0
$\begingroup$

A feed forward neural network trains best if the data is normalised so that each input has a mean of 0 and a standard deviation of 1. Is this true for a Restricted Boltzmann machine as well? (My experiments are saying, no it isn't.)

$\endgroup$
  • $\begingroup$ Based on my experience and some papers if you are working on binary RBM you should normalize your data between [0,1]. could you explain why your experiment says no? $\endgroup$ – Feras Jul 9 '16 at 9:33
1
$\begingroup$

That depends on the distributions you assume the visible and hidden variables to have. If the visibles are binary, you should scale them to the [0, 1] interval. If they are Gaussian, you should scale them to $\mathcal{N}(0, 1)$.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.