0
$\begingroup$

In papers on this topic, I have seen deep ensembles being compared to dropout monte carlo. I was wondering why they are never used simultanously, since adding dropout monte carlo to every member of an ensemble isn't computationally expensive, especially compared too obtaining an deep ensemble.

$\endgroup$

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.