A Survey of Uncertainty in Deep Neural Networks

Abstract

Due to their increasing spread, confidence in neural network predictions became more and more important. However, basic neural networks do not deliver certainty estimates or suffer from over or under confidence. Many researchers have been working on understanding and quantifying uncertainty in a neural network's prediction. As a result, different types and sources of uncertainty have been identified and a variety of approaches to measure and quantify uncertainty in neural networks have been proposed. This work gives a comprehensive overview of uncertainty estimation in neural networks, reviews recent advances in the field, highlights current challenges, and identifies potential research opportunities. It is intended to give anyone interested in uncertainty estimation in neural networks a broad overview and introduction, without presupposing prior knowledge in this field. A comprehensive introduction to the most crucial sources of uncertainty is given and their separation into reducible model uncertainty and not reducible data uncertainty is presented. The modeling of these uncertainties based on deterministic neural networks, Bayesian neural networks, ensemble of neural networks, and test-time data augmentation approaches is introduced and different branches of these fields as well as the latest developments are discussed. For a practical application, we discuss different measures of uncertainty, approaches for the calibration of neural networks and give an overview of existing baselines and implementations. Different examples from the wide spectrum of challenges in different fields give an idea of the needs and challenges regarding uncertainties in practical applications. Additionally, the practical limitations of current methods for mission- and safety-critical real world applications are discussed and an outlook on the next steps towards a broader usage of such methods is given.

Cited by in corpus (25)

• Remote patient monitoring using artificial intelligence: Current state, applications, and challenges
• Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial
• AI Security for Geoscience and Remote Sensing: Challenges and Future Trends
• Probabilistic Deep Learning for Real-Time Large Deformation Simulations
• Machine-learned molecular mechanics force field for the simulation of protein-ligand systems and beyond
• Artificial Neural Networks Modelling of Wall Pressure Spectra Beneath Turbulent Boundary Layers
• Uncertainty Aware Training to Improve Deep Learning Model Calibration for Classification of Cardiac MR Images
• The long road to calibrated prediction uncertainty in computational chemistry
• Pixle: a fast and effective black-box attack based on rearranging pixels
• Uncertainty Quantification for Molecular Property Predictions with Graph Neural Architecture Search
• CertainNet: Sampling-free Uncertainty Estimation for Object Detection
• Finite-time Lyapunov exponents of deep neural networks
• TMS-Net: A Segmentation Network Coupled With A Run-time Quality Control Method For Robust Cardiac Image Segmentation
• A Deep Registration Method for Accurate Quantification of Joint Space Narrowing Progression in Rheumatoid Arthritis
• Interpretable Uncertainty Quantification in AI for HEP
• Deep Learning reconstruction with uncertainty estimation for $\gamma$ photon interaction in fast scintillator detectors
• Bayesian posterior approximation with stochastic ensembles
• Experimental online quantum dots charge autotuning using neural networks
• Robust quantum dots charge autotuning using neural network uncertainty
• Uncertainty estimations methods for a deep learning model to aid in clinical decision-making -- a clinician's perspective
• That Label's Got Style: Handling Label Style Bias for Uncertain Image Segmentation
• Out-of-Distribution Detection for Adaptive Computer Vision
• Bayesian Uncertainty and Expected Gradient Length -- Regression: Two Sides Of The Same Coin?
• Confidence Contours: Uncertainty-Aware Annotation for Medical Semantic Segmentation
• A technique to jointly estimate depth and depth uncertainty for unmanned aerial vehicles