.com    SAS Campus Drive     are mine and not necessarily
(919) 677-8000        Cary, NC 27513, USA  those of SAS Institute.
