0
$\begingroup$

To my understanding, a BNN's weights come from a Gaussian with trained mean and standard deviation, while a FFNN of the following form, comes from a learned weight, which acts as a 'mean', and is multiplied by an untrainable standard deviation

Dense()
GaussianNoise(stddev=0.3) 

What is the practical difference between these two approaches?

$\endgroup$

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.