Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!bb3.andrew.cmu.edu!newsfeed.pitt.edu!gatech!swrinde!howland.reston.ans.net!newsfeed.internetmci.com!in1.uu.net!bcstec!nntp
From: Mike Fouche <mikef@hsvaic.hv.boeing.com>
Subject: Re: GA for learning in ANN
X-Nntp-Posting-Host: e570254.hv.boeing.com
Content-Type: text/plain; charset=us-ascii
Message-ID: <DqsHK5.58H@bcstec.ca.boeing.com>
To: 76743.1740@CompuServe.COM
Sender: nntp@bcstec.ca.boeing.com (NNTP News Access)
Content-Transfer-Encoding: 7bit
Organization: Missiles & Space Division
References: <DqoyKy.L52@bcstec.ca.boeing.com> <4ma7er$g3k$1@mhadf.production.compuserve.com>
Mime-Version: 1.0
Date: Thu, 2 May 1996 17:50:28 GMT
X-Mailer: Mozilla 1.2 (Windows; U; 16bit)
Lines: 13

Hello,

Although I'd like to be able to share the method it wouldn't be in 
Boeing's best interest at the current time.  However, what I've done
in the past is generate neural nets for a given set of data that is
sent to me (usually via email) and return the neural nets to the owner of 
the data.  This saves the "owner" a lot of time in terms of training,
and cuts down on the time it takes to determine an adequate architecture.
After that, the owner can generate his/her own nets using other methods.
Or if we are collaborating on something we continue to generate the nets.

Mike Fouche  

