Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!bb3.andrew.cmu.edu!nntp.sei.cmu.edu!news.psc.edu!wink.radian.com!gatech!news.mathworks.com!newsgate.duke.edu!interpath!news.interpath.net!news.interpath.net!sas!newshost.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: representing inequalities in NN
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <E6yACn.8z@unx.sas.com>
Date: Wed, 12 Mar 1997 21:57:59 GMT
X-Nntp-Posting-Host: hotellng.unx.sas.com
References:  <33252A8D.41C6@mh.uk.sbphrd.com>
Organization: SAS Institute Inc.
Lines: 23


In article <33252A8D.41C6@mh.uk.sbphrd.com>, Mike Tennant <tennant@mh.uk.sbphrd.com> writes:
|>      is it possible to represent a set of inequalities using any NN
|> techniques? I want to solve a large set of equations of the form 
|> Ax(1) + Bx(2) + ... + Nx(N) =  some value
|> Ax'(1) + Bx'(2) + ... + Nx'(N) < that value

Yes, see:
 
   Cichocki, A. and Unbehauen, R. (1993). Neural Networks for
   Optimization and Signal Processing. NY: John Wiley & Sons, ISBN
   0-471-930105 (hardbound), 526 pages, $57.95.

But why not just use some standard method from numerical analysis,
such as linear programming, for which software is widely available?

-- 

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.
 *** Do not send me unsolicited commercial or political email! ***

