Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!udel!gatech!swrinde!cs.utexas.edu!news.sprintlink.net!redstone.interpath.net!sas!mozart.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: variable elimination
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <D5r9z7.18K@unx.sas.com>
Date: Mon, 20 Mar 1995 20:23:31 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References: <D5K0KK.FGL@unx.sas.com> <NEWTNews.5843.795623315.RoboNet@Bud_The_King_of_Beers.ibm.net>
Organization: SAS Institute Inc.
Lines: 34


In article <NEWTNews.5843.795623315.RoboNet@Bud_The_King_of_Beers.ibm.net>, RoboNet@pop03.ny.us.ibm.net writes:
|>
|> There is a simpler method....to this problem....
|>
|>
|> >   I am seeking a little advice, if anyone out there can help me.  I am
|> >   interested in applying neural nets to a problem in which I have more than
|> >   100 predictor/independent variables (inputs) but I know that probably
|> >   only 12 or so are really necessary.
|> >
|> >   Once I make a neural net, how can I go about determining which inputs are
|> >   unnecessary?  Can I rank them in importance?  Basically I am wishing that
|> >   there is some way, even a primitive unreliable way, to get the equivalent
|> >   of the coefficients and t-tests that you get with linear regression.
|>
|>
|> >>> Since there will usually be more than one weight associated with each
|> >>> input, you will have an F test rather than a t test.
|>
|>
|> Solution:=
|>
|> For those interested in eliminate un-neccsary inputs I would first try using a
|> Hinton Diagram to represent your Neural Net ... and then look for those inputs
|> with smallest weight values...

That method would indeed qualify under the "primitive unreliable" clause.

-- 

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.
