REVIEW 2 cited by
Notes on the Behavior of MC Dropout
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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 a study offering a different point of view on the behavior of Monte-Carlo dropout, which enables us to observe a few interesting properties of the technique to keep in mind when considering its use for uncertainty estimation.
Forward citations
Cited by 2 Pith papers
-
Predicting the Kinematics of the Cold Circumgalactic Medium from its Morphology using Convolutional Neural Networks
A convolutional neural network recovers plane-of-sky velocities of cold circumgalactic gas from H-alpha emission maps alone, with errors of 0.3 to 0.5 v_vir in TNG50 simulations.
-
Improving the Predictability of the Madden-Julian Oscillation at Subseasonal Scales with Gaussian Process Models
A Gaussian process MJO forecaster with empirical correlations claims better skill than an ANN for the first five lead days and probabilistic coverage extending beyond three weeks after a covariance correction.
Discussion (0). Continue with ORCID to comment.