A Survey on Evidential Deep Learning For Single-Pass Uncertainty Estimation

10/06/2021
by   Dennis Ulmer, et al.
2

Popular approaches for quantifying predictive uncertainty in deep neural networks often involve a set of weights or models, for instance via ensembling or Monte Carlo Dropout. These techniques usually produce overhead by having to train multiple model instances or do not produce very diverse predictions. This survey aims to familiarize the reader with an alternative class of models based on the concept of Evidential Deep Learning: For unfamiliar data, they admit "what they don't know" and fall back onto a prior belief. Furthermore, they allow uncertainty estimation in a single model and forward pass by parameterizing distributions over distributions. This survey recapitulates existing works, focusing on the implementation in a classification setting. Finally, we survey the application of the same paradigm to regression problems. We also provide a reflection on the strengths and weaknesses of the mentioned approaches compared to existing ones and provide the most central theoretical results in order to inform future research.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

12/02/2021

Quantifying the uncertainty of neural networks using Monte Carlo dropout for deep learning based quantitative MRI

Dropout is conventionally used during the training phase as regularizati...
06/06/2015

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

Deep learning tools have gained tremendous attention in applied machine ...
02/22/2021

Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression

We propose a new model that estimates uncertainty in a single forward pa...
01/31/2020

Fast Monte Carlo Dropout and Error Correction for Radio Transmitter Classification

Monte Carlo dropout may effectively capture model uncertainty in deep le...
06/01/2021

Quantifying Predictive Uncertainty in Medical Image Analysis with Deep Kernel Learning

Deep neural networks are increasingly being used for the analysis of med...
08/20/2019

n-MeRCI: A new Metric to Evaluate the Correlation Between Predictive Uncertainty and True Error

As deep learning applications are becoming more and more pervasive in ro...
07/21/2021

High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm

Electroencephalography (EEG) is crucial for the monitoring and diagnosis...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.