1
$\begingroup$

Is it possible to sample from a distribution inside a neural network forward function? Assume that there is a NN and a sample is needed to be derived from it at every forward-pass to randomly set a layer-specific hyper-parameter.

Is this operation differentiable

$\endgroup$

Your Answer

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

Browse other questions tagged or ask your own question.