Bayesian Neural Network

Bayesian neural networks (BNNs) aim to combine the power of deep learning with probabilistic reasoning, enabling models to not only make predictions but also quantify their uncertainty. Current research focuses on improving the efficiency and accuracy of BNN inference, exploring various architectures (like U-Nets and Transformers) and algorithms (including variational inference, MCMC, and ensemble methods) to address challenges like high dimensionality and multimodality in the posterior distribution. This work is significant because reliable uncertainty quantification is crucial for trustworthy AI in safety-critical applications such as medical diagnosis, autonomous driving, and scientific modeling, leading to more robust and explainable AI systems.

Papers

November 10, 2024

BayesNAM: Leveraging Inconsistency for Reliable Explanations
Hoki Kim, Jinseong Park, Yujin Choi, Seungyun Lee, Jaewook Lee
Bayesian Neural Network Hard to Easy Inconsistency Neural Additive Model Consistent Model

November 1, 2024

October 24, 2024

An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation
Farah Alsafadi, Mahmoud Yaseen, Xu Wu
Data Augmentation Bayesian Neural Network Comprehensive Investigation Generative Deep Learning Nuclear Engineering

October 23, 2024

The Probabilistic Tsetlin Machine: A Novel Approach to Uncertainty Quantification
K. Darshana Abeyrathna, Sara El Mekkaoui, Andreas Hafver, Christian Agrell
Uncertainty Quantification High Uncertainty Anticipation Uncertainty Estimation Bayesian Neural Network Novel Approach Tsetlin Machine

October 21, 2024

High-Fidelity Transfer of Functional Priors for Wide Bayesian Neural Networks by Learning Activations
Marcin Sendera, Amin Sorkhei, Tomasz Kuśmierczyk
Network Programming Bayesian Neural Network Wide Neural Network Functional Prior Complex Posterior

October 14, 2024

Improved Depth Estimation of Bayesian Neural Networks
Bart van Erp, Bert de Vries
Depth Estimation Bayesian Neural Network Deeper Network Free Energy Posterior Distribution

October 11, 2024

Edge AI Collaborative Learning: Bayesian Approaches to Uncertainty Estimation
Gleb Radchenko, Victoria Andrea Fill
High Uncertainty Anticipation Estimation Task Uncertainty Estimation Bayesian Neural Network Edge Computing Bayesian Approach Distributed Optimization Edge Cloud Collaborative

October 8, 2024

October 4, 2024

Optimization Proxies using Limited Labeled Data and Training Time -- A Semi-Supervised Bayesian Neural Network Approach
Parikshit Pareek, Kaarthik Sundar, Deepjyoti Deka, Sidhant Misra
Bayesian Neural Network Constrained Optimization Non Convex Optimization Problem Optimization Proxy Training Time Limited Labeled Data Feasibility Constraint

October 2, 2024

Bayesian Binary Search
Vikash Singh, Matthew Khanzadeh, Vincent Davis, Harrison Rush, Emanuele Rossi, Jesse Shrader, Pietro Lio
Bayesian Neural Network Density Estimation Binary Code

September 25, 2024

September 17, 2024

Uncertainty Decomposition and Error Margin Detection of Homodyned-K Distribution in Quantitative Ultrasound
Dorsa Ameri, Ali K. Z. Tehrani, Ivan M. Rosado-Mendez, Hassan Rivaz
Bayesian Neural Network Bayesian Model Quantitative Ultrasound Uncertainty Decomposition K Distribution Error Simulation

September 12, 2024

Detection of Electric Motor Damage Through Analysis of Sound Signals Using Bayesian Neural Networks
Waldemar Bauer, Marta Zagorowska, Jerzy Baranowski
General Analysis Data Detection Bayesian Neural Network Fault Detection Motor Health Monitoring

September 8, 2024

Empowering Bayesian Neural Networks with Functional Priors through Anchored Ensembling for Mechanics Surrogate Modeling Applications
Javad Ghorbanian, Nicholas Casaprima, Audrey Olivier
Bayesian Neural Network Model Ensembling Neural Network Weight Fidelity Model Surrogate Modelling Functional Prior

August 27, 2024

Low-Budget Simulation-Based Inference with Bayesian Neural Networks
Arnaud Delaunoy, Maxence de la Brassinne Bonardeaux, Siddharth Mishra-Sharma, Gilles Louppe
Scientific Inference Bayesian Neural Network Simulation Based Inference Low Budget

August 26, 2024

Bayesian Neural Network

Papers

BayesNAM: Leveraging Inconsistency for Reliable Explanations

Comparative Evaluation of Applicability Domain Definition Methods for Regression Models

Efficient Model Compression for Bayesian Neural Networks

An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation

The Probabilistic Tsetlin Machine: A Novel Approach to Uncertainty Quantification

High-Fidelity Transfer of Functional Priors for Wide Bayesian Neural Networks by Learning Activations

Improved Depth Estimation of Bayesian Neural Networks

Edge AI Collaborative Learning: Bayesian Approaches to Uncertainty Estimation

Predicting Battery Capacity Fade Using Probabilistic Machine Learning Models With and Without Pre-Trained Priors

Robust Domain Generalisation with Causal Invariant Bayesian Neural Networks

Optimization Proxies using Limited Labeled Data and Training Time -- A Semi-Supervised Bayesian Neural Network Approach

Bayesian Binary Search

Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation

Functional Stochastic Gradient MCMC for Bayesian Neural Networks

Uncertainty Decomposition and Error Margin Detection of Homodyned-K Distribution in Quantitative Ultrasound

Detection of Electric Motor Damage Through Analysis of Sound Signals Using Bayesian Neural Networks

Empowering Bayesian Neural Networks with Functional Priors through Anchored Ensembling for Mechanics Surrogate Modeling Applications

Low-Budget Simulation-Based Inference with Bayesian Neural Networks

Function-Space MCMC for Bayesian Wide Neural Networks

Estimating Uncertainty with Implicit Quantile Network