Problem about taking optimum performance of neural network output for pattern classification

Hello, I am using MATLAB 2012a. I am doing 2 class classification using patternnet MATLAB for Biosignal , I am worried about the following items:

a) In the program , How can I set Initial weight and bias of input and hidden layer manually ? I am getting some abnormal/unconsistent result.

b) How i can plot MSE vs no iteraton up to 1000. I want see MSE is constant even after converge at certain iteration.?

c) How I can set optimum number of hidden neuron in the hidden layer?

d) Also, How I can do the 10 fold cross validation for the above data to get optimum error? anybody has clues/videos/ideas?

Thanks a lot.

Answer 1

[Greg Heath]

Didn't I answer these questions already?