MATLAB: THE DIFFERACE RESULT IN NEURAL NETWORK PROBLEM

Deep Learning ToolboxImage Processing Toolboxneural networkneural networks

I hope someone can help me with my question.

When I run the backprop neural network more than once on the same data set i get a different set of results. (the predicted results are different each time). Is there a way to train the Neural Network to output the same (lowest error predictions) if you run the code more than once for the same data set ? when enter the testimage for first time will classify as first class but when rerun the program with same testimage will classify as second class.. how can solve this problem …this is my file Thanks

Best Answer

if you are using a saved net that has been previously trained, this should not happen.

If you are setting the RNG to the same initial state before retraining, this should not happen.

Hope this helps.

Thank you for formally accepting my answer

Greg

Related Solutions

MATLAB: About neural net fitting (at neural network toolkit)

 IW = net.IW
  B = net.B
 LW = net.LW

Thank you for formally accepting my answer

Greg

MATLAB: How to divide class in neural network for Biometric authentication

You are going to have to design many candidate nets to decide the number of hidden nodes and which random weight initialization will yields the best net. If you have a lot of data, you can just use the default dividerand with the default train/val/test ratio = 0.7/0.15/0.15 . However, if this isn't satisfactory, you could change it to 0.666/0.167/0.167/. However, it really isn't worth the trouble.

If you don't have much data you might want to use divideind to specify which inputs belong to each trn/val/test subset.

How many people are there? If there are Np people you could use one input from each person in every group of Np.

Hope this helps.

Greg

Best Answer

Related Solutions

MATLAB: About neural net fitting (at neural network toolkit)

MATLAB: How to divide class in neural network for Biometric authentication

Related Question