Sim function giving different answer

I have trained a neural network with XOR gate using nprtool. I want to export it into my .net application. I used d sim function to simulate the network and it produced the expected result. However, the sim function does not work outside matlab so i need to write out the weights so i can use in my dotnet application. I wrote this function and tested it in matlab. The problem is that the function does not return same result as when i use sim function in matlab. Please i need help!!!

function [ Result ] = TrainedXOR_net(input )
load C:\Users\Student\Desktop\my_MatlabFiles\SampleXOR_Net.mat
y1 = tansig(net.IW{1}* input + net.b{1});
Result = tansig(net.LW{2}* y1 + net.b{2});
end

[Greg Heath]

It's a common mistake responsible for many posts in both the NEWSGROUP and ANSWERS.

Answer 1

[Omotayo Asiru]

I got it sorted. Just wanna post my solution so another person with same problem can sort it easily. It turns out that i needed to do some pre-processing on my input and post-processing on the result. With this code below,I now have same result as sim function.

function [ Result ] = TrainedXOR_net(inputs)
%This is just to load the pre-trained network from the location i saved it.
load C:\Users\Student\Desktop\my_MatlabFiles\SampleXOR_Net.mat
for iii = 1:numel(net.inputs{1}.processFcns)

inputs = feval( net.inputs{1}.processFcns{iii}, 'apply', inputs,         net.inputs{1}.processSettings{iii} );
end
y1 = tansig(net.IW{1}* inputs + net.b{1});
Result = tansig(net.LW{2}* y1 + net.b{2});
for iii = 1:numel(net.outputs{2}.processFcns)
Result = feval( net.outputs{2}.processFcns{iii},'reverse', Result, net.outputs{2}.processSettings{iii} );
  end