MATLAB: Manually reproduce results from a neural network generated from Matlab

Deep Learning Toolboxneural networks

I've tried to reproduce the results I got from a trained network but was unable. Here's my script:
load 'C:\Users\ZA\Documents\cosjacorr.mat'
inputs = cosjacorr(:, 1:9)';
targets = cosjacorr(:, 10:13)';
numHiddenNeurons = 2;  % Adjust as desired



net = newpr(inputs,targets,numHiddenNeurons);
net.divideParam.trainRatio = 75/100;  % Adjust as desired
net.divideParam.valRatio = 15/100;  % Adjust as desired
net.divideParam.testRatio = 10/100;  % Adjust as desired
net.inputs{1}.processFcns = {}; 
net.outputs{2}.processFcns = {};
% Train and Apply Network
[net,tr] = train(net,inputs,targets);
outputs = sim(net,inputs);
% Plot
plotconfusion(targets,outputs)
I removed all pre and post processing hoping that I would be able to reproduce the results but was unsuccessful.
Here's what I did in terms of replicating the network's output:
y1 = tansig(net.IW{1} * input + net.b{1});
      Results = tansig(net.LW{2} * y1 + net.b{2});
Can someone please help me out? thanks.
PS. I can even send the entire data file to you if it will help.

Best Answer

Type "whos" to see the dimensionality of all variables and parameters.
 % help newpr
 % doc newpr
 % Obsoleted in R2010b NNET 7.0.  Last used in R2010a 
 close all, clear all, clc
 [x t ] = simpleclass_dataset; 
 [ I  N ] = size(x)             % [ 2 1000 ]
 [O N ] = size(t)               %  [ 4 1000]
 H = 2
  net = newpr(x,t,H);
  net = train(net,x,t);
  y    = net(x);  
  IW   = net.IW{1,1};
b1   = net.b{1};
b2   = net.b{2};
LW = net.LW{2,1};
   whos          
 %   IW          2x2                  32  double               
 %   LW          4x2                  64  double                         
 %   b1          2x1                  16  double               
 %   b2          4x1                  32  double                             
 %   t           4x1000            32000  double               
 %   x           2x1000            16000  double               
 %   y           4x1000            32000  double               
B1 = repmat( b1, 1, N );
B2 = repmat( b2, 1, N );
[ xn,xsettings] = mapminmax(x);
[ tn,tsettings] = mapminmax(t);
yn = tanh( B2 + LW*tanh( B1 + IW*xn ) ); 
y1 = mapminmax.reverse( yn,tsettings);
dy = max(max(abs(y1-y)))
Hope this helps
Thank you for formally accepting my answer
Greg
Related Question