A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges

Abstract

Uncertainty quantification (UQ) plays a pivotal role in reduction of uncertainties during both optimization and decision making processes. It can be applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning. Moreover, we also investigate the application of these methods in reinforcement learning (RL). Then, we outline a few important applications of UQ methods. Finally, we briefly highlight the fundamental research challenges faced by UQ methods and discuss the future research directions in this field.

References in corpus (364)

• A Survey on Deep Learning in Medical Image Analysis
• Auto-Encoding Variational Bayes
• YOLOv3: An Incremental Improvement
• Practical Bayesian Optimization of Machine Learning Algorithms
• Intriguing properties of neural networks
• Variational Inference: A Review for Statisticians
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• On Calibration of Modern Neural Networks
• Graph Neural Networks: A Review of Methods and Applications
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• Weight Uncertainty in Neural Networks
• Hierarchical Question-Image Co-Attention for Visual Question Answering
• VQA: Visual Question Answering
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
• Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning
• The Loss Surfaces of Multilayer Networks
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Deep Bayesian Active Learning with Image Data
• AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
• Deep Neural Networks as Gaussian Processes
• Infrared and Visible Image Fusion using a Deep Learning Framework
• Evidential Deep Learning to Quantify Classification Uncertainty
• VIME: Variational Information Maximizing Exploration
• Bayesian Active Learning for Classification and Preference Learning
• Stochastic Gradient Hamiltonian Monte Carlo
• Energy-based Out-of-distribution Detection
• Using Pre-Training Can Improve Model Robustness and Uncertainty
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Deep Anomaly Detection with Outlier Exposure
• Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation
• A Tutorial on Bayesian Optimization
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Artificial Intelligence and Statistics
• Accurate Uncertainties for Deep Learning Using Calibrated Regression
• Predictive Uncertainty Estimation via Prior Networks
• Optimization under Uncertainty in the Era of Big Data and Deep Learning: When Machine Learning Meets Mathematical Programming
• Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
• BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
• Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network
• Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation
• Variational Continual Learning
• To Trust Or Not To Trust A Classifier
• Deep Gaussian Processes
• Bayesian Reinforcement Learning: A Survey
• Averaging Weights Leads to Wider Optima and Better Generalization
• Uncertainty-Aware Reinforcement Learning for Collision Avoidance
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• Parameterized Explainer for Graph Neural Network
• Reliable deep-learning-based phase imaging with uncertainty quantification
• Deep Learning for Post-Processing Ensemble Weather Forecasts
• BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization
• Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
• Bayesian Dark Knowledge
• Uncertainty and Interpretability in Convolutional Neural Networks for Semantic Segmentation of Colorectal Polyps
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization
• Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• Understanding Measures of Uncertainty for Adversarial Example Detection
• A Simple Baseline for Bayesian Uncertainty in Deep Learning
• Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT
• Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
• Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning
• Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentation
• SpinalNet: Deep Neural Network with Gradual Input
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• Bayesian Model-Agnostic Meta-Learning
• High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach
• Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
• Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion
• Bayesian Recurrent Neural Networks
• Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks
• DR$|$GRADUATE: uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images
• Deep Learning: A Bayesian Perspective
• On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators
• Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
• Functional Variational Bayesian Neural Networks
• Cascaded V-Net using ROI masks for brain tumor segmentation
• Uncertainty-based Continual Learning with Adaptive Regularization
• Coresets for Scalable Bayesian Logistic Regression
• Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning
• Unsupervised Scene Adaptation with Memory Regularization in vivo
• Addressing Failure Prediction by Learning Model Confidence
• FMix: Enhancing Mixed Sample Data Augmentation
• From Variational to Deterministic Autoencoders
• Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
• Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud
• ODE${}^2$VAE: Deep generative second order ODEs with Bayesian neural networks
• Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network
• Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory
• HyperNetworks
• Evaluating model calibration in classification
• Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors
• Verified Uncertainty Calibration
• A Bayesian Deep Learning Framework for End-To-End Prediction of Emotion from Heartbeat
• Functional Regularisation for Continual Learning with Gaussian Processes
• Deeply Uncertain: Comparing Methods of Uncertainty Quantification in Deep Learning Algorithms
• Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
• Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
• Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
• Avoiding pathologies in very deep networks
• Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic
• Bayesian Layers: A Module for Neural Network Uncertainty
• Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation
• CXPlain: Causal Explanations for Model Interpretation under Uncertainty
• Single-Model Uncertainties for Deep Learning
• Learning Sparse Networks Using Targeted Dropout
• Quality of Uncertainty Quantification for Bayesian Neural Network Inference
• A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
• "Why Should You Trust My Explanation?" Understanding Uncertainty in LIME Explanations
• Task Agnostic Continual Learning Using Online Variational Bayes
• Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness
• Bayesian Batch Active Learning as Sparse Subset Approximation
• Integrating uncertainty in deep neural networks for MRI based stroke analysis
• Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
• Implicit Weight Uncertainty in Neural Networks
• Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo
• DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
• SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates
• Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
• Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
• Reinforcement Learning through Active Inference
• The Uncertainty Bellman Equation and Exploration
• Ensemble Slice Sampling: Parallel, black-box and gradient-free inference for correlated & multimodal distributions
• Analyzing the Role of Model Uncertainty for Electronic Health Records
• Neural Tangents: Fast and Easy Infinite Neural Networks in Python
• Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning
• Continual Deep Learning by Functional Regularisation of Memorable Past
• Uncertainty-Aware Organ Classification for Surgical Data Science Applications in Laparoscopy
• Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning
• Modeling Uncertainty with Hedged Instance Embedding
• Convolutional Gaussian Processes
• Noise Contrastive Priors for Functional Uncertainty
• Analyzing Uncertainty in Neural Machine Translation
• Leveraging Uncertainty Estimates for Predicting Segmentation Quality
• Uncertainty Aware Semi-Supervised Learning on Graph Data
• Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
• Conditional Neural Processes
• Estimating Risk and Uncertainty in Deep Reinforcement Learning
• Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning
• Direct Uncertainty Prediction for Medical Second Opinions
• A Unifying Bayesian View of Continual Learning
• Linear Maximum Margin Classifier for Learning from Uncertain Data
• Ensemble Sampling
• Optimal Uncertainty-guided Neural Network Training
• Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation
• On the Expressiveness of Approximate Inference in Bayesian Neural Networks
• Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning
• Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models
• Uncertainty in Neural Networks: Approximately Bayesian Ensembling
• An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
• Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator
• Uncertainty-driven Sanity Check: Application to Postoperative Brain Tumor Cavity Segmentation
• Hydra: Preserving Ensemble Diversity for Model Distillation
• Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks
• Stacking for Non-mixing Bayesian Computations: The Curse and Blessing of Multimodal Posteriors
• Accurate Uncertainty Estimation and Decomposition in Ensemble Learning
• Deep-ESN: A Multiple Projection-encoding Hierarchical Reservoir Computing Framework
• Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings
• Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors
• Uncertainty-Aware Attention for Reliable Interpretation and Prediction
• Uncertainty Estimation in Autoregressive Structured Prediction
• Uncertainty Sets for Image Classifiers using Conformal Prediction
• Striking the Right Balance with Uncertainty
• Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization
• Propagating Uncertainty in Multi-Stage Bayesian Convolutional Neural Networks with Application to Pulmonary Nodule Detection
• 'In-Between' Uncertainty in Bayesian Neural Networks
• Learning the Pareto Front with Hypernetworks
• Adversarial Distillation of Bayesian Neural Network Posteriors
• Information Aware Max-Norm Dirichlet Networks for Predictive Uncertainty Estimation
• Variational Bayesian Monte Carlo with Noisy Likelihoods
• Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks
• Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
• Bayesian Deep Ensembles via the Neural Tangent Kernel
• IDK Cascades: Fast Deep Learning by Learning not to Overthink
• DEUP: Direct Epistemic Uncertainty Prediction
• Robustness of Bayesian Neural Networks to Gradient-Based Attacks
• A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities
• Calibration tests in multi-class classification: A unifying framework
• Uncertainty-guided Continual Learning with Bayesian Neural Networks
• The MBPEP: a deep ensemble pruning algorithm providing high quality uncertainty prediction
• Deep Ensemble Bayesian Active Learning : Addressing the Mode Collapse issue in Monte Carlo dropout via Ensembles
• On the Importance of Strong Baselines in Bayesian Deep Learning
• The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning
• SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient
• Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations
• Accuracy, Uncertainty, and Adaptability of Automatic Myocardial ASL Segmentation using Deep CNN
• Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning
• Bayesian Neural Networks With Maximum Mean Discrepancy Regularization
• The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
• Multi-Fidelity Bayesian Optimization via Deep Neural Networks
• Inhibited Softmax for Uncertainty Estimation in Neural Networks
• Learnable Bernoulli Dropout for Bayesian Deep Learning
• Calibrated Reliable Regression using Maximum Mean Discrepancy
• Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution
• Uncertainty Quantification with Generative Models
• Uncertainty on Asynchronous Time Event Prediction
• Subspace Inference for Bayesian Deep Learning
• Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers
• Bayesian Inference with Anchored Ensembles of Neural Networks, and Application to Exploration in Reinforcement Learning
• Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
• Transferable Calibration with Lower Bias and Variance in Domain Adaptation
• Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting
• Neural Ensemble Search for Uncertainty Estimation and Dataset Shift
• Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization
• Confident Multiple Choice Learning
• Uncertainty Quantification for Data-driven Turbulence Modelling with Mondrian Forests
• Bayesian Graph Neural Networks with Adaptive Connection Sampling
• On the Modularity of Hypernetworks
• Single Shot MC Dropout Approximation
• Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
• Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
• Deep Active Learning for Axon-Myelin Segmentation on Histology Data
• Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection
• MotherNets: Rapid Deep Ensemble Learning
• Bayesian Semisupervised Learning with Deep Generative Models
• A Survey on Bayesian Deep Learning
• Matrix Completion with Quantified Uncertainty through Low Rank Gaussian Copula
• Training Binary Neural Networks using the Bayesian Learning Rule
• Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift
• Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantification
• Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Data
• Supervised Uncertainty Quantification for Segmentation with Multiple Annotations
• Spatial Uncertainty Sampling for End-to-End Control
• Bayesian Hypernetworks
• Fast uncertainty quantification of reservoir simulation with variational U-Net
• Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
• Deep Network Uncertainty Maps for Indoor Navigation
• Bayesian Policy Gradients via Alpha Divergence Dropout Inference
• Variance Networks: When Expectation Does Not Meet Your Expectations
• Uncertainty Quantification for Sparse Deep Learning
• Individual Calibration with Randomized Forecasting
• Calibrating Deep Convolutional Gaussian Processes
• Mondrian Forests for Large-Scale Regression when Uncertainty Matters
• CRUDE: Calibrating Regression Uncertainty Distributions Empirically
• Expressive Priors in Bayesian Neural Networks: Kernel Combinations and Periodic Functions
• A Gaussian Process perspective on Convolutional Neural Networks
• Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning
• Estimating Model Uncertainty of Neural Networks in Sparse Information Form
• Variational Inference to Measure Model Uncertainty in Deep Neural Networks
• Double-Uncertainty Weighted Method for Semi-supervised Learning
• Interpretable deep Gaussian processes with moments
• Distribution-Free Uncertainty Quantification for Kernel Methods by Gradient Perturbations
• Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions
• Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification
• Posterior inference unchained with EL_2O
• Deep Evidential Regression
• Bayesian Structure Learning by Recursive Bootstrap
• Diversity inducing Information Bottleneck in Model Ensembles
• Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator
• Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation
• Calibration of Model Uncertainty for Dropout Variational Inference
• Predictive Uncertainty Quantification with Compound Density Networks
• Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
• Self-Loop Uncertainty: A Novel Pseudo-Label for Semi-Supervised Medical Image Segmentation
• ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition
• Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow
• Being Bayesian about Categorical Probability
• Variational Bayesian Monte Carlo
• Stochastic Prototype Embeddings
• DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networks
• Output-Constrained Bayesian Neural Networks
• Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality
• NADS: Neural Architecture Distribution Search for Uncertainty Awareness
• Learning Structural Weight Uncertainty for Sequential Decision-Making
• Uncertainty in Multitask Transfer Learning
• On uncertainty estimation in active learning for image segmentation
• Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning
• A Bayesian Perspective on Training Speed and Model Selection
• Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks
• Fast Predictive Uncertainty for Classification with Bayesian Deep Networks
• Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables
• Validated Variational Inference via Practical Posterior Error Bounds
• Deep Bayesian Gaussian Processes for Uncertainty Estimation in Electronic Health Records
• Improving Back-Translation with Uncertainty-based Confidence Estimation
• Uncertainty aware Search Framework for Multi-Objective Bayesian Optimization with Constraints
• Data Uncertainty Learning in Face Recognition
• Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation
• Cost-aware Multi-objective Bayesian optimisation
• A Bayesian Hierarchical Network for Combining Heterogeneous Data Sources in Medical Diagnoses
• Prediction Intervals: Split Normal Mixture from Quality-Driven Deep Ensembles
• Bayesian Modelling in Practice: Using Uncertainty to Improve Trustworthiness in Medical Applications
• Learning from the Past: Continual Meta-Learning via Bayesian Graph Modeling
• Stationary Activations for Uncertainty Calibration in Deep Learning
• Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning
• Deep density networks and uncertainty in recommender systems
• Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections
• Uncertainty-Aware Lookahead Factor Models for Quantitative Investing
• Meta-Learning PAC-Bayes Priors in Model Averaging
• Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet
• Quantifying Intrinsic Uncertainty in Classification via Deep Dirichlet Mixture Networks
• Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Clouds
• Exploiting Uncertainties from Ensemble Learners to Improve Decision-Making in Healthcare AI
• Probabilistic Numeric Convolutional Neural Networks
• Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration
• Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classification
• Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning
• Regularizing Meta-Learning via Gradient Dropout
• Epistemic Risk-Sensitive Reinforcement Learning
• Incorporating Interpretable Output Constraints in Bayesian Neural Networks
• Markov-Chain Monte Carlo Approximation of the Ideal Observer using Generative Adversarial Networks
• Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functions
• BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty
• Ensemble Model Patching: A Parameter-Efficient Variational Bayesian Neural Network
• Uncertainty-Driven Semantic Segmentation through Human-Machine Collaborative Learning
• Quantile Regularization: Towards Implicit Calibration of Regression Models
• Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification
• Wasserstein variational gradient descent: From semi-discrete optimal transport to ensemble variational inference
• Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry
• Unsupervised Data Uncertainty Learning in Visual Retrieval Systems
• Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery
• Bayesian Optimization Meets Laplace Approximation for Robotic Introspection
• Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?
• Bayesian Structure Adaptation for Continual Learning
• Efficient Ensemble Model Generation for Uncertainty Estimation with Bayesian Approximation in Segmentation
• Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights
• Know Your Limits: Uncertainty Estimation with ReLU Classifiers Fails at Reliable OOD Detection
• URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks
• Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task
• Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
• Bayesian Policy Optimization for Model Uncertainty
• Estimating Uncertainty Intervals from Collaborating Networks
• Towards Principled Uncertainty Estimation for Deep Neural Networks
• Variational Inference and Bayesian CNNs for Uncertainty Estimation in Multi-Factorial Bone Age Prediction
• Uncertainty-Aware Deep Classifiers using Generative Models
• Variational Smoothing in Recurrent Neural Network Language Models
• Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification
• A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation
• Learning while Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Data
• Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent
• Facilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients
• Combining Model and Parameter Uncertainty in Bayesian Neural Networks
• Weighting Is Worth the Wait: Bayesian Optimization with Importance Sampling
• Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models
• Estimation with Uncertainty via Conditional Generative Adversarial Networks
• Uncertainty Evaluation Metric for Brain Tumour Segmentation
• Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
• Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective
• Sampling-Free Learning of Bayesian Quantized Neural Networks
• An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation
• Uncertainty Estimation in Deep 2D Echocardiography Segmentation
• Uncertainty quantification in medical image segmentation with normalizing flows
• BDLOB: Bayesian Deep Convolutional Neural Networks for Limit Order Books
• Uncertainty Quantification for Bayesian Optimization
• Difficulty-aware Glaucoma Classification with Multi-Rater Consensus Modeling
• Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization
• Quantum Deformed Neural Networks
• On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
• Fully Bayesian Recurrent Neural Networks for Safe Reinforcement Learning
• Wisdom of the Ensemble: Improving Consistency of Deep Learning Models
• Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables
• Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties
• Active Perception in Adversarial Scenarios using Maximum Entropy Deep Reinforcement Learning
• Uncertainty Quantification in Deep Residual Neural Networks
• Dirichlet uncertainty wrappers for actionable algorithm accuracy accountability and auditability
• Assessing the Robustness of Bayesian Dark Knowledge to Posterior Uncertainty
• Uncertainty Quantification for Inferring Hawkes Networks
• Predictive Uncertainty through Quantization
• Bayesian Brain meets Bayesian Recommender - Towards Systems with Empathy for the Human Nature

Cited by in corpus (185)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Recent advances and clinical applications of deep learning in medical image analysis
• Remote patient monitoring using artificial intelligence: Current state, applications, and challenges
• A Review of Generalized Zero-Shot Learning Methods
• Medical Deep Learning -- A systematic Meta-Review
• Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial
• A broadband hyperspectral image sensor with high spatio-temporal resolution
• Deep learning-based synthetic-CT generation in radiotherapy and PET: a review
• A review of predictive uncertainty estimation with machine learning
• Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
• A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic
• A critical examination of robustness and generalizability of machine learning prediction of materials properties
• Fusion of Probability Density Functions
• A Brief Review of Hypernetworks in Deep Learning
• Current and future directions in network biology
• UncertaintyFuseNet: Robust Uncertainty-aware Hierarchical Feature Fusion Model with Ensemble Monte Carlo Dropout for COVID-19 Detection
• An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future works
• Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
• MCUa: Multi-level Context and Uncertainty aware Dynamic Deep Ensemble for Breast Cancer Histology Image Classification
• Retention Time Prediction for Chromatographic Enantioseparation by Quantile Geometry-enhanced Graph Neural Network
• A Survey on Semantic Communications for Intelligent Wireless Networks
• Uncertainty Quantification in Multivariable Regression for Material Property Prediction with Bayesian Neural Networks
• Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends
• Physics-Informed Deep Learning For Traffic State Estimation: A Survey and the Outlook
• QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
• Medical Imaging and Machine Learning
• Advancing Additive Manufacturing through Deep Learning: A Comprehensive Review of Current Progress and Future Challenges
• Artificial Neural Networks Modelling of Wall Pressure Spectra Beneath Turbulent Boundary Layers
• Virtual stain transfer in histology via cascaded deep neural networks
• Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models
• Artificial intelligence approaches for materials-by-design of energetic materials: state-of-the-art, challenges, and future directions
• Reliability and Interpretability in Science and Deep Learning
• Learning Uncertainty with Artificial Neural Networks for Improved Predictive Process Monitoring
• Uncertainty-Aware Mixed-Variable Machine Learning for Materials Design
• Uncertainty Aware Training to Improve Deep Learning Model Calibration for Classification of Cardiac MR Images
• GraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for Identifying COVID-19 on Chest X-rays
• Bridging adaptive management and reinforcement learning for more robust decisions
• CHS-Net: A Deep learning approach for hierarchical segmentation of COVID-19 infected CT images
• Comparing hundreds of machine learning classifiers and discrete choice models in predicting travel behavior: an empirical benchmark
• Robust model benchmarking and bias-imbalance in data-driven materials science: a case study on MODNet
• Quantification of Deep Neural Network Prediction Uncertainties for VVUQ of Machine Learning Models
• When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System
• Time Series Predictions in Unmonitored Sites: A Survey of Machine Learning Techniques in Water Resources
• Small Drone Classification with Light CNN and New Micro-Doppler Signature Extraction Method Based on A-SPC Technique
• Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment
• Machine learning applications for weather and climate need greater focus on extremes
• Assaying Out-Of-Distribution Generalization in Transfer Learning
• Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications
• Improved uncertainty quantification for neural networks with Bayesian last layer
• Neural network model for imprecise regression with interval dependent variables
• A robust and scalable framework for hallucination detection in virtual tissue staining and digital pathology
• Ultrafast Radiographic Imaging and Tracking: An overview of instruments, methods, data, and applications
• Calibration in Machine Learning Uncertainty Quantification: beyond consistency to target adaptivity
• Hessian-based toolbox for reliable and interpretable machine learning in physics
• Lightweight Regression Model with Prediction Interval Estimation for Computer Vision-based Winter Road Surface Condition Monitoring
• CycleSense: Detecting Near Miss Incidents in Bicycle Traffic from Mobile Motion Sensors
• Towards a Comprehensive Human-Centred Evaluation Framework for Explainable AI
• A Rigorous Uncertainty-Aware Quantification Framework Is Essential for Reproducible and Replicable Machine Learning Workflows
• Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Data
• Adversarial Attack for Uncertainty Estimation: Identifying Critical Regions in Neural Networks
• Exploring the Landscape of Ubiquitous In-home Health Monitoring: A Comprehensive Survey
• A Quantitative Comparison of Epistemic Uncertainty Maps Applied to Multi-Class Segmentation
• Fairness through Aleatoric Uncertainty
• Time series forecasting of multiphase microstructure evolution using deep learning
• Bridging the Gap Between Explainable AI and Uncertainty Quantification to Enhance Trustability
• Engineering Artificial Intelligence: Framework, Challenges, and Future Direction
• Rapid quantitative magnetization transfer imaging: utilizing the hybrid state and the generalized Bloch model
• Learned, uncertainty-driven adaptive acquisition for photon-efficient scanning microscopy
• A Hybrid Probabilistic Battery Health Management Approach for Robust Inspection Drone Operations
• JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks
• A Robust Learning Methodology for Uncertainty-aware Scientific Machine Learning models
• Attention-based Multi-fidelity Machine Learning Model for Computational Fractional Flow Reserve Assessment
• Uncertainty Aware ML-based surrogate models for particle accelerators: A Study at the Fermilab Booster Accelerator Complex
• An Ensemble Semi-Supervised Adaptive Resonance Theory Model with Explanation Capability for Pattern Classification
• One-shot skill assessment in high-stakes domains with limited data via meta learning
• Uncertainty Aware Neural Network from Similarity and Sensitivity
• Using Bayesian Deep Learning to infer Planet Mass from Gaps in Protoplanetary Disks
• Temperature as Uncertainty in Contrastive Learning
• Data-driven modeling of hypersonic reentry flow with heat and mass transfer
• Transfer learning-based physics-informed convolutional neural network for simulating flow in porous media with time-varying controls
• Deep Evidential Learning for Radiotherapy Dose Prediction
• Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
• Understanding the Impact of Semi-numeric Reionization Models when using CNNs
• Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL
• Bias-Reduced Neural Networks for Parameter Estimation in Quantitative MRI
• Constraining cosmological parameters from N-body simulations with Variational Bayesian Neural Networks
• Stochastic Modeling of Inhomogeneities in the Aortic Wall and Uncertainty Quantification using a Bayesian Encoder-Decoder Surrogate
• Uncertainty-Aware Segmentation Quality Prediction via Deep Learning Bayesian Modeling: Comprehensive Evaluation and Interpretation on Skin Cancer and Liver Segmentation
• Interpretable Uncertainty Quantification in AI for HEP
• Probabilistic deep learning approach for targeted hybrid organic-inorganic perovskites
• Log-Gaussian Gamma Processes for Training Bayesian Neural Networks in Raman and CARS Spectroscopies
• Deep Ensembles from a Bayesian Perspective
• Review of Physics-based and Data-driven Multiscale Simulation Methods for Computational Fluid Dynamics and Nuclear Thermal Hydraulics
• Machine Learning Methods for the Design and Operation of Liquid Rocket Engines -- Research Activities at the DLR Institute of Space Propulsion
• Bayesian deep learning for cosmic volumes with modified gravity
• Causal Inference with Latent Variables: Recent Advances and Future Prospectives
• Deep Huber quantile regression networks
• Unified Uncertainty Estimation for Cognitive Diagnosis Models
• PI3NN: Out-of-distribution-aware prediction intervals from three neural networks
• Fast and Reliable Probabilistic Face Embeddings in the Wild
• Uncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach
• Uncertainty Quantification of Surrogate Models using Conformal Prediction
• Analyzing Uncertainty Quantification in Statistical and Deep Learning Models for Probabilistic Electricity Price Forecasting
• Cycle Consistency-based Uncertainty Quantification of Neural Networks in Inverse Imaging Problems
• A Trustworthiness Score to Evaluate DNN Predictions
• Connect the Dots: In Situ 4D Seismic Monitoring of CO2 Storage with Spatio-temporal CNNs
• aSAGA: Automatic Sleep Analysis with Gray Areas
• Theoretical characterization of uncertainty in high-dimensional linear classification
• Uncertainty Quantification for Deep Learning
• On the Quality of Uncertainty Estimates from Neural Network Potential Ensembles
• Anomaly Detection using Ensemble Classification and Evidence Theory
• Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control
• Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning
• Single- to multi-fidelity history-dependent learning with uncertainty quantification and disentanglement: application to data-driven constitutive modeling
• Bayesian posterior approximation with stochastic ensembles
• Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships
• Deep Anti-Regularized Ensembles provide reliable out-of-distribution uncertainty quantification
• A review of machine learning concepts and methods for addressing challenges in probabilistic hydrological post-processing and forecasting
• Graph-accelerated non-intrusive polynomial chaos expansion using partially tensor-structured quadrature rules for uncertainty quantification
• Uncertainty Calibration for Counterfactual Propensity Estimation in Recommendation
• Object Detection as Probabilistic Set Prediction
• Graceful Degradation and Related Fields
• Testing Human-Hand Segmentation on In-Distribution and Out-of-Distribution Data in Human-Robot Interactions Using a Deep Ensemble Model
• Learning to Map for Active Semantic Goal Navigation
• A Priori Uncertainty Quantification of Reacting Turbulence Closure Models using Bayesian Neural Networks
• A Bayesian Evaluation Framework for Subjectively Annotated Visual Recognition Tasks
• Seven challenges for harmonizing explainability requirements
• Improved context-sensitive transformer model for inland vessel trajectory prediction
• Online Decision-Making Under Uncertainty for Vehicle-to-Building Systems
• Evaluating the Quality of the Quantified Uncertainty for (Re)Calibration of Data-Driven Regression Models
• Multi-Exit Kolmogorov-Arnold Networks: enhancing accuracy and parsimony
• Reliable Classification with Conformal Learning and Interval-Type 2 Fuzzy Sets
• Dual-Splitting Conformal Prediction for Multi-Step Time Series Forecasting
• Risks of ignoring uncertainty propagation in AI-augmented security pipelines
• LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data
• Robust quantum dots charge autotuning using neural network uncertainty
• Interpretable machine learning approach for electron antineutrino selection in a large liquid scintillator detector
• Uncertainty estimates for semantic segmentation: providing enhanced reliability for automated motor claims handling
• A Stochastic-Geometrical Framework for Object Pose Estimation based on Mixture Models Avoiding the Correspondence Problem
• A Mapping of Assurance Techniques for Learning Enabled Autonomous Systems to the Systems Engineering Lifecycle
• Combined Data and Deep Learning Model Uncertainties: An Application to the Measurement of Solid Fuel Regression Rate
• GoTube: Scalable Stochastic Verification of Continuous-Depth Models
• Energy-Efficient Data Transfer Optimization via Decision-Tree Based Uncertainty Reduction
• torchosr -- a PyTorch extension package for Open Set Recognition models evaluation in Python
• Trustworthy Long-Tailed Classification
• Uncertainties of Satellite-based Essential Climate Variables from Deep Learning
• Identifying Incorrect Classifications with Balanced Uncertainty
• Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS) challenge results
• From ANN to BNN: Inferring Reionization Parameters using Uncertainty-aware Emulators of 21-cm Summaries
• Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks
• SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations
• The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis
• Towards Generative Location Awareness for Disaster Response: A Probabilistic Cross-view Geolocalization Approach
• Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification
• Uncertainty Propagation in Node Classification
• Document Classification Pattern Recognition via Information Fusion: A Systematic Review of Multimodal and Multiview Representation Approaches
• I-GLIDE: Input Groups for Latent Health Indicators in Degradation Estimation
• A Collaborative Content Moderation Framework for Toxicity Detection based on Conformalized Estimates of Annotation Disagreement
• Looking at the posterior: accuracy and uncertainty of neural-network predictions
• Uncertainty quantification and stability of neural operators for prediction of three-dimensional turbulence
• Femtosecond pulse parameter estimation from photoelectron momenta using machine learning
• Learning Pole Structures of Hadronic States using Predictive Uncertainty Estimation
• Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control
• Neural network analysis of X-ray polarimeter data
• Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization
• PULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentation
• Uncertainty-driven training for three-dimensional calibrated lung nodule classification
• EchoingECG: An Electrocardiogram Cross-Modal Model for Echocardiogram Tasks
• Uncertainty-Aware Robust Learning on Noisy Graphs
• Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference
• Partial sequence labeling with structured Gaussian Processes
• What classifiers know what they don't?
• Navigating Uncertainties in Machine Learning for Structural Dynamics: A Comprehensive Survey of Probabilistic and Non-Probabilistic Approaches in Forward and Inverse Problems
• SEF: A Method for Computing Prediction Intervals by Shifting the Error Function in Neural Networks
• Measurement of Hybrid Rocket Solid Fuel Regression Rate for a Slab Burner using Deep Learning
• Can Uncertainty Quantification Improve Learned Index Benefit Estimation?
• Last-layer committee machines for uncertainty estimations of benthic imagery
• CASU2Net: Cascaded Unification Network by a Two-step Early Fusion for Fault Detection in Offshore Wind Turbines
• manvr3d: A Platform for Human-in-the-loop Cell Tracking in Virtual Reality
• Accelerating Ensemble Error Bar Prediction with Single Models Fits
• Bayesian Transformer for Pan-Arctic Sea Ice Concentration Mapping and Uncertainty Estimation using Sentinel-1, RCM, and AMSR2 Data
• Multivariate Uncertainty Quantification with Tomographic Quantile Forests
• A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping
• Geographically-Weighted Weakly Supervised Bayesian High-Resolution Transformer for 200m Resolution Pan-Arctic Sea Ice Concentration Mapping and Uncertainty Estimation using Sentinel-1, RCM, and AMSR2 Data
• ExoDNN: Boosting exoplanet detection with artificial intelligence. Application to Gaia Data Release 3