Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!udel!gatech!news.sprintlink.net!redstone.interpath.net!sas!mozart.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Fuzzy ART?
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <DB9oxF.5D3@unx.sas.com>
Date: Wed, 5 Jul 1995 23:51:15 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
Organization: SAS Institute Inc.
Lines: 21


Has anybody ever tried Fuzzy ART on 2-dimensional inputs and then
plotted the results to see what they look like? I am getting bizarre
results. For example, try these data with 5 cases and 2 inputs with
complement coding, fast learning (beta=1), conservative limit
(alpha=1e-6), and a vigilance (rho) of 0.5:

    .1 .5
    .9 .5
    .5 .8
    .5 .2
    .5 .5

Do you get category 1 in two disconnected pieces? Does this make any
sense???

-- 

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.
