Qualitative Analysis of Monte Carlo Dropout
This work provides insights into uncertainty estimation for neural network practitioners, but it is incremental as it focuses on qualitative analysis of an existing method.
The paper analyzes Monte Carlo dropout for measuring uncertainty in neural networks, presenting its mathematical formulation and discussing potential benefits and costs based on experimental results.
In this report, we present qualitative analysis of Monte Carlo (MC) dropout method for measuring model uncertainty in neural network (NN) models. We first consider the sources of uncertainty in NNs, and briefly review Bayesian Neural Networks (BNN), the group of Bayesian approaches to tackle uncertainties in NNs. After presenting mathematical formulation of MC dropout, we proceed to suggesting potential benefits and associated costs for using MC dropout in typical NN models, with the results from our experiments.