Path: news.mathworks.com!newsfeed-00.mathworks.com!nlpi057.nbdc.sbc.com!prodigy.net!news.glorb.com!postnews.google.com!g38g2000yqd.googlegroups.com!not-for-mail
From: Greg Heath <heath@alumni.brown.edu>
Newsgroups: comp.soft-sys.matlab
Subject: Re: Neural Networks and Genetic Algorithm
Date: Thu, 12 Feb 2009 20:41:11 -0800 (PST)
Organization: http://groups.google.com
Lines: 21
Message-ID: <43c9447b-2b6b-410e-860b-a13d4a4ce9f0@g38g2000yqd.googlegroups.com>
References: <gmv4mt$bi6$1@fred.mathworks.com>
NNTP-Posting-Host: 68.39.98.10
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
X-Trace: posting.google.com 1234500071 31400 127.0.0.1 (13 Feb 2009 04:41:11 GMT)
X-Complaints-To: groups-abuse@google.com
NNTP-Posting-Date: Fri, 13 Feb 2009 04:41:11 +0000 (UTC)
Complaints-To: groups-abuse@google.com
Injection-Info: g38g2000yqd.googlegroups.com; posting-host=68.39.98.10; 
	posting-account=mUealwkAAACvQrLWvunjg50tRAnsNtJR
User-Agent: G2/1.0
X-HTTP-UserAgent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; GTB5; 
	Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; .NET CLR 1.1.4322; 
	.NET CLR 2.0.50727; .NET CLR 3.0.04506.30; Seekmo 10.0.341.0),gzip(gfe),gzip(gfe)
Xref: news.mathworks.com comp.soft-sys.matlab:518019


On Feb 11, 1:17=A0pm, "zaheer ahmad" <ahmad.zah...@yah00000.com> wrote:
> Hi All of You
> How to optimize Feed ForwardNeuralNetwork output using Genetic Algorithm =
instead of backpropagation Algorithm. i.e. to used GA for weights optimizat=
ion.
> A small Matlab code will help me alot
> thanks

Genetic algorithms are seldom used to find
weights because they take too long. However,
they are used to find network topology. For
a given topology, weights are found via backprop.

Try GOOGLE GROUP searching in the archives of
comp.ai.neural-nets as well CSSM.

Try GOOGLE WEB searching in Citeseer and Neuroprose.

Hope this helps.

Greg