Hi,
I think you should read more about ANN, in order to put it to work
well you need some theoretical foundation.
The .net file saves your NN, so you can train it and save it so later
you can load it to be used again.
To define all the Inputs and Outputs you can use the following function:
struct fann *ann = fann_create_standard(num_layers, num_input,
num_neurons_hidden, num_output);
But I advise you to read a bit more at FANN website. The tutorials and
references are well described and easy to understand.
Play a bit with examples...
About the hidden neurons:
"The hidden layers connect the input and the output layers: in our
case, we will use only one hidden layer, which can have as much hidden
neurons as the user wants.
The number of hidden neurons has to be carefully specified, as the
level of abstraction, the speed and the learning capability depend on
this value.
Over-fitting is a common error when using ANNs where the number of
hidden neurons is overestimated, which degrades the generalization
capability."
Br,
Fábio
On Sun, Oct 10, 2010 at 6:06 PM, Gurumurti Maharana <
Post by Gurumurti MaharanaHi All ,
If I have to draw a NN diagram which we get in the .net file after
training. How can we go about ? Can any one explain for the XOR problem ?
basically how we draw all the I/P and O/P s in the NN?
What to do with the hidden neuron ?
Thanks with Regards.
--
Gurumurti L Maharana
------------------------------------------------------------------------------
Beautiful is writing same markup. Internet Explorer 9 supports
standards for HTML5, CSS3, SVG 1.1, ECMAScript5, and DOM L2 & L3.
Spend less time writing and rewriting code and more time creating great
experiences on the web. Be a part of the beta today.
http://p.sf.net/sfu/beautyoftheweb
_______________________________________________
Fann-general mailing list
https://lists.sourceforge.net/lists/listinfo/fann-general