Path: news.mathworks.com!newsfeed-00.mathworks.com!NNTP.WPI.EDU!elk.ncren.net!newsflash.concordia.ca!canopus.cc.umanitoba.ca!not-for-mail
From: roberson@ibd.nrc-cnrc.gc.ca (Walter Roberson)
Newsgroups: comp.soft-sys.matlab
Subject: Re: Neural N/W IP's
Date: Fri, 23 May 2008 20:36:17 +0000 (UTC)
Organization: National Research Council Canada - Conseil national de rechereches Canada
Lines: 27
Message-ID: <g179s1$9cu$1@canopus.cc.umanitoba.ca>
References: <g0v67i$mql$1@fred.mathworks.com> <9ac58a2e-707c-477d-b13f-8afc83538c3c@59g2000hsb.googlegroups.com> <g178gd$a$1@fred.mathworks.com>
NNTP-Posting-Host: origin.ibd.nrc.ca
X-Trace: canopus.cc.umanitoba.ca 1211574977 9630 192.70.172.160 (23 May 2008 20:36:17 GMT)
X-Complaints-To: abuse@cc.umanitoba.ca
NNTP-Posting-Date: Fri, 23 May 2008 20:36:17 +0000 (UTC)
Originator: roberson@ibd.nrc-cnrc.gc.ca (Walter Roberson)
Xref: news.mathworks.com comp.soft-sys.matlab:470105


In article <g178gd$a$1@fred.mathworks.com>,
hozefa Patrawala <hozefa_pat@hotmail.com> wrote:

>What I want is a neural network, in which each neuron
>responds to a value of my matrix 

>i.e say first element of my matrix is given to first neuron
>and second element of the matrix given to second neuron and
>so on and neuron should be on or off depending on the threshold.

>How can i implement tht ??

Well, I suppose you could do that, but it doesn't sound like a
useful application of neural networks to me. Neural networks are
supposed to allow the neurons to affect each other, to allow
feedback corelations can develop between the neurons, so that the
network as a whole detects a pattern. You are asking for each
neuron to be independant. Instead of using a neural net matrix,
of however many elements, N by M, you might as well just use 
(N * M) independant neural networks each with a single input
and output.

-- 
  "Let me live in my house by the side of the road --
   It's here the race of men go by.
   They are good, they are bad, they are weak, they are strong
   Wise, foolish -- so am I;"                 -- Sam Walter Foss