SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.02627 · ICML · 2020

Notes on the Behavior of MC Dropout

Francesco Verdoja, Ville Kyrki

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
aalto-intelligent-robotics/mc-dropout-notebooks canonical 3 of 5
FunctionStatusWhere it lives
LineSample Ran aalto-intelligent-robotics/mc-dropout-notebooks/functions.py
code served (permissive licence) · get_code("4242fbb59bb8ad5d")
to_cuda Ran aalto-intelligent-robotics/mc-dropout-notebooks/nets.py
code served (permissive licence) · get_code("3748277200ac8e4c")
to_variable Ran aalto-intelligent-robotics/mc-dropout-notebooks/nets.py
code served (permissive licence) · get_code("cf417f6499909dfa")
GMMsample Not yet run aalto-intelligent-robotics/mc-dropout-notebooks/functions.py
code served (permissive licence) · get_code("9fb65a7ecff0a064")
ShapeSample Not yet run aalto-intelligent-robotics/mc-dropout-notebooks/functions.py
code served (permissive licence) · get_code("d555811c9f1edccf")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Among the various options to estimate uncertainty in deep neural networks, Monte-Carlo dropout is widely popular for its simplicity and effectiveness. However the quality of the uncertainty estimated through this method varies and choices in architecture design and in training procedures have to be carefully considered and tested to obtain satisfactory results. In this paper we present study offering a different point of view on the behavior of Monte-Carlo dropout, which enable us to observe a few interesting properties of the technique to keep in mind when considering its use for uncertainty estimation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2008.02627")
get_code_for_paper("2008.02627")
have("2008.02627")

Connect an agent — have() is free.