Weight Uncertainty in Neural Networks

Abstract

We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop. It regularises the weights by minimising a compression cost, known as the variational free energy or the expected lower bound on the marginal likelihood. We show that this principled kind of regularisation yields comparable performance to dropout on MNIST classification. We then demonstrate how the learnt uncertainty in the weights can be used to improve generalisation in non-linear regression problems, and how this weight uncertainty can be used to drive the exploration-exploitation trade-off in reinforcement learning.

arXiv commentIn Proceedings of the 32nd International Conference on Machine Learning (ICML 2015)

References in corpus (7)

• Auto-Encoding Variational Bayes
• Distilling the Knowledge in a Neural Network
• Improving neural networks by preventing co-adaptation of feature detectors
• A Contextual-Bandit Approach to Personalized News Article Recommendation
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Analysis of Thompson Sampling for the multi-armed bandit problem
• Further Optimal Regret Bounds for Thompson Sampling

Cited by in corpus (463)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• An Introduction to Variational Autoencoders
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Attention in Natural Language Processing
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• VIME: Variational Information Maximizing Exploration
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• Deep Exploration via Bootstrapped DQN
• Variational Dropout and the Local Reparameterization Trick
• Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
• Deep and Confident Prediction for Time Series at Uber
• Accurate Uncertainties for Deep Learning Using Calibrated Regression
• Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Bayesian Compression for Deep Learning
• A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network
• Adding Gradient Noise Improves Learning for Very Deep Networks
• Bayesian Dark Knowledge
• Multi-fidelity Bayesian Neural Networks: Algorithms and Applications
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• Towards Robust Evaluations of Continual Learning
• A Simple Baseline for Bayesian Uncertainty in Deep Learning
• Gravitational-wave parameter estimation with autoregressive neural network flows
• A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference
• Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
• Bayesian-Deep-Learning Estimation of Earthquake Location from Single-Station Observations
• Probabilistic neural networks for fluid flow surrogate modeling and data recovery
• High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach
• Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
• Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
• Bayesian Recurrent Neural Networks
• Peer-to-peer Federated Learning on Graphs
• Physics-guided deep learning framework for predictive modeling of the Reynolds stress anisotropy
• Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets
• Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks
• Compressing Neural Networks using the Variational Information Bottleneck
• Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning
• Lifelong Generative Modeling
• Quantum Machine Learning: from physics to software engineering
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• A survey on intrinsic motivation in reinforcement learning
• Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors
• A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications
• VIBNN: Hardware Acceleration of Bayesian Neural Networks
• Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
• Stochastic Hyperparameter Optimization through Hypernetworks
• Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space
• Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
• Quality of Uncertainty Quantification for Bayesian Neural Network Inference
• A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
• Meta-Learning without Memorization
• Non-Intrusive Reduced-Order Modeling Using Uncertainty-Aware Deep Neural Networks and Proper Orthogonal Decomposition: Application to Flood Modeling
• Task Agnostic Continual Learning Using Online Variational Bayes
• Bayesian Batch Active Learning as Sparse Subset Approximation
• Discrete Sequential Prediction of Continuous Actions for Deep RL
• Implicit Weight Uncertainty in Neural Networks
• A Survey of Active Learning for Text Classification using Deep Neural Networks
• Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference
• Interpretable Sequence Learning for COVID-19 Forecasting
• Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
• Reinforcement Learning through Active Inference
• Dropout as a Bayesian Approximation: Appendix
• Uncertainty-Aware Organ Classification for Surgical Data Science Applications in Laparoscopy
• Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspective
• Information fusion and machine learning for sensitivity analysis using physics knowledge and experimental data
• Contrastive Training for Improved Out-of-Distribution Detection
• Estimating Risk and Uncertainty in Deep Reinforcement Learning
• Conditional Neural Processes
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• An Equivalence of Fully Connected Layer and Convolutional Layer
• The Free Energy Principle for Perception and Action: A Deep Learning Perspective
• Model Selection in Bayesian Neural Networks via Horseshoe Priors
• Structured Bayesian Gaussian process latent variable model: applications to data-driven dimensionality reduction and high-dimensional inversion
• Detection of Gravitational Waves Using Bayesian Neural Networks
• A Spectral Approach to Gradient Estimation for Implicit Distributions
• Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors
• On the Expressiveness of Approximate Inference in Bayesian Neural Networks
• Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation
• Exploiting Oxide Based Resistive RAM Variability for Bayesian Neural Network Hardware Design
• Transient-optimised real-bogus classification with Bayesian Convolutional Neural Networks -- sifting the GOTO candidate stream
• A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks
• Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation
• Dynamical mass inference of galaxy clusters with neural flows
• Automated Curriculum Learning for Neural Networks
• Molecule Identification with Rotational Spectroscopy and Probabilistic Deep Learning
• Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging
• Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
• Deep Gamblers: Learning to Abstain with Portfolio Theory
• Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors
• Adversarial Distributional Training for Robust Deep Learning
• Hyperparameter Ensembles for Robustness and Uncertainty Quantification
• Neural Thompson Sampling
• Uncertainty Quantification and Deep Ensembles
• Information Aware Max-Norm Dirichlet Networks for Predictive Uncertainty Estimation
• Adversarial Distillation of Bayesian Neural Network Posteriors
• 'In-Between' Uncertainty in Bayesian Neural Networks
• Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation
• Large-Scale Visual Active Learning with Deep Probabilistic Ensembles
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
• Notes on the Behavior of MC Dropout
• Approximate Bayesian Uncertainties on Deep Learning Dynamical Mass Estimates of Galaxy Clusters
• Robustness of Bayesian Neural Networks to Gradient-Based Attacks
• Providing physics guides in Bayesian neural networks from input layer: case of giant dipole resonance predictions
• Uncertainty-Aware Reliable Text Classification
• Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
• Noisy Natural Gradient as Variational Inference
• Bayesian Neural Network Priors Revisited
• The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning
• Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables
• ProbAct: A Probabilistic Activation Function for Deep Neural Networks
• Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling
• Variational Inference at Glacier Scale
• Probabilistic Model-Agnostic Meta-Learning
• Action and Perception as Divergence Minimization
• Improving Local Identifiability in Probabilistic Box Embeddings
• The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
• Bayesian Neural Networks With Maximum Mean Discrepancy Regularization
• Learnable Bernoulli Dropout for Bayesian Deep Learning
• TherML: Thermodynamics of Machine Learning
• Uncertainty-Aware Self-Supervised Learning of Spatial Perception Tasks
• ACDC: A Structured Efficient Linear Layer
• Transferable Calibration with Lower Bias and Variance in Domain Adaptation
• Safe end-to-end imitation learning for model predictive control
• Subspace Inference for Bayesian Deep Learning
• Bayesian Inference with Anchored Ensembles of Neural Networks, and Application to Exploration in Reinforcement Learning
• Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
• Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting
• Deep Robust Kalman Filter
• Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks
• Deep Fried Convnets
• Bayesian Semisupervised Learning with Deep Generative Models
• Repulsive Deep Ensembles are Bayesian
• Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates
• Active Testing: Sample-Efficient Model Evaluation
• Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation
• Can We Leverage Predictive Uncertainty to Detect Dataset Shift and Adversarial Examples in Android Malware Detection?
• On Hallucination and Predictive Uncertainty in Conditional Language Generation
• Cosmological Parameter Estimation and Inference using Deep Summaries
• Uncertainty quantification of molecular property prediction with Bayesian neural networks
• Quantifying Uncertainties in Natural Language Processing Tasks
• AutoOD: Automated Outlier Detection via Curiosity-guided Search and Self-imitation Learning
• Unsupervised Knowledge-Transfer for Learned Image Reconstruction
• Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantification
• Bayesian sparse reconstruction: a brute-force approach to astronomical imaging and machine learning
• Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Data
• Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
• Learning Neural Network Subspaces
• Physics-Constrained Bayesian Neural Network for Fluid Flow Reconstruction with Sparse and Noisy Data
• Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations
• Efficient exploration with Double Uncertain Value Networks
• Bridging the Gap Between Explainable AI and Uncertainty Quantification to Enhance Trustability
• Deep Gaussian Processes: A Survey
• Randomized Value Functions via Multiplicative Normalizing Flows
• Uncertainty Quantification for Sparse Deep Learning
• Variance Networks: When Expectation Does Not Meet Your Expectations
• Bayesian Policy Gradients via Alpha Divergence Dropout Inference
• Information Complexity and Generalization Bounds
• Expressive Priors in Bayesian Neural Networks: Kernel Combinations and Periodic Functions
• Deep learning for Gaussian process tomography model selection using the ASDEX Upgrade SXR system
• An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation
• A Simple Probabilistic Method for Deep Classification under Input-Dependent Label Noise
• Distance-Based Learning from Errors for Confidence Calibration
• Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel
• Benchmarking the Neural Linear Model for Regression
• A Variational Bayes Approach to Adaptive Radio Tomography
• Making Sense of Reinforcement Learning and Probabilistic Inference
• Variational Inference to Measure Model Uncertainty in Deep Neural Networks
• Estimating Model Uncertainty of Neural Networks in Sparse Information Form
• DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference
• Bayesian Neural Networks for Reversible Steganography
• Contextual Dropout: An Efficient Sample-Dependent Dropout Module
• Bayesian Convolutional Neural Networks for Limited Data Hyperspectral Remote Sensing Image Classification
• Diversity inducing Information Bottleneck in Model Ensembles
• Towards calibrated and scalable uncertainty representations for neural networks
• Calibration of Model Uncertainty for Dropout Variational Inference
• Predictive Uncertainty Quantification with Compound Density Networks
• Bayesian Deep Learning via Subnetwork Inference
• Deep Evidential Regression
• Bayesian Learning of Neural Network Architectures
• A Tutorial on Sparse Gaussian Processes and Variational Inference
• Bayesian Neural Networks
• Generating Neural Networks with Neural Networks
• Deep Bayesian Active Learning for Multiple Correct Outputs
• Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow
• Meta-Learning surrogate models for sequential decision making
• Quantifying sources of uncertainty in drug discovery predictions with probabilistic models
• Hypermodels for Exploration
• Routing Networks with Co-training for Continual Learning
• Being Bayesian about Categorical Probability
• Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks
• Improving predictions of Bayesian neural nets via local linearization
• Uncertainty in Multitask Transfer Learning
• Bayesian active learning for production, a systematic study and a reusable library
• Interval Neural Networks: Uncertainty Scores
• Uncertainty Quantification in CNN Through the Bootstrap of Convex Neural Networks
• Deep Contextual Multi-armed Bandits
• Kalman meets Bellman: Improving Policy Evaluation through Value Tracking
• Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks
• One Versus all for deep Neural Network Incertitude (OVNNI) quantification
• Interpreting Deep Neural Networks Through Variable Importance
• Eigenvalue Corrected Noisy Natural Gradient
• A Financial Service Chatbot based on Deep Bidirectional Transformers
• Data Uncertainty Learning in Face Recognition
• Improving Back-Translation with Uncertainty-based Confidence Estimation
• Variational Implicit Processes
• Bayesian Graph Neural Networks for Molecular Property Prediction
• Machine learning at the atomic-scale
• Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections
• Individual Claims Forecasting with Bayesian Mixture Density Networks
• Radial and Directional Posteriors for Bayesian Neural Networks
• Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network using Truncated Gaussian Approximation
• Deep density networks and uncertainty in recommender systems
• Almost Surely Stable Deep Dynamics
• Constrained Structured Regression with Convolutional Neural Networks
• Influence of uncertainty estimation techniques on false-positive reduction in liver lesion detection
• The missing radial velocities of Gaia: blind predictions for DR3
• Online Learning in Contextual Bandits using Gated Linear Networks
• Deep Probabilistic Programming Languages: A Qualitative Study
• Prior choice affects ability of Bayesian neural networks to identify unknowns
• Sampling-based Bayesian Inference with gradient uncertainty
• A Batched Scalable Multi-Objective Bayesian Optimization Algorithm
• Stationary Activations for Uncertainty Calibration in Deep Learning
• Bayesian Inference with Certifiable Adversarial Robustness
• Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition
• Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data
• Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework
• The Bayesian Learning Rule
• Uncertainty aware audiovisual activity recognition using deep Bayesian variational inference
• A Convergence Analysis for A Class of Practical Variance-Reduction Stochastic Gradient MCMC
• Scalable Natural Gradient Langevin Dynamics in Practice
• Calibrating Bayesian Generative Machine Learning for Bayesiamplification
• VFunc: a Deep Generative Model for Functions
• Uncertainty-Aware Lookahead Factor Models for Quantitative Investing
• Stochastic Maximum Likelihood Optimization via Hypernetworks
• Structured Bayesian Gaussian process latent variable model
• Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting
• Exploring Uncertainty in Deep Learning for Construction of Prediction Intervals
• A Scale Mixture Perspective of Multiplicative Noise in Neural Networks
• Continual Learning in Deep Neural Network by Using a Kalman Optimiser
• Remote sensing image fusion based on Bayesian GAN
• Bayesian Neural Networks at Scale: A Performance Analysis and Pruning Study
• Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification
• Consistent Sparse Deep Learning: Theory and Computation
• Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series
• Conditional Variational Autoencoder for Learned Image Reconstruction
• VINNAS: Variational Inference-based Neural Network Architecture Search
• AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMC
• Bayesian regression explains how human participants handle parameter uncertainty
• Kernel Implicit Variational Inference
• Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
• Sparsifying Neural Network Connections for Face Recognition
• Multi-Task Variational Information Bottleneck
• Tractable Approximate Gaussian Inference for Bayesian Neural Networks
• Ensemble Model Patching: A Parameter-Efficient Variational Bayesian Neural Network
• Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?
• $M{C}^{2}RAM$: Markov Chain Monte Carlo Sampling in SRAM for Fast Bayesian Inference
• Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimation
• Learn to Estimate Labels Uncertainty for Quality Assurance
• Fast learning rate of deep learning via a kernel perspective
• NOMU: Neural Optimization-based Model Uncertainty
• Bayesian Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of-Distribution Detection
• Comparing Semi-Parametric Model Learning Algorithms for Dynamic Model Estimation in Robotics
• Meta Learning Black-Box Population-Based Optimizers
• Continual Learning Using Bayesian Neural Networks
• Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation
• A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
• Stein Self-Repulsive Dynamics: Benefits From Past Samples
• On Stein Variational Neural Network Ensembles
• On architectural choices in deep learning: From network structure to gradient convergence and parameter estimation
• Flexible Bayesian Nonlinear Model Configuration
• Trust Region Value Optimization using Kalman Filtering
• Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time-Series Forecast
• BAR: Bayesian Activity Recognition using variational inference
• Data augmentation in Bayesian neural networks and the cold posterior effect
• Efficient Ensemble Model Generation for Uncertainty Estimation with Bayesian Approximation in Segmentation
• The Benefit of the Doubt: Uncertainty Aware Sensing for Edge Computing Platforms
• Accelerate CNN via Recursive Bayesian Pruning
• JAXNS: a high-performance nested sampling package based on JAX
• On Batch Normalisation for Approximate Bayesian Inference
• Multi-Loss Sub-Ensembles for Accurate Classification with Uncertainty Estimation
• When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting
• Simplified Stochastic Feedforward Neural Networks
• Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering
• Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference
• Bayesian posterior approximation with stochastic ensembles
• Probabilistic Spatial Transformer Networks
• Know Your Limits: Uncertainty Estimation with ReLU Classifiers Fails at Reliable OOD Detection
• Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights
• Quantification of Uncertainties in Deep Learning-based Environment Perception
• Probabilistically-autoencoded horseshoe-disentangled multidomain item-response theory models
• Bayesian Structure Adaptation for Continual Learning
• Improving Confidence Estimates for Unfamiliar Examples
• Beyond Point Estimate: Inferring Ensemble Prediction Variation from Neuron Activation Strength in Recommender Systems
• A benchmark study on reliable molecular supervised learning via Bayesian learning
• Deep Bayesian regression models
• On Machine Learning and Structure for Mobile Robots
• Quantum Bayesian Neural Networks
• Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory
• Bayesian Learning of LF-MMI Trained Time Delay Neural Networks for Speech Recognition
• Tutorial and Survey on Probabilistic Graphical Model and Variational Inference in Deep Reinforcement Learning
• Efficient Computation Reduction in Bayesian Neural Networks Through Feature Decomposition and Memorization
• Low Complexity Approximate Bayesian Logistic Regression for Sparse Online Learning
• Combining Model and Parameter Uncertainty in Bayesian Neural Networks
• Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates
• On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks
• Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics
• Bayesian Neural Networks at Finite Temperature
• A Survey of Techniques All Classifiers Can Learn from Deep Networks: Models, Optimizations, and Regularization
• Sparse Uncertainty Representation in Deep Learning with Inducing Weights
• A Generative Model for Sampling High-Performance and Diverse Weights for Neural Networks
• Star-Galaxy Separation via Gaussian Processes with Model Reduction
• TRADI: Tracking deep neural network weight distributions for uncertainty estimation
• Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent
• Gradient-Free Adversarial Attacks for Bayesian Neural Networks
• The Monte Carlo Transformer: a stochastic self-attention model for sequence prediction
• Estimation with Uncertainty via Conditional Generative Adversarial Networks
• Adaptively Preconditioned Stochastic Gradient Langevin Dynamics
• B-SCST: Bayesian Self-Critical Sequence Training for Image Captioning
• A Physics-Data-Driven Bayesian Method for Heat Conduction Problems
• Robust quantum dots charge autotuning using neural network uncertainty
• Uncertainty-Aware Deep Classifiers using Generative Models
• Uncertainty Estimation in Cancer Survival Prediction
• Sampling-Free Learning of Bayesian Quantized Neural Networks
• Distilled Thompson Sampling: Practical and Efficient Thompson Sampling via Imitation Learning
• Fast Adaptive Weight Noise
• Continual Learning via Bit-Level Information Preserving
• Bayesian Recurrent Framework for Missing Data Imputation and Prediction with Clinical Time Series
• Robustness via Cross-Domain Ensembles
• Deep kernel processes
• Bayesian Neural Networks with Soft Evidence
• Masked Contrastive Learning for Anomaly Detection
• Harnessing Optoelectronic Noises in a Photonic Generative Network
• Efficient Action Recognition Using Confidence Distillation
• Hidden Markov Neural Networks
• Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
• Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
• Estimating Predictive Uncertainty Under Program Data Distribution Shift
• Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables
• Prediction-based Resource Allocation using Bayesian Neural Networks and Minimum Cost and Maximum Flow Algorithm
• Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning
• Bayesian Variational Optimization for Combinatorial Spaces
• Variational Resampling Based Assessment of Deep Neural Networks under Distribution Shift
• Probabilistic neural network-based reduced-order surrogate for fluid flows
• SkiNet: A Deep Learning Solution for Skin Lesion Diagnosis with Uncertainty Estimation and Explainability
• A Novel Regression Loss for Non-Parametric Uncertainty Optimization
• Approaching Neural Network Uncertainty Realism
• On the Calibration and Uncertainty of Neural Learning to Rank Models
• Efficient Uncertainty Estimation for Semantic Segmentation in Videos
• Uncertainty-aware Remaining Useful Life predictor
• Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks
• Discrete flow posteriors for variational inference in discrete dynamical systems
• On Modelling Label Uncertainty in Deep Neural Networks: Automatic Estimation of Intra-observer Variability in 2D Echocardiography Quality Assessment
• Safety and Robustness in Decision Making: Deep Bayesian Recurrent Neural Networks for Somatic Variant Calling in Cancer
• Probabilistic Discriminative Learning with Layered Graphical Models
• Uncertainty quantification of molecular property prediction using Bayesian neural network models
• High-Order Stochastic Gradient Thermostats for Bayesian Learning of Deep Models
• Variational Bayes: A report on approaches and applications
• Neural Likelihoods for Multi-Output Gaussian Processes
• Radial Prediction Layer
• Closed Form Variational Objectives For Bayesian Neural Networks with a Single Hidden Layer
• Revisiting hard thresholding for DNN pruning
• Adaptive Variational Bayesian Inference for Sparse Deep Neural Network
• RCoNet: Deformable Mutual Information Maximization and High-order Uncertainty-aware Learning for Robust COVID-19 Detection
• Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models
• Bayesian analysis of the prevalence bias: learning and predicting from imbalanced data
• Accurate and Reliable Forecasting using Stochastic Differential Equations
• Explanation and Use of Uncertainty Quantified by Bayesian Neural Network Classifiers for Breast Histopathology Images
• Practical calibration of the temperature parameter in Gibbs posteriors
• Bayesian Convolutional Neural Networks for Seven Basic Facial Expression Classifications
• Pixel Invisibility: Detecting Objects Invisible in Color Images
• Learning a Discriminant Latent Space with Neural Discriminant Analysis
• Variational Bayesian Quantization
• Uncertainty Quantification in Deep Residual Neural Networks
• Bayesian Attention Modules
• A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features
• On Graph Neural Network Ensembles for Large-Scale Molecular Property Prediction
• Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales
• Stabilising priors for robust Bayesian deep learning
• Probability Paths and the Structure of Predictions over Time
• Sampling-free Uncertainty Estimation in Gated Recurrent Units with Exponential Families
• The Bayesian Method of Tensor Networks
• FeTa: A DCA Pruning Algorithm with Generalization Error Guarantees
• Understanding Uncertainty in Bayesian Deep Learning
• Sampling Prediction-Matching Examples in Neural Networks: A Probabilistic Programming Approach
• Revisiting Explicit Regularization in Neural Networks for Well-Calibrated Predictive Uncertainty
• Entropy-based Active Learning of Graph Neural Network Surrogate Models for Materials Properties
• Model Free Barrier Functions via Implicit Evading Maneuvers
• Performance Measurement for Deep Bayesian Neural Network
• Stochastic Gradient MCMC with Stale Gradients
• A Survey on Assessing the Generalization Envelope of Deep Neural Networks: Predictive Uncertainty, Out-of-distribution and Adversarial Samples
• Generator evaluator-selector net for panoptic image segmentation and splitting unfamiliar objects into parts
• TyXe: Pyro-based Bayesian neural nets for Pytorch
• NP-ODE: Neural Process Aided Ordinary Differential Equations for Uncertainty Quantification of Finite Element Analysis
• Efficient and Robust Machine Learning for Real-World Systems
• Uncertainty-Based Biological Age Estimation of Brain MRI Scans
• Verifying the Causes of Adversarial Examples
• Stochastic Bayesian Neural Networks
• Ladder Polynomial Neural Networks
• Approximate Bayesian Optimisation for Neural Networks
• $\Delta$-UQ: Accurate Uncertainty Quantification via Anchor Marginalization
• Probabilistic prediction of the heave motions of a semi-submersible by a deep learning problem model
• Comparison of Graphcore IPUs and Nvidia GPUsfor cosmology applications
• Class Incremental Online Streaming Learning
• Uncertainty Estimation in Deep Neural Networks for Point Cloud Segmentation in Factory Planning
• Transformation Models for Flexible Posteriors in Variational Bayes
• Know Where To Drop Your Weights: Towards Faster Uncertainty Estimation
• Amortized Variational Deep Q Network
• Nearest-Neighbor Neural Networks for Geostatistics
• A Novel Unsupervised Post-Processing Calibration Method for DNNS with Robustness to Domain Shift
• Adaptive Bayesian Reticulum
• Estimating the Uncertainty of Neural Network Forecasts for Influenza Prevalence Using Web Search Activity
• Implicit Priors for Knowledge Sharing in Bayesian Neural Networks
• Generating Diverse Translation from Model Distribution with Dropout
• Variational Laplace for Bayesian neural networks
• Deep Bayesian Recurrent Neural Networks for Somatic Variant Calling in Cancer
• Learning Sparsity of Representations with Discrete Latent Variables
• Bayesian Optimized 1-Bit CNNs
• Uncertainty based Class Activation Maps for Visual Question Answering
• Multiple Angles of Arrival Estimation using Neural Networks
• Modeling continuous-time stochastic processes using $\mathcal{N}$-Curve mixtures
• Thompson Sampling via Local Uncertainty
• The Effect of Prior Lipschitz Continuity on the Adversarial Robustness of Bayesian Neural Networks
• Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval
• Probabilistic Trust Intervals for Out of Distribution Detection
• Robustness Against Outliers For Deep Neural Networks By Gradient Conjugate Priors
• Variational Information Bottleneck Model for Accurate Indoor Position Recognition
• An Approximate Bayesian Long Short-Term Memory Algorithm for Outlier Detection
• Structured DropConnect for Uncertainty Inference in Image Classification
• REST: Performance Improvement of a Black Box Model via RL-based Spatial Transformation
• On the generalization of bayesian deep nets for multi-class classification
• A Kernel Framework to Quantify a Model's Local Predictive Uncertainty under Data Distributional Shifts
• Fundamental Issues Regarding Uncertainties in Artificial Neural Networks
• T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptation
• Decision Theoretic Bootstrapping
• Bayesian Distributional Policy Gradients
• Weight Pruning and Uncertainty in Radio Galaxy Classification
• MPC-guided Imitation Learning of Neural Network Policies for the Artificial Pancreas
• Generative Particle Variational Inference via Estimation of Functional Gradients
• Uncertainty-Aware Multiple Instance Learning from Large-Scale Long Time Series Data
• Sequential Anomaly Detection using Inverse Reinforcement Learning
• Towards On-Chip Bayesian Neuromorphic Learning
• Probabilistic Human Motion Prediction via A Bayesian Neural Network
• Posterior Ratio Estimation of Latent Variables
• Inherent Noise in Gradient Based Methods
• Variational Bayes Neural Network: Posterior Consistency, Classification Accuracy and Computational Challenges
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning
• Bayesian Sampling Bias Correction: Training with the Right Loss Function
• Bayesian deep learning of affordances from RGB images
• Uncertainty in Neural Relational Inference Trajectory Reconstruction
• Combining Model-Free Q-Ensembles and Model-Based Approaches for Informed Exploration
• Logit-based Uncertainty Measure in Classification
• TAG: Task-based Accumulated Gradients for Lifelong learning
• A Bayesian Approach to Invariant Deep Neural Networks
• Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems