Neural Networks in MATLAB, initial weights [closed]

Question

I made Neural Network in MATLAB with newff(...). When you train it with the same inputs and outputs, the training results are different on different runs. I understand that it is happening because the weights are different for each time I run it. My question is how to make initial weights to be the same each time I train my NN so I can get the same results? Also, is it possible to save some weights from training No1 and latter use it for training No2, and how?

Tnx

Answer 1

To generate reproducible results, you need to manually set the random number generator to the same seed/state at the beginning of the code. This can be done in a number of ways (depending on what version of MATLAB you have):

The old style:

rand('twister',1234)

The updated style:

RandStream.setGlobalStream( RandStream('mt19937ar','Seed',1234) );

A new function was introduced in R2011a that simplifies the last call:

rng(1234,'twister')

The latter syntax is the recommended approach.