Path: news.mathworks.com!newsfeed-00.mathworks.com!newscon02.news.prodigy.net!prodigy.net!news.glorb.com!postnews.google.com!n60g2000hse.googlegroups.com!not-for-mail
From:  Greg Heath <heath@alumni.brown.edu>
Newsgroups: comp.soft-sys.matlab
Subject: Re: classification using ANN
Date: Fri, 06 Jul 2007 16:39:52 -0700
Organization: http://groups.google.com
Lines: 14
Message-ID: <1183765192.890585.57060@n60g2000hse.googlegroups.com>
References: <ef5c9e0.-1@webcrossing.raydaftYaTP>
NNTP-Posting-Host: 68.32.133.5
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
X-Trace: posting.google.com 1183765193 3816 127.0.0.1 (6 Jul 2007 23:39:53 GMT)
X-Complaints-To: groups-abuse@google.com
NNTP-Posting-Date: Fri, 6 Jul 2007 23:39:53 +0000 (UTC)
In-Reply-To: <1183705534.066599.128590@e9g2000prf.googlegroups.com>
User-Agent: G2/1.0
X-HTTP-UserAgent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; AT&T CSM6.0; AT&T CSM 6; (R1 1.3); .NET CLR 1.0.3705),gzip(gfe),gzip(gfe)
Complaints-To: groups-abuse@google.com
Injection-Info: n60g2000hse.googlegroups.com; posting-host=68.32.133.5;
Xref: news.mathworks.com comp.soft-sys.matlab:417684



On Jul 6, 3:05 am, Srikanth <s...@xdtech.com> wrote:
> Nope, I don't have any code as such... any NN book would give you some
> algorithm (Greatest descent algo. is an easy one), or since you know
> there are two groups, you could use a mean feature vector algorithm.
> However, having more than 2 hidden layers makes the system extremely
> complex, and I doubt it would be worth the effort in any system.

Having more than 1 hidden layer is seldom
necessary. See the comp.ai.neural-nets FAQ.

Hope this helps.

Greg