How to generate initial weights for back-propagation neural network (BPNN) using MATLAB R2012a?

I am trying to predict future values using BPNN, with 1 input and output neuron respectively and also 1 layer of hidden layer. And I change the number of hidden neurons from 2 to 10. For example, I set the number of hidden neurons (N) as 10 first. So, I want to generate the weights (10 weights from input to hidden, and 10 from hidden to output),and I write this:

s=rng; m=rand(10,2)

Is this the correct way? However, when I change the N to 7, it gives me the same predicted values as N=10.

Answer 1

[Greg Heath]

The reason why the answers are different is because the state of the random number generator changes each time it is called.

Therefore if you want reproducibility, initialize the state of the rng before the first call of configure or train.

Most of my serious designs involve searching over multiple designs for the best combination of random initial weights, random trn/val/tst data divisions and number of hidden nodes.

I have posted scores of examples in the NEWSGROUP and ANSWERS. Search on

 greg rng('default')
 or
 greg rng(0)

Hope this helps

Thank you for formally accepting my answer

Greg

Answer 2

[Greg Heath]

 Most of the neural network functions create their own initial weights.

 See the documentation examples

 help fitnet
 doc fitnet

Or, if by prediction you mean predict future values,

 help narxnet
 doc narxnet

Hope this helps.

Thank you for formally accepting my answer

Greg

[soo rachael]

But, I got much different predicted values even I use all the parameters the same. It was not stable. So, I think of fixing my initial weights. How could I do this?