how to create exe file from NN toolbox trained network for testing on new data inputs

Question

essam on 28 May 2016

0
Link

Direct link to this question

https://se.mathworks.com/matlabcentral/answers/286242-how-to-create-exe-file-from-nn-toolbox-trained-network-for-testing-on-new-data-inputs

Commented: essam on 31 May 2016

Hi all I created a NN using NNtoolbox to predict company failure, but now I want to create it as EXE for further analysis for new dataset so third users can use it can anyone tell me how to do that? and how to test the NN for predicating failure with using inputs of a new dataset here the code generated

if true
  % Solve a Pattern Recognition Problem with a Neural Network
% Script generated by Neural Pattern Recognition app
% Created 28-May-2016 22:38:23
%
% This script assumes these variables are defined:
%
%   inou - input data.
%   out - target data.
x = inou';
t = out';
% Choose a Training Function
% For a list of all training functions type: help nntrain
% 'trainlm' is usually fastest.
% 'trainbr' takes longer but may be better for challenging problems.
% 'trainscg' uses less memory. Suitable in low memory situations.
trainFcn = 'trainscg';  % Scaled conjugate gradient backpropagation.
% Create a Pattern Recognition Network
hiddenLayerSize = 10;
net = patternnet(hiddenLayerSize);
% Setup Division of Data for Training, Validation, Testing
net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;
% Train the Network
[net,tr] = train(net,x,t);
% Test the Network
y = net(x);
e = gsubtract(t,y);
performance = perform(net,t,y)
tind = vec2ind(t);
yind = vec2ind(y);
percentErrors = sum(tind ~= yind)/numel(tind);
% View the Network
view(net)
end