Matlab Neural Network Tool Kit

Question

I used the Matlab neural network to train some data, but I want to run this neural network in a C ++ program, how to do it?

Answer 1

You can use ML to create your own set of functions (input level), and then use the open source C ++ NN implementation for training / classification. (For example, http://takinginitiative.net/2008/04/23/basic-neural-network-tutorial-c-implementation-and-source-code/ ) If you want to use ML for training and C ++ for classification, it should not be too difficult to write additional code to write out a prepared network so that it can be read by the C ++ classifier.

Answer 2

You can use the Matlab Compiler, which generates code that you can embed in your C ++ application

Answer 3

I am using Matlab R2013a. If you are still experiencing this problem, try looking at this location.

Matlab\R2013a\toolbox\nnet\nnet\nnderivative\+nnMex2 

inside the matlab directory. I found there the file "yy.cpp", which contains mexFunction , which does the thing. It is very likely that Matlab calls this function to simulate a network.

It seems that you can integrate this feature into your project after a little refactoring. At least I plan to do it. :-)