MATLAB: ,the overallperformance in the confusion matrix changed although i used the same number of hidden layer

neural network

when i repeat the classification by nn and by the same number of hidden layer ,the overall-performance in the confusion matrix changed (96-100-98 …etc) what is the wrong thanks and best regards

Best Answer

Most likely you did not initialize the random number generator to the same initial state.

Hope this helps,

Thank you for formally accepting my answer

Greg

Related Solutions

MATLAB: How to train a feedfordward neural network with error weights

 Use the command window
 help mse
 doc mse

Hope this helps.

Thank you for formally accepting my answer

Greg

MATLAB: For the project work I have used Elman neural network, with Resilient back propagation algorithm, Nguyen widrow algorithm for generating initial layer values. I observed lot difference between outputs in different trials

Weights are initialized randomly for Neural Networks unless you initialize them manually. If you are getting as large of a difference as you are seeing, it should suggest to you that your network is not robust.

You can control the random number seed to reproduce particular networks. In R2010 you should see the documentation for the randstream class; R2011a or so introduced rng() as a simpler way to set the random seed.

Best Answer

Related Solutions

MATLAB: How to train a feedfordward neural network with error weights

MATLAB: For the project work I have used Elman neural network, with Resilient back propagation algorithm, Nguyen widrow algorithm for generating initial layer values. I observed lot difference between outputs in different trials

Related Question