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

2015/06/06 by Yarin Gal, Zoubin Ghahramani, Gal, Yarin +1 · 1 voice · 1,230 citations
Computer Science · Mathematics · Physics and Astronomy · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Model Reduction and Neural Networks #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1506.02142

12 pages, 6 figures; fixed a mistake with standard error and added a new table with updated results (marked "Update [October 2016]"); Published in ICML 2016

openalex publication_date 2015/06/06 · arxiv published 2015/06/06 · arxiv created 2016/10/04 · arxiv updated 2016/10/05 · openalex created_date 2019/07/30 · openalex updated_date 2026/07/28

Abstract

Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost. In this paper we develop a new theoretical framework casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes. A direct result of this theory gives us tools to model uncertainty with dropout NNs -- extracting information from existing models that has been thrown away so far. This mitigates the problem of representing uncertainty in deep learning without sacrificing either computational complexity or test accuracy. We perform an extensive study of the properties of dropout's uncertainty. Various network architectures and non-linearities are assessed on tasks of regression and classification, using MNIST as an example. We show a considerable improvement in predictive log-likelihood and RMSE compared to existing state-of-the-art methods, and finish by using dropout's uncertainty in deep reinforcement learning.

Citations

• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• Auto-Encoding Variational Bayes
• A Practical Bayesian Framework for Backpropagation Networks
• Gradient-based learning applied to document recognition
• Variational Bayesian Inference with Stochastic Search
• Practical Bayesian Optimization of Machine Learning Algorithms

Cited by

• DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton
• Verbalized Particle Posterior: Bayesian Inference over Natural Language Hypotheses
• Calibrated Tree-Neural Fusion for Fine-Grained Vegetation Community Classification
• Unifying Active Learning and Semi-Supervised Learning for Medical Image Segmentation
• Trustworthy Medical Segmentation: Uncertainty-Aware U-Net Evaluation Under Clinical Image Degradation
• Visible-Light Imaging Diagnosis of Neutral Particle Emission Tomography in the Tokamak Divertor: An Efficient Transformer-based Surrogate Model
• A Unified Framework for Uncertainty-Aware Explainable Artificial Intelligence: A Case Study in Power Quality Disturbance Classification
• Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
• Am I Confused or Is This Confusing?: Deep Ensembles for ENSO Uncertainty Quantification
• Solomonoff-Inspired Hypothesis Ranking with LLMs for Prediction Under Uncertainty
• GraviBERT: Transformer-based inference for gravitational-wave time series
• Autonomous Uncertainty Quantification for Computational Point-of-care Sensors
• Assessing Coronary Microvascular Dysfunction using Angiography-based Data-driven Methods
• Over-the-Air Goal-Oriented Communications
• UbiQVision: Quantifying Uncertainty in XAI for Image Recognition
• Attention Fusion for Bridge Deck Delamination Detection
• Generative Bayesian Hyperparameter Tuning
• Multi-Layer Confidence Scoring for Detection of Out-of-Distribution Samples, Adversarial Attacks, and In-Distribution Misclassifications
• Dual Model Deep Learning for Alzheimer Prognostication
• Out-of-Distribution Detection in Molecular Complexes via Diffusion Models for Irregular Graphs
• What is Stochastic Supervenience?
• Detection of AI Generated Images Using Combined Uncertainty Measures and Particle Swarm Optimised Rejection Mechanism
• Toward Ethical AI Through Bayesian Uncertainty in Neural Question Answering
• The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems
• EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecasting
• Unreliable Uncertainty Estimates with Monte Carlo Dropout
• Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes
• Expert Switching for Robust AAV Landing: A Dual-Detector Framework in Simulation
• From Overfitting to Reliability: Introducing the Hierarchical Approximate Bayesian Neural Network
• General OOD Detection via Model-aware and Subspace-aware Variable Priority
• Calibrating Uncertainty for Zero-Shot Adversarial CLIP
• Selective Conformal Risk Control
• Flow matching Operators for Residual-Augmented Probabilistic Learning of Partial Differential Equations
• PerNodeDrop: A Method Balancing Specialized Subnets and Regularization in Deep Neural Networks
• PIS: A Generalized Physical Inversion Solver for Arbitrary Sparse Observations via Set Conditioned Flow Matching
• Uncertainty Quantification for Machine Learning: One Size Does Not Fit All
• Supervised Learning of Random Neural Architectures Structured by Latent Random Fields on Compact Boundaryless Multiply-Connected Manifolds
• CheXmask-U: Quantifying uncertainty in landmark-based anatomical segmentation for X-ray images
• Uncertainty-Preserving QBNNs: Multi-Level Quantization of SVI-Based Bayesian Neural Networks for Image Classification
• Quantifying Uncertainty in Machine Learning-Based Pervasive Systems: Application to Human Activity Recognition
• Graph-Based Bayesian Optimization for Quantum Circuit Architecture Search with Uncertainty Calibrated Surrogates
• Semantic Geometry for policy-constrained interpretation
• MelanomaNet: Explainable Deep Learning for Skin Lesion Classification
• WTNN: Weibull-Tailored Neural Networks for survival analysis
• Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning
• Physics-Guided Deepfake Detection for Voice Authentication Systems
• Uncertainty Quantification for Scientific Machine Learning using Sparse Variational Gaussian Process Kolmogorov-Arnold Networks (SVGP KAN)
• Dflow-SUR: Enhancing Generative Aerodynamic Inverse Design using Differentiation Throughout Flow Matching
• Zero-Splat TeleAssist: A Zero-Shot Pose Estimation Framework for Semantic Teleoperation
• PVeRA: Probabilistic Vector-Based Random Matrix Adaptation
• ϕ-Table: A Statistical Explanation for Global SHAP
• Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models
• Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood
• UncertaintyZoo: A Unified Toolkit for Quantifying Predictive Uncertainty in Deep Learning Systems
• Scenario-aware Uncertainty Quantification for Trajectory Prediction with Statistical Guarantees
• Intra-Class Probabilistic Embeddings for Uncertainty Estimation in Vision-Language Models
• Knowing when to trust machine-learned interatomic potentials
• Bayes-DIC Net: Estimating Digital Image Correlation Uncertainty with Bayesian Neural Networks
• Adaptive Regime-Switching Forecasts with Distribution-Free Uncertainty: Deep Switching State-Space Models Meet Conformal Prediction
• U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences
• Credal Graph Neural Networks
• Conformal Correction for Efficiency May be at Odds with Entropy
• Detecting AI Hallucinations in Finance: An Information-Theoretic Method Cuts Hallucination Rate by 92%
• Where to Measure: Epistemic Uncertainty-Based Sensor Placement with ConvCNPs
• Probabilistic Neuro-Symbolic Reasoning for Sparse Historical Data: A Framework Integrating Bayesian Inference, Causal Models, and Game-Theoretic Allocation
• Neural network-based deconvolution for GeV-Scale Gamma-Ray Spectroscopy
• CLAPS: Aleatoric-Epistemic Scaling via Last-Layer Laplace for Conformal Regression
• Building Trustworthy AI for Materials Discovery: From Autonomous Laboratories to Z-scores
• Sleep Apnea Detection on a Wireless Multimodal Wearable Device Without Oxygen Flow Using a Mamba-based Deep Learning Approach
• MicroProbe: Efficient Reliability Assessment for Foundation Models with Minimal Data
• Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
• Probabilistic Modeling of Multi-rater Medical Image Segmentation for Diversity and Personalization
• TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion
• TIE: A Training-Inversion-Exclusion Framework for Visually Interpretable and Uncertainty-Guided Out-of-Distribution Detection
• Epistemic and Aleatoric Uncertainty Quantification in Weather and Climate Models
• Accelerated Execution of Bayesian Neural Networks using a Single Probabilistic Forward Pass and Code Generation
• Improving motor imagery decoding methods for an EEG-based mobile brain-computer interface in the context of the 2024 Cybathlon
• Active Learning for GCN-based Action Recognition
• Beyond Accuracy: An Empirical Study of Uncertainty Estimation in Imputation
• Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference
• I-GLIDE: Input Groups for Latent Health Indicators in Degradation Estimation
• Structure-Aware Prototype Guided Trusted Multi-View Classification
• Geometric Calibration and Neutral Zones for Uncertainty-Aware Multi-Class Classification
• Active learning with physics-informed neural networks for optimal sensor placement in deep tunneling through transversely isotropic elastic rocks
• PaTAS: A Framework for Trust Propagation in Neural Networks Using Subjective Logic
• Neural surrogates for designing gravitational wave detectors
• Uncertainty-Aware Dual-Student Knowledge Distillation for Efficient Image Classification
• Uncertainty of Network Topology with Applications to Out-of-Distribution Detection
• Robust Multimodal Sentiment Analysis of Image-Text Pairs by Distribution-Based Feature Recovery and Fusion
• Robust and Generalizable GNN Fine-Tuning via Uncertainty-aware Adapter Learning
• Lightweight Transformer Framework for Weakly Supervised Semantic Segmentation
• Physics-Guided Deep Learning for Heat Pump Stress Detection: A Comprehensive Analysis on When2Heat Dataset
• PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation
• ReVeal-MT: A Physics-Informed Neural Network for Multi-Transmitter Radio Environment Mapping
• Uncertainty-Aware Federated Learning for Cyber-Resilient Microgrid Energy Management
• CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation
• Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networks
• Uncertainty Quantification in Melody Estimation using Histogram Representation
• MedBayes-Lite: A Clinical Uncertainty Governance Layer for Risk-Aware Medical Decision Support
• Black-Box Uncertainty Estimation for Deep Learning Models in Atomistic Simulations
• Thinking, Faithful and Stable: Mitigating Hallucinations in LLMs
• Attention-Based Feature Online Conformal Prediction for Time Series
• Learning from Imperfect Labels: A Physics-Aware Neural Operator with Application to DAS Data Denoising
• Controlling False Positives in Image Segmentation via Conformal Prediction
• As If We've Met Before: LLMs Exhibit Certainty in Recognizing Seen Files
• nnMIL: A generalizable multiple instance learning framework for computational pathology
• Uncertainty-Calibrated Prediction of Randomly-Timed Biomarker Trajectories with Conformal Bands
• Uncertainty-aware Physics-informed Neural Networks for Robust CARS-to-Raman Signal Reconstruction
• Online Adaptive Probabilistic Safety Certificate with Language Guidance
• Calibrated Decomposition of Aleatoric and Epistemic Uncertainty in Deep Features for Inference-Time Adaptation
• Bayesian--AI Fusion for Epidemiological Decision Making: Calibrated Risk, Honest Uncertainty, and Hyperparameter Intelligence
• PIRA: Preference-Oriented Instruction-Tuned Reward Models with Dual Aggregation
• Multimodal Posterior Sampling-based Uncertainty in PD-L1 Segmentation from H&E Images
• A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts
• Taming Object Hallucinations with Verified Atomic Confidence Estimation
• Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification
• Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models
• SHRUG-FM: Reliability-Aware Foundation Models for Earth Observation
• Continuum Dropout for Neural Differential Equations
• Bayesian Neural Networks with Monte Carlo Dropout for Probabilistic Electricity Price Forecasting
• Benchmarking GNNs for OOD Materials Property Prediction with Uncertainty Quantification
• Towards a Machine Learning Solution for Hubble Tension: Physics-Informed Neural Network (PINN) Analysis of Tsallis Holographic Dark Energy in Presence of Neutrinos
• Uncertainty Calibration of Multi-Label Bird Sound Classifiers
• Operational machine learning for remote spectroscopic detection of CH₄ point sources
• Spectrum and Physics-Informed Neural Networks (SaPINNs) for Input-State-Parameter Estimation in Dynamic Systems Subjected to Natural Hazards-Induced Excitation
• Bayesian Uncertainty Quantification with Anchored Ensembles for Robust EV Power Consumption Prediction
• Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning
• QiVC-Net: Quantum-Inspired Variational Convolutional Network, with Application to Biosignal Classification
• On Joint Regularization and Calibration in Deep Ensembles
• Temporal Zoom Networks: Distance Regression and Continuous Depth for Efficient Action Localization
• Uncertainty Modeling for Multi-Objective RTA Interception with Distillation Acceleration
• Few-Shot Multimodal Medical Imaging: A Theoretical Framework
• Trustworthy Quantum Machine Learning: A Roadmap for Reliability, Robustness, and Security in the NISQ Era
• Efficient Quantification of Time-Series Prediction Error: Optimal Selection Conformal Prediction
• Uncertainty Guided Online Ensemble for Non-stationary Data Streams in Fusion Science
• Reducing Robotic Upper-Limb Assessment Time While Maintaining Precision: A Time Series Foundation Model Approach
• A systematic evaluation of uncertainty quantification techniques in deep learning: a case study in photoplethysmography signal analysis
• CausalGuard: A Smart System for Detecting and Preventing False Information in Large Language Models
• Parameter Averaging in Link Prediction
• Covariance Last-Layer Ensembles: Function-Space Diversity for Efficient Uncertainty Quantification
• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations
• Uncertainty-Guided LLM Semantic Augmentation for Heterogeneous Treatment Effect Estimation
• Calibrated Uncertainty Sampling for Active Learning
• From Keypoints to Predictive Distributions: Post-Hoc Uncertainty for YOLO-Pose Models
• MedFusionT5: Cross-Modal Attention Boosts Semantic Quality and Reduces Hallucinations in Dental AI
• Structurally Separated Uncertainty in Supervised Latent Variable Models
• Bayesian Inference via GeTe x ‐OTS Based Stochastic Synapse for Uncertainty‐Aware Medical Diagnostics
• Energy-Efficient Autonomous Driving with Adaptive Perception and Robust Decision
• Selective Diabetic Retinopathy Screening with Accuracy-Weighted Deep Ensembles and Entropy-Guided Abstention
• UP2D: Uncertainty-aware Progressive Pseudo-label Denoising for Source-Free Domain Adaptive Medical Image Segmentation
• Loss Given Default Prediction Under Measurement-Induced Mixture Distributions: An Information-Theoretic Approach
• Bayesian Neural Networks vs. Mixture Density Networks: Theoretical and Empirical Insights for Uncertainty-Aware Nonlinear Modeling
• FruitProm: Probabilistic Maturity Estimation and Detection of Fruits and Vegetables
• Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards
• Synergizing chemical and AI communities for advancing laboratories of the future
• Bayesian Speech synthesizers Can Learn from Multiple Teachers
• When Good Fit Goes Bad: Identifying and Minimising Overfitting in Ecological Niche Models
• Uncertainty Calibration in Molecular Machine Learning: Comparing Evidential and Ensemble Approaches
• IAEmu: Learning Galaxy Intrinsic Alignment Correlations
• Semantic-Guided Cross-Sensor Super Resolution of Remote Sensing Images: A Gated Dual Conditioning Flow Matching Model
• Multi-Modal Fact-Verification Framework for Reducing Hallucinations in Large Language Models
• Uncertainty-Aware Autonomous Vehicles: Predicting the Road Ahead
• Variational Polya Tree
• AI-Driven Carbon Monitoring: Transformer-Based Reconstruction of Atmospheric CO2 in Canadian Poultry Regions
• Deep Gaussian Processes for Functional Maps
• Frequentist Validity of Epistemic Uncertainty Estimators
• Worst-Case Distance-Aware Error Bounds for Neural Networks
• Interpretable epistemic uncertainty decomposition in sequential generative models via polynomial chaos surrogates
• Efficient semantic uncertainty quantification in language models via diversity-steered sampling
• EBOP MAVEN: A machine learning model to estimate the input parameters for analytic fitting of detached eclipsing binary light curves
• Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems
• Bayesian Inference of Primordial Magnetic Field Parameters from CMB with Spherical Graph Neural Networks
• Ask a Strong LLM Judge when Your Reward Model is Uncertain
• Federated Learning via Meta-Variational Dropout
• An Empirical Study on Variance-based MC Dropout Uncertainty-Error Correlation in 2D Brain Tumor Segmentation
• A Tutorial on Cognitive Biases in Agentic AI-Driven 6G Autonomous Networks
• BATIS: Bayesian Approaches for Targeted Improvement of Species Distribution Models
• Knowledge Distillation of Uncertainty using Deep Latent Factor Model
• No Intelligence Without Statistics: The Invisible Backbone of Artificial Intelligence
• Uncertainty evaluation of segmentation models for Earth observation
• Neural Variational Dropout Processes
• A Climate-Aware Deep Learning Framework for Generalizable Epidemic Forecasting
• Image augmentation with invertible networks in interactive satellite image change detection
• Uncertainty Estimation by Flexible Evidential Deep Learning
• Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
• FST.ai 2.0: An Explainable AI Ecosystem for Fair, Fast, and Inclusive Decision-Making in Olympic and Paralympic Taekwondo
• Functional Distribution Networks (FDN)
• Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories
• Uncertainty-aware data assimilation through variational inference
• Trading with the Devil: Risk and Return in Foundation Model Strategies
• Benchmarking Out-of-Distribution Detection for Plankton Recognition: A Systematic Evaluation of Advanced Methods in Marine Ecological Monitoring
• Confidence-Weighted Semi-Supervised Learning for Skin Lesion Segmentation Using Hybrid CNN-Transformer Networks
• Adaptive Individual Uncertainty under Out-Of-Distribution Shift with Expert-Routed Conformal Prediction
• ObjectTransforms for Uncertainty Quantification and Reduction in Vision-Based Perception for Autonomous Vehicles
• Automated C-Arm Positioning via Conformal Landmark Localization
• Uncertainty-Aware Extreme Point Tracing for Weakly Supervised Ultrasound Image Segmentation
• Fine-tuning LLMs with variational Bayesian last layer for high-dimensional Bayesian optimization
• Measure-Theoretic Anti-Causal Representation Learning
• Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation
• Rock Classification through Knowledge-Enhanced Deep Learning: A Hybrid Mineral-Based Approach
• Convergence, design and training of continuous-time dropout as a random batch method
• Likelihood-free inference of phylogenetic tree posterior distributions
• Market-Driven Subset Selection for Budgeted Training
• Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions
• Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning
• Uncertainty-Aware, Risk-Adaptive Access Control for Agentic Systems using an LLM-Judged TBAC Model
• An AI dose engine for fast carbon ion treatment planning
• Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation
• ΔEnergy: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
• Uncertainty-Aware Post-Detection Framework for Enhanced Fire and Smoke Detection in Compact Deep Learning Models
• Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learning
• Calibrating the Full Predictive Class Distribution of 3D Object Detectors for Autonomous Driving
• Escaping the Agreement Trap: Defensibility Signals for Evaluating Rule-Governed AI
• SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models
• Failure Prediction at Runtime for Generative Robot Policies
• When a Robot is More Capable than a Human: Learning from Constrained Demonstrators
• VirDA: Reusing Backbone for Unsupervised Domain Adaptation with Visual Reprogramming
• Scalable Offline Metrics for Autonomous Driving
• Revisiting Hallucination Detection with Effective Rank-based Uncertainty
• Parallel Test-Time Scaling for Latent Reasoning Models
• PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation
• Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation
• MoGU: Mixture-of-Gaussians with Uncertainty-based Gating for Time Series Forecasting
• Label-frugal satellite image change detection with generative virtual exemplar learning
• Robust Classification of Oral Cancer with Limited Training Data
• Early wind turbine alarm prediction based on machine learning: AlarmForecasting
• MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation
• UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene
• Mangrove3D: Terrestrial Laser Scanning Dataset for Coastal Mangrove Forests
• How Confident are Video Models? Empowering Video Models to Express their Uncertainty
• Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics
• Conformalized Gaussian processes for online uncertainty quantification over graphs
• Scalable deep fusion of spaceborne lidar and synthetic aperture radar for global forest structural complexity mapping
• Uncertainty assessment in satellite-based greenhouse gas emissions estimates using emulated atmospheric transport
• Uncertainty in Machine Learning
• Out-of-Distribution Detection from Small Training Sets using Bayesian Neural Network Classifiers
• Latent Uncertainty Representations for Video-based Driver Action and Intention Recognition
• When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA
• HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model
• Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning
• UGround: Towards Unified Visual Grounding with Unrolled Transformers
• Training-Free Out-Of-Distribution Segmentation With Foundation Models
• Uncertainty Quantification In Surface Landmines and UXO Classification Using MC Dropout
• Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering
• Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs
• What Did I Learn? Operational Competence Assessment for AI-Based Trajectory Planners
• Uncertainty Quantification for Regression using Proper Scoring Rules
• Dynamic Meta-Learning for Adaptive XGBoost-Neural Ensembles
• Uncertainty-Aware Deep Learning for Wildfire Danger Forecasting
• Uncertainty-Guided Expert-AI Collaboration for Efficient Soil Horizon Annotation
• Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model
• The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration
• Stochastic Bottleneck: Rateless Auto-Encoder for Flexible Dimensionality Reduction
• Learn to Propagate Reliably on Noisy Affinity Graphs
• Exploring Uncertainty in Deep Learning for Construction of Prediction Intervals
• DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction
• Robust Multi-Modal Face Anti-Spoofing with Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-Labels, and Model Degradation
• Demystifying Brain Tumour Segmentation Networks: Interpretability and Uncertainty Analysis
• The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models
• Calibration of Model Uncertainty for Dropout Variational Inference
• Quantifying Epistemic Uncertainty in Deep Learning
• Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropout
• When Can AI Models Explain Learning? Validity Criteria for AI as Cognitive Models in Education
• Stochastic activations
• Learnable Conformal Prediction with Context-Aware Nonconformity Functions for Robotic Planning and Perception
• Enhancing Safety in Diabetic Retinopathy Detection: Uncertainty-Aware Deep Learning Models with Rejection Capabilities
• Multi-modal Bayesian Neural Network Surrogates with Conjugate Last-Layer Estimation
• Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
• Uncertainty-Aware Knowledge Tracing Models
• Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
• Classification Uncertainty of Deep Neural Networks Based on Gradient Information
• Short-term Load Forecasting with Deep Residual Networks
• Deep Contextual Multi-armed Bandits
• MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model
• Weight Pruning and Uncertainty in Radio Galaxy Classification
• The Sensitivity of Variational Bayesian Neural Network Performance to Hyperparameters
• APPLI: Adaptive Planner Parameter Learning From Interventions
• Uncertainty in Semantic Language Modeling with PIXELS
• Confidence Calibration in Large Language Model-Based Entity Matching
• Witness Evidence Portfolios: Single-Prefill Risk Detection for Closed Multimodal Answers
• BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
• Pathologies in priors and inference for Bayesian transformers
• Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation
• Leveraging Visual Question Answering for Image-Caption Ranking
• Ellipse Regression with Predicted Uncertainties for Accurate Multi-View 3D Object Estimation
• Approaching Neural Network Uncertainty Realism
• On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration
• Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability
• ReDiff: Reliability-Guided Diffusion for Trustworthy Ultra-Low-Field to High-Field MRI Synthesis
• AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers
• End-to-end deep attention-based multitask pipeline for predicting uncertainty-quantified peptide properties from mass spectrometry data
• Generalizing from a few environments in safety-critical reinforcement learning
• Amortising Inference and Meta-Learning Priors in Neural Networks
• GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data
• Deep Gaussian Processes for Regression using Approximate Expectation Propagation
• Adversarial Phenomenon in the Eyes of Bayesian Deep Learning
• Bayesian Active Learning for Wearable Stress and Affect Detection
• Uncertainty Estimation in Deep Neural Networks for Point Cloud Segmentation in Factory Planning
• Physics-informed machine learning: case studies for weather and climate modelling
• How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks
• Towards Trustworthy Breast Tumor Segmentation in Ultrasound using Monte Carlo Dropout and Deep Ensembles for Epistemic Uncertainty Estimation
• Evaluating the Quality of the Quantified Uncertainty for (Re)Calibration of Data-Driven Regression Models
• Dropping Networks for Transfer Learning
• Data-Efficient ASR Personalization for Non-Normative Speech Using an Uncertainty-Based Phoneme Difficulty Score for Guided Sampling
• Probabilistic Machine Learning for Uncertainty-Aware Diagnosis of Industrial Systems
• Confidence-Aware Routing for Large Language Model Reliability Enhancement: A Multi-Signal Approach to Pre-Generation Hallucination Mitigation
• Flow marching for a generative PDE foundation model
• Analyzing Uncertainty Quantification in Statistical and Deep Learning Models for Probabilistic Electricity Price Forecasting
• Is It Certainly a Deepfake? Reliability Analysis in Detection & Generation Ecosystem
• Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise
• nn-dependability-kit: Engineering Neural Networks for Safety-Critical Autonomous Driving Systems
• Bayesian Uncertainty Matching for Unsupervised Domain Adaptation
• Improving Active Learning for Melody Estimation by Disentangling Uncertainties
• Towards Open-Ended Discovery for Low-Resource NLP
• Influence of Classification Task and Distribution Shift Type on OOD Detection in Fetal Ultrasound
• Uncertainty-Supervised Interpretable and Robust Evidential Segmentation
• Conformalized Quantile Regression
• 3D Reconstruction in Canonical Co-ordinate Space from Arbitrarily Oriented 2D Images
• ScenGAN: Attention-Intensive Generative Model for Uncertainty-Aware Renewable Scenario Forecasting
• Closing the Loop Inside Neural Networks: Causality-Guided Layer Adaptation for Fault Recovery Control
• AHA -- Predicting What Matters Next: Online Highlight Detection Without Looking Ahead
• Uncertainty Quantification of Large Language Models using Approximate Bayesian Computation
• Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks
• Bayesian Physics Informed Neural Networks for Reliable Transformer Prognostics
• Phylogenetic Methods Meet Deep Learning
• Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations
• Boosting Active Learning with Knowledge Transfer
• Improving the Reliability of Semantic Segmentation of Medical Images by Uncertainty Modeling with Bayesian Deep Networks and Curriculum Learning
• Being Bayesian about Categorical Probability
• URNet: Uncertainty-aware Refinement Network for Event-based Stereo Depth Estimation
• Improving Building Segmentation for Off-Nadir Satellite Imagery
• Anchor-MoE: A Mean-Anchored Mixture of Experts For Probabilistic Regression
• BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection
• A Conformal Prediction Framework for Uncertainty Quantification in Physics-Informed Neural Networks
• Multi-robot Multi-source Localization in Complex Flows with Physics-Preserving Environment Models
• Learning a Predictive Model for Music Using PULSE
• Dynamic Aware: Adaptive Multi-Mode Out-of-Distribution Detection for Trajectory Prediction in Autonomous Vehicles
• Towards Open World Object Detection
• Out of Distribution Detection in Self-adaptive Robots with AI-powered Digital Twins
• From Machine Learning to Robotics: Challenges and Opportunities for\n Embodied Intelligence
• MEGAN: Mixture of Experts for Robust Uncertainty Estimation in Endoscopy Videos
• Similarity-Distance-Magnitude Activations
• Surrogate Modelling of Proton Dose with Monte Carlo Dropout Uncertainty Quantification
• Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses
• On the Decision Boundary of Deep Neural Networks
• Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
• ColabFold: making protein folding accessible to all
• Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons
• Bayesian Graph Neural Networks with Adaptive Connection Sampling
• Deep Convolutional Networks as shallow Gaussian Processes
• Post-Hoc Split-Point Self-Consistency Verification for Efficient, Unified Quantification of Aleatoric and Epistemic Uncertainty in Deep Learning
• Integrating Deep Neural Networks with Full-waveform Inversion: Reparametrization, Regularization, and Uncertainty Quantification
• Selective Risk Certification for LLM Outputs via Information-Lift Statistics: PAC-Bayes, Robustness, and Skeleton Design
• Road Obstacle Video Segmentation
• Addressing Failure Prediction by Learning Model Confidence
• Comparison of Deterministic and Probabilistic Machine Learning Algorithms for Precise Dimensional Control and Uncertainty Quantification in Additive Manufacturing
• Quality Management of Machine Learning Systems
• Travel Time and Weather-Aware Traffic Forecasting in a Conformal Graph Neural Network Framework
• Hypothesis Disparity Regularized Mutual Information Maximization
• Deep Ensembles: A Loss Landscape Perspective
• Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process
• Uncertainty-Aware Retinal Vessel Segmentation via Ensemble Distillation
• Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost
• Stochastic Neural Network with Kronecker Flow
• Mutual Information Tracks Policy Coherence in Reinforcement Learning
• Kalman Bayesian Transformer
• No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes
• GraphPPD: Posterior Predictive Modelling for Graph-Level Inference
• Vendi Information Gain for Active Learning and its Application to Ecology
• Monte Carlo dropout increases model repeatability
• CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
• Uncertainty Propagation Networks for Neural Ordinary Differential Equations
• Accuracy, Uncertainty, and Adaptability of Automatic Myocardial ASL Segmentation using Deep CNN
• Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks
• Quantifying Out-of-Training Uncertainty of Neural-Network based Turbulence Closures
• Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data
• Improving Greenland Bed Topography Mapping with Uncertainty-Aware Graph Learning on Sparse Radar Data
• Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Can deep learning beat numerical weather prediction?
• Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Driving
• Sparse Uncertainty Representation in Deep Learning with Inducing Weights
• IBN: An Interpretable Bidirectional-Modeling Network for Multivariate Time Series Forecasting with Variable Missing
• Physics-Informed Neural Networks in Clean Combustion: A Pathway to Sustainable Aerospace Propulsion
• Stochastic Aggregation in Graph Neural Networks
• Machine-Learned HASDM Model with Uncertainty Quantification
• A High-order Backpropagation Algorithm for Neural Stochastic Differential Equation Model
• Adaptive, Distribution-Free Prediction Intervals for Deep Networks
• Rule-Based Moral Principles for Explaining Uncertainty in Natural Language Generation
• Dynamic Knowledge Distillation for Pre-trained Language Models
• Uncertainty Estimation using Variance-Gated Distributions
• Methodological Insights into Structural Causal Modelling and Uncertainty-Aware Forecasting for Economic Indicators
• Asymmetry Vulnerability and Physical Attacks on Online Map Construction for Autonomous Driving
• TGLF-SINN: Deep Learning Surrogate Model for Accelerating Turbulent Transport Modeling in Fusion
• A guide to machine learning for biologists
• Performance of Conformal Prediction in Capturing Aleatoric Uncertainty
• Simulation Priors for Data-Efficient Deep Learning
• GUIDe: Generative and Uncertainty-Informed Inverse Design for On-Demand Nonlinear Functional Responses
• LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood
• Data Uncertainty Learning in Face Recognition
• Uncertainty based Class Activation Maps for Visual Question Answering
• Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation
• Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs
• Uncertainty Quantification and Propagation for ACORN, a geometric deep learning tracking pipeline for HEP experiments
• An evaluation of word-level confidence estimation for end-to-end automatic speech recognition
• Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
• TyXe: Pyro-based Bayesian neural nets for Pytorch
• What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?
• Can Active Learning Preemptively Mitigate Fairness Issues?
• Deep Mixed Effect Model using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare
• TopoMap: A Feature-based Semantic Discriminator of the Topographical Regions in the Test Input Space
• TRADI: Tracking deep neural network weight distributions for uncertainty estimation
• Deep Neural Network Perception Models and Robust Autonomous Driving Systems
• Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation
• WILDS: A Benchmark of in-the-Wild Distribution Shifts
• Neural Graph Evolution: Towards Efficient Automatic Robot Design
• PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction
• Physics-informed deep generative models
• LiBRe: A Practical Bayesian Approach to Adversarial Detection
• Masked Contrastive Learning for Anomaly Detection
• Exploring accuracy and uncertainty quantification in physics-informed neural networks for inferring microbial community dynamics
• Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
• Diversity inducing Information Bottleneck in Model Ensembles
• DropoutDAgger: A Bayesian Approach to Safe Imitation Learning
• Propagating Uncertainty in Multi-Stage Bayesian Convolutional Neural Networks with Application to Pulmonary Nodule Detection
• Class Similarity-Based Multimodal Classification under Heterogeneous Category Sets
• Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate
• Domain Adaptation via Feature Refinement
• Sampling-based Bayesian Inference with gradient uncertainty
• Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimation
• Prior-Guided Residual Diffusion: Calibrated and Efficient Medical Image Segmentation
• Towards Trustworthy Vital Sign Forecasting: Leveraging Uncertainty for Prediction Intervals
• Why Pool When You Can Flow? Active Learning with GFlowNets
• Practical Evaluation of Out-of-Distribution Detection Methods for Image Classification
• Dropout drops double descent
• Kernel Identification Through Transformers
• Deep Learning for CMB Foreground Removal and Beam Deconvolution: A U-Net GAN Approach
• Entropy-Based Non-Invasive Reliability Monitoring of Convolutional Neural Networks
• Automatic Curriculum Learning through Value Disagreement
• Self-Loop Uncertainty: A Novel Pseudo-Label for Semi-Supervised Medical Image Segmentation
• Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier
• Deep Active Learning for Lung Disease Severity Classification from Chest X-rays: Learning with Less Data in the Presence of Class Imbalance
• Distance-based Confidence Score for Neural Network Classifiers
• Understanding Classifier Mistakes with Generative Models
• Efficient Semi-Supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency
• Zero-shot and few-shot time series forecasting with ordinal regression recurrent neural networks
• Reliable training and estimation of variance networks
• Bayesian Graph Convolutional Neural Networks using Node Copying
• PAUL: Uncertainty-Guided Partition and Augmentation for Robust Cross-View Geo-Localization under Noisy Correspondence
• Conditional Normalizing Flow Surrogate for Monte Carlo Prediction of Radiative Properties in Nanoparticle-Embedded Layers
• Unifying Model Explainability and Robustness via Machine-Checkable Concepts
• Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
• HierCVAE: Hierarchical Attention-Driven Conditional Variational Autoencoders for Multi-Scale Temporal Modeling
• Distance-informed Neural Processes
• The Functional Neural Process
• Uncertainty-Aware Reinforcement Learning for Collision Avoidance
• Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation
• AI-Powered Machine Learning Approaches for Fault Diagnosis in Industrial Pumps
• Optimistic and Pessimistic Neural Networks for Scene and Object Recognition
• Efficient Approximate Inference with Walsh-Hadamard Variational Inference
• Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration
• Autonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphs
• Twin-Boot: Uncertainty-Aware Optimization via Online Two-Sample Bootstrapping
• CUTE-MRI: Conformalized Uncertainty-based framework for Time-adaptivE MRI
• NP-ODE: Neural Process Aided Ordinary Differential Equations for Uncertainty Quantification of Finite Element Analysis
• Effect of Data Augmentation on Conformal Prediction for Diabetic Retinopathy
• Estimating Risk and Uncertainty in Deep Reinforcement Learning
• Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network
• Distilled-3DGS:Distilled 3D Gaussian Splatting
• OmViD: Omni-supervised active learning for video action detection
• Uncertainty Tube Visualization of Particle Trajectories
• BLIPs: Bayesian Learned Interatomic Potentials
• Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning
• Seeing the Many: Exploring Parameter Distributions Conditioned on Features in Surrogates
• SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML
• Block Annotation: Better Image Annotation for Semantic Segmentation with Sub-Image Decomposition
• Uncertainty Propagation in Deep Neural Network Using Active Subspace
• Understanding Uncertainty in Bayesian Deep Learning
• Cost-Sensitive Diagnosis and Learning Leveraging Public Health Data
• Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models
• Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting
• TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML
• Calibrated Reliable Regression using Maximum Mean Discrepancy
• Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness
• A Tutorial on Deep Latent Variable Models of Natural Language
• Design by adaptive sampling
• Segmenting Thalamic Nuclei: T1 Maps Provide a Reliable and Efficient Solution
• An Uncertainty Estimation Framework for Risk Assessment in Deep Learning-based Atrial Fibrillation Classification
• Task-Agnostic Morphology Evolution
• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability
• Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation
• PEdger++: Practical Edge Detection via Assembling Cross Information
• Approximate Inference with Amortised MCMC
• Learning to Predict Trustworthiness with Steep Slope Loss
• Calibrated and uncertain? Evaluating uncertainty estimates in binary classification models
• RAG for Geoscience: What We Expect, Gaps and Opportunities
• A Macro-Micro Weakly-supervised Framework for AS-OCT Tissue Segmentation
• Meta-Reinforcement Learning for Adaptive Motor Control in Changing Robot Dynamics and Environments
• Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification Tasks
• Selective Question Answering under Domain Shift
• Teaching Uncertainty Quantification in Machine Learning through Use Cases
• Hey Human, If your Facial Emotions are Uncertain, You Should Use Bayesian Neural Networks!
• Modeling the Uncertainty in Electronic Health Records: a Bayesian Deep Learning Approach
• GeoMAE: Masking Representation Learning for Spatio-Temporal Graph Forecasting with Missing Values
• Deep density networks and uncertainty in recommender systems
• Synaptic Pruning: A Biological Inspiration for Deep Learning Regularization
• Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring
• Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness
• Towards Robust Active Feature Acquisition
• Calibration Attention: Learning Reliability-Aware Representations for Vision Transformers
• Deep Learning-Based Analysis of Power Consumption in Gasoline, Electric, and Hybrid Vehicles
• Efficient Data-Dependent Learnability
• Meta Off-Policy Estimation
• Human-Alignment and Calibration of Inference-Time Uncertainty in Large Language Models
• ProteoKnight: Convolution-based phage virion protein classification and uncertainty analysis
• Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be Forgotten
• Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution
• Mapping fractional vegetation cover in UAS RGB and multispectral imagery in semi-arid Australian ecosystems using CNN-based semantic segmentation
• Confidence Estimation for Text-to-SQL in Large Language Models
• Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization
• Comparative study of ensemble-based uncertainty quantification methods for neural network interatomic potentials
• Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
• FIVA: Federated Inverse Variance Averaging for Universal CT Segmentation with Uncertainty Estimation
• Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Temporal Grounding
• Cognitive computational neuroscience
• Tractable Sharpness-Aware Learning of Probabilistic Circuits
• EnergyPatchTST: Multi-scale Time Series Transformers with Uncertainty Estimation for Energy Forecasting
• ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning
• Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation
• Uncertainty-aware Predict-Then-Optimize Framework for Equitable Post-Disaster Power Restoration
• Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems
• Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• On Hallucination and Predictive Uncertainty in Conditional Language Generation
• A Generative Model for Sampling High-Performance and Diverse Weights for Neural Networks
• Is Uncertainty Quantification a Viable Alternative to Learned Deferral?
• The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Data
• Hierarchical Gaussian Processes with Wasserstein-2 Kernels
• Model-Agnostic Dynamic Feature Selection with Uncertainty Quantification
• Combining Ensembles and Data Augmentation can Harm your Calibration
• Uncertainty-Aware Segmentation Quality Prediction via Deep Learning Bayesian Modeling: Comprehensive Evaluation and Interpretation on Skin Cancer and Liver Segmentation
• ModelNet40-E: An Uncertainty-Aware Benchmark for Point Cloud Classification
• A Simple and Effective Method for Uncertainty Quantification and OOD Detection
• SU-ESRGAN: Semantic and Uncertainty-Aware ESRGAN for Super-Resolution of Satellite and Drone Imagery with Fine-Tuning for Cross Domain Evaluation
• Deep Metric Learning for Open World Semantic Segmentation
• Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection
• Light-Weight Diffusion Multiplier and Uncertainty Quantification for Fourier Neural Operators
• Semantic-Aware Gaussian Process Calibration with Structured Layerwise Kernels for Deep Neural Networks
• Efficient dataset construction using active learning and uncertainty-aware neural networks for plasma turbulent transport surrogate models
• BOOD: Boundary-based Out-Of-Distribution Data Generation
• Explainable Image Classification with Reduced Overconfidence for Tissue Characterisation
• ART: Adaptive Relation Tuning for Generalized Relation Prediction
• Are Recommenders Self-Aware? Label-Free Recommendation Performance Estimation via Model Uncertainty
• A Bayesian Hybrid Parameter-Efficient Fine-Tuning Method for Large Language Models
• Aleatoric Uncertainty Medical Image Segmentation Estimation via Flow Matching
• Beyond Accuracy: How AI Metacognitive Sensitivity improves AI-assisted Decision Making
• Bayesian Graph Neural Networks for Molecular Property Prediction
• The Implicit and Explicit Regularization Effects of Dropout
• Bayesian Neural Network Surrogates for Bayesian Optimization of Carbon Capture and Storage Operations
• CLEVER: Stream-based Active Learning for Robust Semantic Perception from Human Instructions
• Neural Bootstrapper
• The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation
• Bridging In- and Out-of-distribution Samples for Their Better Discriminability
• A Novel Regression Loss for Non-Parametric Uncertainty Optimization
• Benchmarking the Neural Linear Model for Regression
• Diffusion-based Deep Active Learning
• B-SCST: Bayesian Self-Critical Sequence Training for Image Captioning
• Transferable Calibration with Lower Bias and Variance in Domain Adaptation
• What training reveals about neural network complexity
• Joint-Local Grounded Action Transformation for Sim-to-Real Transfer in Multi-Agent Traffic Control
• Examining Deep Learning Models with Multiple Data Sources for COVID-19 Forecasting
• Adversarial Distillation of Bayesian Neural Network Posteriors
• Leveraging Uncertainty Estimates for Predicting Segmentation Quality
• Make (Nearly) Every Neural Network Better: Generating Neural Network Ensembles by Weight Parameter Resampling
• BayesGrad: Explaining Predictions of Graph Convolutional Networks
• Counting People by Estimating People Flows
• Probabilistic modeling of lake surface water temperature using a Bayesian spatio-temporal graph convolutional neural network
• On Modelling Label Uncertainty in Deep Neural Networks: Automatic Estimation of Intra-observer Variability in 2D Echocardiography Quality Assessment
• Bag of Coins: A Statistical Probe into Neural Confidence Structures
• Accounting for Physics Uncertainty in Ultrasonic Wave Propagation using Deep Learning
• HyperGAN: A Generative Model for Diverse, Performant Neural Networks
• Distributional Uncertainty for Out-of-Distribution Detection
• Interactive Text2Pickup Network for Natural Language based Human-Robot Collaboration
• Augmented Vision-Language Models: A Systematic Review
• Local Interpretable Model-agnostic Explanations of Bayesian Predictive Models via Kullback-Leibler Projections
• Visualizing Uncertainty and Saliency Maps of Deep Convolutional Neural Networks for Medical Imaging Applications
• Old Rules in a New Game: Mapping Uncertainty Quantification to Quantum Machine Learning
• Adversarial Robustness for Code
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
• Discretizing Reward Models
• Uncertainty Quantification for Machine Learning-Based Prediction: A Polynomial Chaos Expansion Approach for Joint Model and Input Uncertainty Propagation
• Theoretical Foundations and Mitigation of Hallucination in Large Language Models
• QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems
• RECOWNs: Probabilistic Circuits for Trustworthy Time Series Forecasting
• Better Training Data Attribution via Better Inverse Hessian-Vector Products
• Generating Diverse Descriptions from Semantic Graphs
• Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networks
• f-Cal: Calibrated aleatoric uncertainty estimation from neural networks for robot perception
• Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study
• A Locally Adaptive Interpretable Regression
• A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy
• Calibrated Top-1 Uncertainty estimates for classification by score based models
• MetaFusion: Controlled False-Negative Reduction of Minority Classes in Semantic Segmentation
• A Novel Approach for Semiconductor Etching Process with Inductive Biases
• Consistent Estimators for Learning to Defer to an Expert
• Accelerating Hamiltonian Monte Carlo for Bayesian Inference in Neural Networks and Neural Operators
• A Bayesian Convolutional Neural Network for Robust Galaxy Ellipticity Regression
• XAI-Guided Analysis of Residual Networks for Interpretable Pneumonia Detection in Paediatric Chest X-rays
• Learning to Predict Error for MRI Reconstruction
• Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Clouds
• Improving Uncertainty Calibration via Prior Augmented Data
• UGPL: Uncertainty-Guided Progressive Learning for Evidence-Based Classification in Computed Tomography
• ATOM: Commit Message Generation Based on Abstract Syntax Tree and Hybrid Ranking
• Grasping Detection Network with Uncertainty Estimation for Confidence-Driven Semi-Supervised Domain Adaptation
• Testing the Efficient Network TRaining (ENTR) Hypothesis: initially reducing training image size makes Convolutional Neural Network training for image recognition tasks more efficient
• Confidence-Filtered Relevance (CFR): An Interpretable and Uncertainty-Aware Machine Learning Framework for Naturalness Assessment in Satellite Imagery
• The Case for Bayesian Deep Learning
• Dual-Teacher++: Exploiting Intra-domain and Inter-domain Knowledge with Reliable Transfer for Cardiac Segmentation
• On-the-Fly Fine-Tuning of Foundational Neural Network Potentials: A Bayesian Neural Network Approach
• Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning
• FedSkipTwin: Digital-Twin-Guided Client Skipping for Communication-Efficient Federated Learning
• Confidence Calibration in Vision-Language-Action Models
• DONUT: Physics-aware Machine Learning for Real-time X-ray Nanodiffraction Analysis
• Bayesian Deep Learning for Convective Initiation Nowcasting Uncertainty Estimation
• Know What You Don't Know: Uncertainty Calibration of Process Reward Models
• Single- to multi-fidelity history-dependent learning with uncertainty quantification and disentanglement: application to data-driven constitutive modeling
• Variational Implicit Processes
• Towards GANs' Approximation Ability
• GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation
• Pixel Invisibility: Detecting Objects Invisible in Color Images
• Online Training and Pruning of Deep Reinforcement Learning Networks
• Selective Classification Can Magnify Disparities Across Groups
• A Physics-Informed Data-Driven Discovery for Constitutive Modeling of Compressible, Nonlinear, History-Dependent Soft Materials under Multiaxial Cyclic Loading
• Differentially Private Conformal Prediction via Quantile Binary Search
• AutoCP: Automated Pipelines for Accurate Prediction Intervals
• From Detection of Individual Metastases to Classification of Lymph Node Status at the Patient Level: The CAMELYON17 Challenge
• Manifold Modeling in Embedded Space: A Perspective for Interpreting Deep Image Prior
• Exploiting Contextual Information with Deep Neural Networks
• Gamma-Ray Bursts Calibrated by Using Artificial Neural Networks from the Pantheon+ Sample
• Deep Deterministic Uncertainty for Semantic Segmentation
• Deep Bayesian Active Learning, A Brief Survey on Recent Advances
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization
• Meta Dropout: Learning to Perturb Features for Generalization
• Reinforced active learning for image segmentation
• Effective and Efficient Dropout for Deep Convolutional Neural Networks
• Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
• Probabilistic Discriminative Learning with Layered Graphical Models
• Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation
• Few-shot Conformal Prediction with Auxiliary Tasks
• Compositional uncertainty in deep Gaussian processes
• Boosting Cloud Data Analytics using Multi-Objective Optimization
• Universal Adversarial Perturbations: A Survey
• Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers
• Probabilistic prediction of the heave motions of a semi-submersible by a deep learning problem model
• β-Variational Classifiers Under Attack
• Deep active inference agents using Monte-Carlo methods
• Spatiotemporal Fusion in 3D CNNs: A Probabilistic View
• Cascade Attentive Dropout for Weakly Supervised Object Detection
• Scene Uncertainty and the Wellington Posterior of Deterministic Image\n Classifiers
• Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
• Test Selection for Deep Learning Systems
• Regularizing Neural Networks via Stochastic Branch Layers
• CheXbreak: Misclassification Identification for Deep Learning Models Interpreting Chest X-rays
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning
• SAFARI: Safe and Active Robot Imitation Learning with Imagination
• Bayesian active learning for production, a systematic study and a reusable library
• Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation
• Interpretable Mixture Density Estimation by use of Differentiable Tree-module
• Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search
• A deep learning pipeline for localization, differentiation, and uncertainty estimation of liver lesions using multi-phasic and multi-sequence MRI
• A Simple Approximate Bayesian Inference Neural Surrogate for Stochastic Petri Net Models
• ZClassifier: Temperature Tuning and Manifold Approximation via KL Divergence on Logit Space
• Iceberg: Enhancing HLS Modeling with Synthetic Data
• An Improved Autoencoder Conjugacy Network to Learn Chaotic Maps
• Spatial Lifting for Dense Prediction
• Deep Bayesian Active Learning for Multiple Correct Outputs
• Bayesian Tensorized Neural Networks with Automatic Rank Selection
• Impute With Confidence: A Framework for Uncertainty Aware Multivariate Time Series Imputation
• Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baseline
• Implicit Regularization and Convergence for Weight Normalization
• UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Data
• Deep Learning with Uncertainty Quantification for Predicting the Segmentation Dice Coefficient of Prostate Cancer Biopsy Images
• SGPMIL: Sparse Gaussian Process Multiple Instance Learning
• Certainty Driven Consistency Loss on Multi-Teacher Networks for Semi-Supervised Learning
• InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching
• Last Layer Hamiltonian Monte Carlo
• Cross-Resolution SAR Target Detection Using Structural Hierarchy Adaptation and Reliable Adjacency Alignment
• Calibrating Deep Neural Network Classifiers on Out-of-Distribution Datasets
• Quantifying Classification Uncertainty using Regularized Evidential Neural Networks
• ViLU: Learning Vision-Language Uncertainties for Failure Prediction
• SCREP: Scene Coordinate Regression and Evidential Learning-based Perception-Aware Trajectory Generation
• Effective Version Space Reduction for Convolutional Neural Networks
• CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk
• Your Absorbing Discrete Diffusion Secretly Models the Bayesian Posterior
• Posterior Variance Is a Constraint Map, Not an Error Map: Closed-Form Uncertainty for Radiative Gaussian Splatting in Sparse-View CT
• Confidence-Aware Learning for Camouflaged Object Detection
• PINN-Obs: Physics-Informed Neural Network-Based Observer for Nonlinear Dynamical Systems
• Uncertainty Quantification as a Complementary Latent Health Indicator for Remaining Useful Life Prediction on Turbofan Engines
• Multi-scale species richness estimation with deep learning
• Event-RGB Fusion for Spacecraft Pose Estimation Under Harsh Lighting
• Mask-guided sample selection for Semi-Supervised Instance Segmentation
• Striking the Right Balance with Uncertainty
• Unsupervised Out-of-Distribution Detection with Batch Normalization
• Semantic Certainty Assessment in Vector Retrieval Systems: A Novel Framework for Embedding Quality Evaluation
• From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations
• Notes on the Behavior of MC Dropout
• ConBatch-BAL: Batch Bayesian Active Learning under Budget Constraints
• UDF-GMA: Uncertainty Disentanglement and Fusion for General Movement Assessment
• Improving Generalization in Meta-learning via Task Augmentation
• Hypermodels for Exploration
• Bayesian Hypernetworks
• Ex uno plures: Splitting One Model into an Ensemble of Subnetworks
• L2M: Practical posterior Laplace approximation with optimization-driven second moment estimation
• Variance Networks: When Expectation Does Not Meet Your Expectations
• GenAI-Powered Inference
• HAD-Net: A Hierarchical Adversarial Knowledge Distillation Network for Improved Enhanced Tumour Segmentation Without Post-Contrast Images
• Cyclist Intention Detection: A Probabilistic Approach
• Localising Dropout Variance in Twin Networks
• A Decision-Theoretic Approach for Model Interpretability in Bayesian Framework
• Shakeout: A New Approach to Regularized Deep Neural Network Training
• Enhancing Uncertainty Quantification for Runtime Safety Assurance Using Causal Risk Analysis and Operational Design Domain
• AEGIS: A Semantic GAN and Evidential Learning Framework for Robust Adversarial Detection in Vision Sensors
• Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
• The Influence of Dropout on Membership Inference in Differentially Private Models
• On Efficient Bayesian Exploration in Model-Based Reinforcement Learning
• A benchmark study on reliable molecular supervised learning via Bayesian learning
• Uncertainty-aware Reward Design Process
• Prediction of Bayesian Intervals for Tropical Storms
• Variational Graph Convolutional Neural Networks
• OoDDINO:A Multi-level Framework for Anomaly Segmentation on Complex Road Scenes
• Stacking for Non-mixing Bayesian Computations: The Curse and Blessing of Multimodal Posteriors
• Uncertainty-Aware Complex Scientific Table Data Extraction
• Variational Continual Learning
• Uncertainty-Aware Label Refinement for Sequence Labeling
• Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models
• Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments
• Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings
• Probabilistic Safety Constraints for Learned High Relative Degree System Dynamics
• Uncertainty Prioritized Experience Replay
• Bridging GANs and Bayesian Neural Networks via Partial Stochasticity
• WATS: Calibrating Graph Neural Networks with Wavelet-Aware Temperature Scaling
• Thinking About Thinking: SAGE-nano's Inverse Reasoning for Self-Aware Language Models
• Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
• Federated Learning-Enabled Hybrid Language Models for Communication-Efficient Token Transmission
• Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity
• A Novel Unsupervised Post-Processing Calibration Method for DNNS with Robustness to Domain Shift
• Sample Margin-Aware Recalibration of Temperature Scaling
• Double-Diffusion: Balancing Speed, Accuracy, and Uncertainty in Probabilistic Forecasting for Urban Sensor Networks
• Learning Adapter Rank via Symmetry Breaking
• Towards Distributed Neural Architectures
• RAUM-Net: Regional Attention and Uncertainty-aware Mamba Network
• The Consistency Hypothesis in Uncertainty Quantification for Large Language Models
• Understanding Uncertainty of Edge Computing: New Principle and Design Approach
• TITAN: Query-Token based Domain Adaptive Adversarial Learning
• Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference
• Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry
• Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors
• Neural Likelihoods via Cumulative Distribution Functions
• Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection
• Extending Epistemic Uncertainty Beyond Parameters Would Assist in Designing Reliable LLMs
• Emergent Granger Causality in Neural Networks: Can Prediction Alone Reveal Structure?
• Mitigating Gambling-Like Risk-Taking Behaviors in Large Language Models: A Behavioral Economics Approach to AI Safety
• Precise Bayesian Neural Networks
• Kalman meets Bellman: Improving Policy Evaluation through Value Tracking
• Uncertainty in Gradient Boosting via Ensembles
• MultiBench: Multiscale Benchmarks for Multimodal Representation Learning
• Simpler but More Accurate Semantic Dependency Parsing
• The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization
• Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
• Quantifying Uncertainty in the Presence of Distribution Shifts
• Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality
• Scaling Out-of-Distribution Detection for Real-World Settings
• Variational Supervised Contrastive Learning
• Pitfalls of Conformal Predictions for Medical Image Classification
• Variational Variance: Simple, Reliable, Calibrated Heteroscedastic Noise Variance Parameterization
• Combining data assimilation and machine learning to infer unresolved scale parametrisation
• Learning Personalized Utility Functions for Drivers in Ride-hailing Systems Using Ensemble Hypernetworks
• Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
• Sparse MoEs meet Efficient Ensembles
• 6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference
• Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysis
• A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence
• Probabilistic Residual Learning for Aleatoric Uncertainty in Image\n Restoration
• An Uncertainty-Aware Dynamic Decision Framework for Progressive Multi-Omics Integration in Classification Tasks
• Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks
• Spatially-Aware Evaluation of Segmentation Uncertainty
• Using Depth for Pixel-Wise Detection of Adversarial Attacks in Crowd Counting
• Practical Deep Learning with Bayesian Principles
• Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
• Induction, Popper, and machine learning
• Out-of-Distribution Example Detection in Deep Neural Networks using Distance to Modelled Embedding
• T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptation
• Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs
• Uncertainty Estimation by Human Perception versus Neural Models
• Towards Reliable WMH Segmentation under Domain Shift: An Application Study using Maximum Entropy Regularization to Improve Uncertainty Estimation
• Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection
• Edge-variational Graph Convolutional Networks for Uncertainty-aware Disease Prediction
• Hepatocellular Carcinoma Intra-arterial Treatment Response Prediction for Improved Therapeutic Decision-Making
• Scheduling Real-time Deep Learning Services as Imprecise Computations
• Next-Generation Conflict Forecasting: Unleashing Predictive Patterns through Spatiotemporal Learning
• Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach
• Probabilistic Regression of Rotations using Quaternion Averaging and a Deep Multi-Headed Network
• Feature-wise change detection and robust indoor positioning using RANSAC-like approach
• Out-of-Distribution Detection for Dermoscopic Image Classification
• Uncertainty-Aware Semi-Supervised Few Shot Segmentation
• Visual Transformer for Task-aware Active Learning
• Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs
• Learning to Fuse: Modality-Aware Adaptive Scheduling for Robust Multimodal Foundation Models
• Dynamic Modality Scheduling for Multimodal Large Models via Confidence, Uncertainty, and Semantic Consistency
• T³S: Think in Thermal Time for Generalizable Crop Mapping from Satellite Image Time Series
• Cascaded Language Models for Cost-effective Human-AI Decision-Making
• Single Shot MC Dropout Approximation
• Uncertainty Awareness Enables Efficient Labeling for Cancer Subtyping in Digital Pathology
• Improving Group Robustness on Spurious Correlation via Evidential Alignment
• Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models
• Pointwise confidence estimation in the non-linear ℓ²-regularized least squares
• Sequential Anomaly Detection using Inverse Reinforcement Learning
• A Quad-Step Approach to Uncertainty-Aware Deep Learning for Skin Cancer Classification
• Test Sample Accuracy Scales with Training Sample Density in Neural Networks
• Provably-Robust Runtime Monitoring of Neuron Activation Patterns
• DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting
• Scaling Laws for Uncertainty in Deep Learning
• Bayesian Deep Learning for Exoplanet Atmospheric Retrieval
• Deep Active Learning by Model Interpretability
• Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'
• Uncertainty Quantification in Computer-Aided Diagnosis: Make Your Model say "I don't know" for Ambiguous Cases
• Large Language Models are Demonstration Pre-Selectors for Themselves
• Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learning
• TRUST: Test-time Resource Utilization for Superior Trustworthiness
• Active Learning in CNNs via Expected Improvement Maximization
• Reinforcement Learning for Robotics and Control with Active Uncertainty Reduction
• Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models
• Probabilistic Safety for Bayesian Neural Networks
• SupportNet: solving catastrophic forgetting in class incremental learning with support data
• Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning
• Regularising Deep Networks with Deep Generative Models
• Uncertainty quantification of molecular property prediction using Bayesian neural network models
• Uncertainty-guided active learning for surrogate prediction of stream-finishing wear fields
• Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output
• Improving Predictive Uncertainty Estimation using Dropout -- Hamiltonian Monte Carlo
• Conformal coronary calcification volume estimation with conditional coverage via histogram clustering
• Probabilistic Approach for Road-Users Detection
• Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators
• On the Importance of Strong Baselines in Bayesian Deep Learning
• Dense Uncertainty Estimation
• High-Performance FPGA-based Accelerator for Bayesian Neural Networks
• Why Does the Future Branch? Identifiable Closure Tests for Stochastic Physical World Models
• Average Calibration Losses for Reliable Uncertainty in Medical Image Segmentation
• FPGA-Enabled Machine Learning Applications in Earth Observation: A Systematic Review
• Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration
• Bayesian Compression for Deep Learning
• Joint Distribution across Representation Space for Out-of-Distribution Detection
• Dropout Q-Functions for Doubly Efficient Reinforcement Learning
• Beyond Point Estimate: Inferring Ensemble Prediction Variation from Neuron Activation Strength in Recommender Systems
• Prior Activation Distribution (PAD): A Versatile Representation to Utilize DNN Hidden Units
• Locally Learned Synaptic Dropout for Complete Bayesian Inference
• DEBOSH: Deep Bayesian Shape Optimization
• Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation
• Finite Versus Infinite Neural Networks: an Empirical Study
• Generative Particle Variational Inference via Estimation of Functional Gradients
• Transferable Cost-Aware Security Policy Implementation for Malware Detection Using Deep Reinforcement Learning
• BAR: Bayesian Activity Recognition using variational inference
• Evaluating and Boosting Uncertainty Quantification in Classification
• Safer Classification by Synthesis
• Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
• Calibrated neighborhood aware confidence measure for deep metric learning
• Isotropic SGD: a Practical Approach to Bayesian Posterior Sampling
• Radial and Directional Posteriors for Bayesian Neural Networks
• Deep covariate-learning: optimising information extraction from terrain texture for geostatistical modelling applications
• Generalized Negative Correlation Learning for Deep Ensembling
• Adversarial Examples in Modern Machine Learning: A Review
• Trustworthy Long-Tailed Classification
• Analyzing Epistemic and Aleatoric Uncertainty for Drusen Segmentation in Optical Coherence Tomography Images
• Improving model calibration with accuracy versus uncertainty optimization
• Efficient exploration with Double Uncertain Value Networks
• ROSA: Addressing text understanding challenges in photographs via ROtated SAmpling
• Class-Similarity Based Label Smoothing for Confidence Calibration
• Interpreting and Boosting Dropout from a Game-Theoretic View
• Decentralized Bayesian Learning over Graphs
• Generative AI as a Pillar for Predicting 2D and 3D Wildfire Spread: Beyond Physics-Based Models and Traditional Deep Learning
• Active Learning Solution on Distributed Edge Computing
• Trusted Fake Audio Detection Based on Dirichlet Distribution
• Semantic similarity metrics for learned image registration
• A Bayesian PINN Framework for Barrow-Tsallis Holographic Dark Energy with Neutrinos: Toward a Resolution of the Hubble Tension
• MMD-Flagger: Leveraging Maximum Mean Discrepancy to Detect Hallucinations
• UPMAD-Net: A Brain Tumor Segmentation Network with Uncertainty Guidance and Adaptive Multimodal Feature Fusion
• Principled Input-Output-Conditioned Post-Hoc Uncertainty Estimation for Regression Networks
• Implications of Human Irrationality for Reinforcement Learning
• Protein Language Model Zero-Shot Fitness Predictions are Improved by Inference-only Dropout
• UNSURF: Uncertainty Quantification for Cortical Surface Reconstruction of Clinical Brain MRIs
• Physics-informed machine learning
• Using Ensemble Diffusion to Estimate Uncertainty for End-to-End Autonomous Driving
• Frequentist Uncertainties on Neural Density Ratios with wifi Ensembles
• Drop Dropout on Single-Epoch Language Model Pretraining
• MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platform
• Energy Forecasting in Smart Grid Systems: A Review of the State-of-the-art Techniques
• Conformal Object Detection by Sequential Risk Control
• Webly Supervised Image Classification with Self-Contained Confidence
• Data Interpolating Prediction: Alternative Interpretation of Mixup
• Hydrogen Passivation Effects on Spatially Resolved Charge Trap Densities in Si(100)-SiO₂
• Mitigating Uncertainty in Document Classification
• Position: Epistemic uncertainty estimation methods are fundamentally incomplete
• Network Inversion for Uncertainty-Aware Out-of-Distribution Detection
• Vid-SME: Membership Inference Attacks against Large Video Understanding Models
• Dynamic Estimation Loss Control in Variational Quantum Sensing via Online Conformal Inference
• Daunce: Data Attribution through Uncertainty Estimation
• Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement
• Knowing More About Questions Can Help: Improving Calibration in Question Answering
• To Trust Or Not To Trust Your Vision-Language Model's Prediction
• Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization
• Data-driven discovery of interpretable causal relations for deep learning material laws with uncertainty propagation
• Fast Monte Carlo Dropout and Error Correction for Radio Transmitter Classification
• Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs
• Hierarchical Material Recognition from Local Appearance
• A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts
• Uncertainty Quantification with Proper Scoring Rules: Adjusting Measures to Prediction Tasks
• Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings
• Improving Out-of-Distribution Detection with Markov Logic Networks
• Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory
• Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer
• Credal Prediction based on Relative Likelihood
• Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance
• Optimizing Data Augmentation through Bayesian Model Selection
• An Uncertainty-Aware ED-LSTM for Probabilistic Suffix Prediction
• Feature Space Singularity for Out-of-Distribution Detection
• Uncertainty-Weighted Image-Event Multimodal Fusion for Video Anomaly Detection
• OrcVIO: Object residual constrained Visual-Inertial Odometry
• Simulation-based Lidar Super-resolution for Ground Vehicles
• Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?
• Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review
• Active Learning for Visual Question Answering: An Empirical Study
• Exploring the Possibility of TypiClust for Low-Budget Federated Active Learning
• Non-linear Multitask Learning with Deep Gaussian Processes
• All You Need is a Good Functional Prior for Bayesian Deep Learning
• Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control
• Deep Learning and Bayesian Deep Learning Based Gender Prediction in Multi-Scale Brain Functional Connectivity
• ADER:Adapting between Exploration and Robustness for Actor-Critic Methods
• A Bayesian Perspective on Training Speed and Model Selection
• Deep Active Inference Agents for Delayed and Long-Horizon Environments
• Cooperative Variance Estimation and Bayesian Neural Networks for Disentangling Aleatoric and Epistemic Uncertainties
• Improving Classifier Confidence using Lossy Label-Invariant Transformations
• Monocle: Hybrid Local-Global In-Context Evaluation for Long-Text Generation with Uncertainty-Based Active Learning
• Ensemble Kalman filter for uncertainty in human language comprehension
• Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads
• A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model
• PANDA: AdaPtive Noisy Data Augmentation for Regularization of Undirected Graphical Models
• VFunc: a Deep Generative Model for Functions
• Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial Inference
• Optimal Conformal Prediction under Epistemic Uncertainty
• Image segmentation of liver stage malaria infection with spatial uncertainty sampling
• Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects
• MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images
• Asymmetric Duos: Sidekicks Improve Uncertainty
• Physics-Informed Neural Networks for Sparse Strain-Field Reconstruction in 4D-STEM
• Uncertainty Quantification of Locally Nonlinear Dynamical Systems using Neural Networks
• Aboveground biomass mapping of Canada with SAR and optical satellite observations aided by active learning
• Uncertainty-aware Human Motion Prediction
• Test-Time Adaptation with Binary Feedback
• Bayesian Optimisation over Multiple Continuous and Categorical Inputs
• Lightweight Data Fusion with Conjugate Mappings
• Predictive Uncertainty Quantification with Compound Density Networks
• Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior
• Implicit Neural Representations for Multimodal Longitudinal Image Imputation and Interpolation
• Decision Theoretic Bootstrapping
• Logit-based Uncertainty Measure in Classification
• Calibrate your listeners! Robust communication-based training for pragmatic speakers
• Stochastic Weight Sharing for Bayesian Neural Networks
• C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models
• A Practical & Unified Notation for Information-Theoretic Quantities in ML
• Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
• High Dimensional Level Set Estimation with Bayesian Neural Network
• EvidenceMoE: A Physics-Guided Mixture-of-Experts with Evidential Critics for Advancing Fluorescence Light Detection and Ranging in Scattering Media
• Overpruning in Variational Bayesian Neural Networks
• Repulsive Ensembles for Bayesian Inference in Physics-informed Neural Networks
• SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
• TULiP: Test-time Uncertainty Estimation via Linearization and Weight Perturbation
• Constrained Co-Design for Photonic Bayesian Neural Networks
• Safe Uncertainty-Aware Learning of Robotic Suturing
• Reliable Deep Grade Prediction with Uncertainty Estimation
• Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models
• Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools
• An ETF view of Dropout regularization
• Bayesian Sparsification Methods for Deep Complex-valued Networks
• Survivable Robotic Control through Guided Bayesian Policy Search with Deep Reinforcement Learning
• DUAL: Dynamic Uncertainty-Aware Learning
• Enhancing Monte Carlo Dropout Performance for Uncertainty Quantification
• Uncertainty-Aware Crossmodal Fusion for Classification of Animal Behavior
• Copula-like Variational Inference
• Quantile Regularization: Towards Implicit Calibration of Regression Models
• Robust Multimodal Learning via Entropy-Gated Contrastive Fusion
• Bayes-Adaptive Deep Model-Based Policy Optimisation
• Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs
• Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
• Fast learning rate of deep learning via a kernel perspective
• Know When to Abstain: Optimal Selective Classification with Likelihood Ratios
• On Mixup Regularization
• Last Layer Empirical Bayes
• Generative AI for Autonomous Driving: A Review
• Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning
• Confidence Modeling for Neural Semantic Parsing
• SurvUnc: A Meta-Model Based Uncertainty Quantification Framework for Survival Analysis
• Breaking Diversity Collapse in Spiking Pseudo-Ensembles for Efficient OOD Detection in Remote Sensing
• Selective Classification via One-Sided Prediction
• Sampling Prediction-Matching Examples in Neural Networks: A Probabilistic Programming Approach
• CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decomposition
• Privacy-preserving Active Learning on Sensitive Data for User Intent Classification
• Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation
• Semi-Local 3D Lane Detection and Uncertainty Estimation
• Scalable Bayesian Monte Carlo: fast uncertainty estimation beyond deep ensembles
• Estimation with Uncertainty via Conditional Generative Adversarial Networks
• Random Feature Expansions for Deep Gaussian Processes
• Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models
• Going deep into schizophrenia with artificial intelligence
• Out of the Black Box: Properties of deep neural networks and their applications
• GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents
• Investigating Active Sampling for Hardness Classification with Vision-Based Tactile Sensors
• Deep Generative Modeling with Spatial and Network Images: An Explainable AI (XAI) Approach
• ST-LoRA: Single Trajectory LoRA Ensemble for Uncertainty Aware Agricultural Segmentation
• An Interpretable and Uncertainty Aware Multi-Task Framework for Multi-Aspect Sentiment Analysis
• Active Learning on Synthons for Molecular Design
• Alternators With Noise Models
• Light-sheets and smart microscopy, an exciting future is dawning
• Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
• Confidence Calibration for Convolutional Neural Networks Using Structured Dropout
• Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission
• Trust Region Value Optimization using Kalman Filtering
• EulerLoRA: Rank-Driven Jump Dynamics for Calibrated Parameter-Efficient Fine-Tuning
• Natural Attribute-based Shift Detection
• Are vision language models robust to uncertain inputs?
• Automated Real-time Assessment of Intracranial Hemorrhage Detection AI Using an Ensembled Monitoring Model (EMM)
• TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
• Self-supervised Remote Sensing Images Change Detection at Pixel-level
• On Statistical Bias In Active Learning: How and When To Fix It
• Multi-Dimensional Assessment for AI Cognition (MAAC): A Theoretical Framework for Process-Oriented Cognitive Evaluation of Text-Based AI Systems
• SPIEDiff: robust learning of long-time macroscopic dynamics from short-time particle simulations with quantified epistemic uncertainty
• MTRE: Multi-Token Reliability Estimation for Hallucination Detection in VLMs
• Uncertainty quantification with approximate variational learning for wearable photoplethysmography prediction tasks
• MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection
• Recursive Gaussian Processes and the Bayesian Brain
• Test-time Adaptation of Pelvic Bone Segmentation Models via Dynamic Reliability-Guided
• Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Models
• An Uncertainty-Driven Hybrid Deep Learning Approach for Broad-Coverage RF Modulation Recognition
• Using Uncertainty in Deep Learning Reconstruction for Cone-Beam CT of the Brain
• Parallel Scaling Law for Language Models
• Multi-Stage Transfer Learning with an Application to Selection Process
• On the Reduction of Variance and Overestimation of Deep Q-Learning
• Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference
• Should We Simultaneously Calibrate Multiple Computer Models?
• Improving Uncertainty Calibration of Deep Neural Networks via Truth Discovery and Geometric Optimization
• Learning the LoS Skyline from LEO Satellite Observations for Proactive Handover
• Heteroscedastic Calibration of Uncertainty Estimators in Deep Learning
• A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks
• Variational Visual Question Answering for Uncertainty-Aware Selective Prediction
• Eigenvalue Corrected Noisy Natural Gradient
• RoNGBa: A Robustly Optimized Natural Gradient Boosting Training Approach with Leaf Number Clipping
• Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks
• A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs
• Feature Fitted Online Conformal Prediction for Deep Time Series Forecasting Model
• Mitigating Visual Hallucinations in Multimodal Systems through Retrieval-Augmented Reliability-Aware Inference
• Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections
• Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review
• Reinforcement Learning with Subspaces using Free Energy Paradigm
• Distribution-Free Federated Learning with Conformal Predictions
• Physen-Noise2Noise: Physics-Guided Self-Supervised Defocus Deblurring with Bias Correction under Low-Light Conditions
• GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding
• DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill Acquisition
• Uncertainty-Aware Voxel based 3D Object Detection and Tracking with von-Mises Loss
• QoSBERT: An Uncertainty-Aware Approach based on Pre-trained Language Models for Service Quality Prediction
• Modeling continuous-time stochastic processes using \N-Curve\n mixtures
• MOrdReD: Memory-based Ordinal Regression Deep Neural Networks for Time Series Forecasting
• Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning
• GeneDisco: A Benchmark for Experimental Design in Drug Discovery
• Stochastic Layer-wise Learning: Scalable and Efficient Alternative to Backpropagation
• Inherent Weight Normalization in Stochastic Neural Networks
• UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model
• Learning Resilient Behaviors for Navigation Under Uncertainty
• Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time
• Nonparametric Distribution Regression Re-calibration
• Bridging the Gap Between Explainable AI and Uncertainty Quantification to Enhance Trustability
• Boundary Uncertainty in a Single-Stage Temporal Action Localization Network
• BORE: Bayesian Optimization by Density-Ratio Estimation
• Uncertainty Quantification for Machine Learning in Healthcare: A Survey
• Epistemic Wrapping for Uncertainty Quantification
• Rethinking Uncertainty Quantification and Entanglement in Image Segmentation
• Calibrating Deep Convolutional Gaussian Processes
• Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection
• kFolden: k-Fold Ensemble for Out-Of-Distribution Detection
• HDI-Forest: Highest Density Interval Regression Forest
• Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training
• Risk-Aware Path Planning for Ground Vehicles using Occluded Aerial Images
• Remaining Useful Life Estimation Under Uncertainty with Causal GraphNets
• Information Planning for Text Data
• Leveraging Uncertainty in Deep Learning for Selective Classification
• Parting with Illusions about Deep Active Learning
• Uncertainty Estimation in Autoregressive Structured Prediction
• Model Selection in Bayesian Neural Networks via Horseshoe Priors
• Meta-Learned Confidence for Few-shot Learning
• Loss-Calibrated Approximate Inference in Bayesian Neural Networks
• Adapting Evidential Neural Networks to Test-Time Neighbor Fusion Improves Molecular Property Prediction
• Wayfinder: Automated Operating System Specialization
• U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster
• A critical look at the current train/test split in machine learning
• Unsupervised Temperature Scaling: An Unsupervised Post-Processing Calibration Method of Deep Networks
• Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data
• Safe end-to-end imitation learning for model predictive control
• Uncertainty Aware Semi-Supervised Learning on Graph Data
• State-Relabeling Adversarial Active Learning
• Angular Visual Hardness
• The Invisible Gorilla Effect in Out-of-distribution Detection
• Understanding Softmax Confidence and Uncertainty
• Practical Solutions for Machine Learning Safety in Autonomous Vehicles
• Leveraging Uncertainty from Deep Learning for Trustworthy Materials Discovery Workflows
• A Batched Scalable Multi-Objective Bayesian Optimization Algorithm
• APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations
• RBUE: A ReLU-Based Uncertainty Estimation Method of Deep Neural Networks
• Epistemic Neural Networks
• Uncertainty-Aware Deep Hedging
• Generalizing MLPs With Dropouts, Batch Normalization, and Skip Connections
• HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detection
• Learning the Standard Model Manifold: Bayesian Latent Diffusion for Collider Anomaly Detection
• Bayesian Graph Convolutional Neural Networks Using Non-Parametric Graph Learning
• Open Set Medical Diagnosis
• A Hybrid Bandit Model with Visual Priors for Creative Ranking in Display Advertising
• AI-Assisted Decision-Making for Clinical Assessment of Auto-Segmented Contour Quality
• A Proper Scoring Rule for Virtual Staining
• Less is More: Rejecting Unreliable Reviews for Product Question Answering
• On the Equivalence of Random Network Distillation, Deep Ensembles, and Bayesian Inference
• Why have a Unified Predictive Uncertainty? Disentangling it using Deep Split Ensembles
• Conditionally Site-Independent Neural Evolution of Antibody Sequences
• Self-Aware Object Detection via Degradation Manifolds
• Scalable Uncertainty Quantification for Extreme Weather Forecasting via Empirical Neural Tangent Kernels
• CHASE: Competing Hypotheses for Ambiguity-Aware Selective Prediction
• Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning
• Multi-Goal Dexterous Hand Manipulation using Probabilistic Model-based Reinforcement Learning
• An adaptive, data-driven multiscale approach for dense granular flows
• When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
• Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent
• Unknowable Manipulators: Social Network Curator Algorithms
• Toward Efficient Exploration by Large Language Model Agents
• Digital Twin-based Out-of-Distribution Detection in Autonomous Vessels
• Hallucination in World Models is Predictable and Preventable
• Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
• Computationally lightweight classifiers with frequentist bounds on predictions
• The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?
• Physical Cue based Depth-Sensing by Color Coding with Deaberration Network
• Band excitation piezo-response spectroscopy (BEPS) data on lead titanate (PTO) samples.
• Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review
• Random-Set Large Language Models
• Bayesian Quantum Orthogonal Neural Networks for Anomaly Detection
• Safe Urban Traffic Control via Uncertainty-Aware Conformal Prediction and World-Model Reinforcement Learning
• Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
• Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?
• Strategy to Increase the Safety of a DNN-based Perception for HAD Systems
• Semi-Supervised Confidence Network aided Gated Attention based Recurrent Neural Network for Clickbait Detection
• Micro-CT Synthesis and Inner Ear Super Resolution via Generative Adversarial Networks and Bayesian Inference
• EPSILON: Adaptive Fault Mitigation in Approximate Deep Neural Network using Statistical Signatures
• ScoreField: Neural Inverse Scattering with Score-Based Generative Priors
• Copolymer Informatics with Multitask Deep Neural Networks
• Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
• Robust Semantic Segmentation with Superpixel-Mix
• Active model learning and diverse action sampling for task and motion planning
• Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression
• Explaining Low Perception Model Competency with High-Competency Counterfactuals
• Mixing Data-Driven and Physics-Based Constitutive Models using Uncertainty-Driven Phase Fields
• A Deep Bayesian Convolutional Spiking Neural Network-based CAD system with Uncertainty Quantification for Medical Images Classification
• From Predictions to Decisions: Using Lookahead Regularization
• Credal Self-Supervised Learning
• Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties
• Fanaroff–Riley classification of radio galaxies using group-equivariant convolutional neural networks
• Last-layer committee machines for uncertainty estimations of benthic imagery
• Using Machine Learning Safely in Automotive Software: An Assessment and\n Adaption of Software Process Requirements in ISO 26262
• CNN-Based Deep Learning Model for Solar Wind Forecasting
• Modeling of AUV Dynamics with Limited Resources: Efficient Online Learning Using Uncertainty
• Bayesian neural networks at scale: a performance analysis and pruning study
• On Batch Normalisation for Approximate Bayesian Inference
• Bayesian Autoencoder for Medical Anomaly Detection: Uncertainty-Aware Approach for Brain 2 MRI Analysis
• Measuring Uncertainty in Shape Completion to Improve Grasp Quality
• A Clinician-Friendly Platform for Ophthalmic Image Analysis Without Technical Barriers
• Context Aware Grounded Teacher for Source Free Object Detection
• CODA: Constructivism Learning for Instance-Dependent Dropout Architecture Construction
• Stochastic Sparse Subspace Clustering
• A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization
• Learning from Stochastic Teacher Representations Using Student-Guided Knowledge Distillation
• CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey
• Learning what is above and what is below: horizon approach to monocular obstacle detection
• Uncertainty-Aware COVID-19 Detection from Imbalanced Sound Data
• Generative Parameter Sampler For Scalable Uncertainty Quantification
• Bayesian Methods for Semi-supervised Text Annotation
• The Role of MRI Physics in Brain Segmentation CNNs: Achieving Acquisition Invariance and Instructive Uncertainties
• STUaNet: Understanding Uncertainty in Spatiotemporal Collective Human Mobility
• Intrinsic uncertainties and where to find them
• A Transferable Adaptive Domain Adversarial Neural Network for Virtual\n Reality Augmented EMG-Based Gesture Recognition
• Parameter estimation for the cosmic microwave background with Bayesian neural networks
• Stopping Criterion for Active Learning Based on Error Stability
• Bayesian Neural Network Priors Revisited
• MILD-Net: Minimal information loss dilated network for gland instance segmentation in colon histology images
• Volumetric Landmark Detection with a Multi-Scale Shift Equivariant Neural Network
• Bayesian Learning-Based Adaptive Control for Safety Critical Systems
• Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning
• Uncertainty-Aware Trajectory Prediction via Rule-Regularized Heteroscedastic Deep Classification
• Accelerated replica exchange stochastic gradient Langevin diffusion enhanced Bayesian DeepONet for solving noisy parametric PDEs
• Towards An Efficient and Effective En Route Travel Time Estimation Framework
• Learnable Bernoulli Dropout for Bayesian Deep Learning
• Representation Learning for Tabular Data: A Comprehensive Survey
• Uncertainty-Guided Coarse-to-Fine Tumor Segmentation with Anatomy-Aware Post-Processing
• DistMedVL: Distributional Vision-Language Alignment for Uncertainty-Aware Medical Image Segmentation
• A Unified Risk View of Uncertainty: Posterior Risk for Disentanglement and Evaluation Beyond Proxies
• Polarization-Conditioned Fourier-enhanced DeepONet for Electric Field Reconstruction from EFISH Measurements
• Evidential Rule Learning for Interpretable Classification with Abstention
• Hybrid Probabilistic Zonotopes for Identifiable and Refinable Predictive Uncertainty
• Matrix Zonotopic Attention: A Context-Adaptive Value Projection for Set Transformers
• MoDAl: Self-Supervised Neural Modality Discovery via Decorrelation for Speech Neuroprosthesis
• Uncertainty-aware electronic density-functional distributions
• Uncertainty Estimation for Trust Attribution to Speed-of-Sound Reconstruction with Variational Networks
• Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
• Towards Scalable Bayesian Optimization via Gradient-Informed Bayesian Neural Networks
• Epistemic Uncertainty-aware Recommendation Systems via Bayesian Deep Ensemble Learning
• DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering
• A Survey on Efficient Vision-Language Models
• Graph Learning-Driven Multi-Vessel Association: Fusing Multimodal Data for Maritime Intelligence
• Road Grip Uncertainty Estimation Through Surface State Segmentation
• Conformalized Generative Bayesian Imaging: An Uncertainty Quantification Framework for Computational Imaging
• Localization Meets Uncertainty: Uncertainty-Aware Multi-Modal Localization
• Towards Lower-Dose PET using Physics-Based Uncertainty-Aware Multimodal\n Learning with Robustness to Out-of-Distribution Data
• Unsupervised Data Uncertainty Learning in Visual Retrieval Systems
• Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation
• Explaining Uncertainty in Multiple Sclerosis Lesion Segmentation Beyond Prediction Errors
• Estimation of Accurate and Calibrated Uncertainties in Deterministic models

Discussions

• It's not present in ANNs after learning, so I think it's not quite the same as noise in biological neurons. Apparently dropout is Bayesian approximation. [bsky, 4 points, 0 comments]

Related

• Dropout as a Bayesian Approximation: Appendix
• Unreliable Uncertainty Estimates with Monte Carlo Dropout
• Notes on the Behavior of MC Dropout
• Dropout Inference in Bayesian Neural Networks with Alpha-divergences
• Novel Uncertainty Framework for Deep Learning Ensembles