Why do I get different input-output sensitivity each time I train a network on the same dataset in Neural Networks Toolbox?

I am training a network several times and I get similar fits each time. However, if I plot the sensitivities of input, I find that they are entirely different after each training.

Answer 1

[MathWorks Support Team]

Each time a neural network is created, it has semi-random weights and bias values. Hence, when trained it will find a different solution and therefore have different input-output sensitivities.

To consistently get the same solution and input-output sensitivities, for the same network architecture trained on the same data, set the random seed generator to a fixed value (such as pi) before creating and training the network:

   rand('seed',pi);