Newsgroups: comp.ai.genetic
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!uhog.mit.edu!news.mtholyoke.edu!news.umass.edu!umassd.edu!umassd!s_vogt
From: s_vogt@umassd.cis.umassd.edu (Stefan Vogt)
Subject: Q: GA & ANN design
Message-ID: <D7719F.Gw9@umassd.edu>
Sender: usenet@umassd.edu (USENET News System)
Organization: University of Massachusetts Dartmouth
X-Newsreader: TIN [version 1.2 PL2]
Date: Mon, 17 Apr 1995 19:10:26 GMT
Lines: 67


Hi,

I've read two papers about artificial neural network design with genetic
algorithms (see below).

My questions related to that are:

 * To find the fitness (qualtity) of an coded ANN (member) I have to
   train a network. Neither training for n epoches nor training until
   a desired error is met, gives a comparable measurment of the
   network fitness.

 * How much time does the GA need? How many ANN do I have train? to
   get good results for a specific problem. Is this practical for
   real-world applications with bigger nets than in the papers?

Thanx for your help!

After all I think the GA approach for ANN gives a nice design method,
if no a priori knowledge is available.

Bye, Steff

@inproceedings{BKHS93,
  author        ="Boers, E.J.W.  and Kuiper, H.  and Happel,
		  B.L.M. and Sprink huizen-Kuyper, I.G.", 
  booktitle     ="Proceedings of Computing Science in The Netherlands",
  title         ="{D}esigning modular artificial neural networks",
  year          ="1993",
  abstractURL   ="http://www.wi.leidenuniv.nl/TechRep/tr93-24.html",
  address       ="SION, Stichting Mathematisch Centrum",
  documentURL   ="file://ftp.wi.LeidenUniv.nl/pub/CS/TechnicalReports/1993/tr93
-24.ps.gz",
  editor        ="Wijshoff, H.A. ",
  pages         ="87--96",
}
@InProceedings{AAT93,
  author = 	 "E.~Alba and J~F.~Aldana and J.~M.~Troya",
  title = 	 "Full automatic ANN design: A genetic approach",
  editor =	 "Jose Mira and Joan Cabestany and Alberto Prieto",
  pages =	 "399--404",
  booktitle =	 "New trends in neural computing: International
		  workshop on artificial neural networks (IWANN '93),
		  Sitges, Spain",
  year =	 1993,
  publisher =	 "Springer-Verlag",
  address =	 "New York",
  month =	 "June",
}
 
                                           -----------------------------
                                           "Good news is just life's way
                                            of keeping you off balance."


!#@$%#^$%^*&^%*$%^&(+~$#^@&)*%&%^%#@^*)^#@!$&*(?<|+),&%^$@$(_*_-\|?,<#@^%

Stefan Vogt                            http://www.cis.umassd.edu/~s_vogt/
Cedar Dell 5357                        August-Knabe-Weg 4
UMass Dartmouth                        59494 Soest
North Dartmouth, MA 02747-2300         Germany
+ (508)-990-9190                       +49 (2921)-62244
s_vogt@cis.umassd.edu                  s_vogt@ira.uka.de



