Skip to content
ml-recall

#mc-dropout

3 questions from Probabilistic & Graphical Models, Training Deep Networks

Timed test

3 questions · 3 min · score and explanations at the end

Take a test
Q 1 / 3Score 0 / 0

Question 1: True or false

mediumAI-checkedProbabilistic & Graphical Models

True or false: in a large benchmark of predictive uncertainty under dataset shift, deep ensembles generally gave better uncertainty estimates on shifted and out-of-distribution data than Monte-Carlo dropout.

Choose one option