You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I was wondering whether there is a nice way to make the predictions (forward passes) stochastic, basically like applying dropout at test time? Essentially what Gal et al. suggest in "Dropout as a Bayesian approximation".
The text was updated successfully, but these errors were encountered:
I was wondering whether there is a nice way to make the predictions (forward passes) stochastic, basically like applying dropout at test time? Essentially what Gal et al. suggest in "Dropout as a Bayesian approximation".
The text was updated successfully, but these errors were encountered: