Newsgroups: comp.ai.neural-nets,comp.ai.genetic,comp.ai.alife
Path: cantaloupe.srv.cs.cmu.edu!bb3.andrew.cmu.edu!newsfeed.pitt.edu!scramble.lm.com!news.math.psu.edu!news.cse.psu.edu!uwm.edu!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: <DqzBM9.6u0@bcstec.ca.boeing.com>
Sender: nntp@bcstec.ca.boeing.com (NNTP News Access)
Content-Transfer-Encoding: 7bit
Organization: Missiles & Space Division
References: <4m2njb$btc@malibu.unice.fr> <DqoyKy.L52@bcstec.ca.boeing.com> <4maejc$ki7@gjallar.daimi.aau.dk>
Mime-Version: 1.0
Date: Mon, 6 May 1996 10:25:20 GMT
X-Mailer: Mozilla 1.2 (Windows; U; 16bit)
Lines: 16
Xref: glinda.oz.cs.cmu.edu comp.ai.neural-nets:31426 comp.ai.genetic:8665 comp.ai.alife:5561

Hello again :),

I certainly didn't want to give the impression that we had the *best*
learning algorithm but ... it works the best of anything I've seen so
far.  In terms of applications we've applied it to: spacecraft reetry
closed-loop guidance, target-interceptor guidance, closed-loop control,
x-ray weld fault detection (image processing), protein crystal growth 
classification (image processing), aerodynamic parameter estimation, etc.
It works well across these applications and has saved us a lot of time
in terms of training and network architecture design.

Like other algorithms it has its problems but we never seem to get very 
close to the areas where they exist.  So ... we're content for now!

Mike Fouche

