I'm requested to implement mnist project using stacked RBM. I didn't find any implementation of RBM in keras or tensorflow. However, there is a Bernoulli RBM in sklearn.

Could you please guide me if they are the same? Can I make a stacked RBM using this package?

And in general, what is the difference between them?


They're not the same at all.

A stacked RBM is probably another name for a DBN (Deep Belief Network). It is derived from an RBM, but it's not an RBM.

A bernoulli RBM is an RBM where the nodes in the graph are bernoulli random variables.


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.