Thread Subject: Neural N/W IP's

I have two matrix, Which i need to give to neurons and based
on the threshold, it should be on or off.
Each value of matrix is given to one neuron and i am
planning to use sigmoid function for threshold.
How should i start ??

On May 20, 2:45 pm, "hozefa Patrawala" <hozefa_...@hotmail.com> wrote:
> I have two matrix, Which i need to give to neurons and based
> on the threshold, it should be on or off.
> Each value of matrix is given to one neuron and i am
> planning to use sigmoid function for threshold.
> How should i start ??

1.Read the documentation

doc newff

2. Read my post on training advice

3. Reply with a more detailed statement of your problem
and an indication of whay you do and do not understand.

Hope this helps.

Greg

Greg Heath <heath@alumni.brown.edu> wrote in message
<9ac58a2e-707c-477d-b13f-8afc83538c3c@59g2000hsb.googlegroups.com>...
> On May 20, 2:45 pm, "hozefa Patrawala"
<hozefa_...@hotmail.com> wrote:
> > I have two matrix, Which i need to give to neurons and based
> > on the threshold, it should be on or off.
> > Each value of matrix is given to one neuron and i am
> > planning to use sigmoid function for threshold.
> > How should i start ??
>
> 1.Read the documentation
>
> doc newff
>
> 2. Read my post on training advice
>
> 3. Reply with a more detailed statement of your problem
> and an indication of whay you do and do not understand.
>
> Hope this helps.
>
> Greg


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 ??

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