Single Shot MC Dropout Approximation

07/07/2020
by   Kai Brach, et al.
0

Deep neural networks (DNNs) are known for their high prediction performance, especially in perceptual tasks such as object recognition or autonomous driving. Still, DNNs are prone to yield unreliable predictions when encountering completely new situations without indicating their uncertainty. Bayesian variants of DNNs (BDNNs), such as MC dropout BDNNs, do provide uncertainty measures. However, BDNNs are slow during test time because they rely on a sampling approach. Here we present a single shot MC dropout approximation that preserves the advantages of BDNNs without being slower than a DNN. Our approach is to analytically approximate for each layer in a fully connected network the expected value and the variance of the MC dropout signal. We evaluate our approach on different benchmark datasets and a simulated toy example. We demonstrate that our single shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BDNNs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/24/2023

Single-shot Bayesian approximation for neural networks

Deep neural networks (NNs) are known for their high-prediction performan...
research
05/06/2022

Controlled Dropout for Uncertainty Estimation

Uncertainty quantification in a neural network is one of the most discus...
research
07/15/2021

Randomized ReLU Activation for Uncertainty Estimation of Deep Neural Networks

Deep neural networks (DNNs) have successfully learned useful data repres...
research
06/16/2023

Spatial-SpinDrop: Spatial Dropout-based Binary Bayesian Neural Network with Spintronics Implementation

Recently, machine learning systems have gained prominence in real-time, ...
research
10/12/2021

Robust Neural Regression via Uncertainty Learning

Deep neural networks tend to underestimate uncertainty and produce overl...
research
09/26/2016

Optimistic and Pessimistic Neural Networks for Scene and Object Recognition

In this paper the application of uncertainty modeling to convolutional n...
research
10/01/2018

Augmented Mitotic Cell Count using Field Of Interest Proposal

Histopathological prognostication of neoplasia including most tumor grad...

Please sign up or login with your details

Forgot password? Click here to reset