What is the order of the InputWeigths vector in a NARX net?

Hello everyone, I am trying to replicate a previously trained NARX net from the net weights.

The net was buit with the following parameters:

inputDelays = 0:12;
feedbackDelays = 1:12;
hiddenLayerSize = 2;

Where the inputs are three elements and the output is one.

When I get the weights from the net, it returns the following:

>>net.IW
ans=
  2×2 cell array
    {2×39 double}    {2×12 double}
    {0×0  double}    {0×0  double}
>>net.LW
ans =
  2×2 cell array
    {0×0 double}    {0×0 double}
    {1×2 double}    {0×0 double}
>>net.b
ans=
  2×1 cell array
    {2×1 double}
    {1×1 double}

I understand that the element net.IW{1,1} corresponds to the weights of the input vector for each neuron, but since I have three input variables, the input is a matrix of size 3x13 and not a vector of size 1x39.

I tried transforming the input matrix into a 1x39 vector, following the order: [X1(t),X2(t),X3(t),X1(t-1),X2(t-1,X3(t-1),...,X1(t-12),X2(t-12),X3(t-12)], but I do not get the same result as using the network. Is this the correct order? If not, how should it be?

Thanks

Answer 1

[Maria Duarte Rosa]

Hi Francisco,

One suggestion is to use genFunction(net) to generate a MATLAB script from the trained network that contains all the operations and parameters of the network. This might help clarifying some of your questions.

https://www.mathworks.com/help/deeplearning/ref/genfunction.html