Priors in bayesian deep learning: A review

V Fortuin - International Statistical Review, 2022‏ - Wiley Online Library
While the choice of prior is one of the most critical parts of the Bayesian inference workflow,
recent Bayesian deep learning models have often fallen back on vague priors, such as …

Variational Bayesian last layers

J Harrison, J Willes, J Snoek - arxiv preprint arxiv:2404.11599, 2024‏ - arxiv.org
We introduce a deterministic variational formulation for training Bayesian last layer neural
networks. This yields a sampling-free, single-pass model and loss that effectively improves …

Federated learning via meta-variational dropout

I Jeon, M Hong, J Yun, G Kim - Advances in neural …, 2023‏ - proceedings.neurips.cc
Federated Learning (FL) aims to train a global inference model from remotely distributed
clients, gaining popularity due to its benefit of improving data privacy. However, traditional …

Improved uncertainty quantification for neural networks with bayesian last layer

F Fiedler, S Lucia - IEEE Access, 2023‏ - ieeexplore.ieee.org
Uncertainty quantification is an important task in machine learning-a task in which standard
neural networks (NNs) have traditionally not excelled. This can be a limitation for safety …

Bayesian physics-informed extreme learning machine for forward and inverse PDE problems with noisy data

X Liu, W Yao, W Peng, W Zhou - Neurocomputing, 2023‏ - Elsevier
Physics-informed extreme learning machine (PIELM) has recently received significant
attention as a rapid version of physics-informed neural network (PINN) for solving partial …

Bayesian deep learning for cosmic volumes with modified gravity

JE García-Farieta, HJ Hortúa, FS Kitaura - Astronomy & Astrophysics, 2024‏ - aanda.org
Context. The new generation of galaxy surveys will provide unprecedented data that will
allow us to test gravity deviations at cosmological scales at a much higher precision than …

Uncertainty-Aware Incremental Automatic Modulation Classification with Bayesian Neural Network

VC Luu, J Park, JP Hong - IEEE Internet of Things Journal, 2024‏ - ieeexplore.ieee.org
Recent advances in deep learning (DL) have significantly enhanced automatic modulation
classification (AMC), reducing the dependence on intricate feature engineering and …

Online laplace model selection revisited

JA Lin, J Antorán, JM Hernández-Lobato - arxiv preprint arxiv:2307.06093, 2023‏ - arxiv.org
The Laplace approximation provides a closed-form model selection objective for neural
networks (NN). Online variants, which optimise NN parameters jointly with hyperparameters …

Pt-hmc: Optimization-based pre-training with hamiltonian monte-carlo sampling for driver intention recognition

K Vellenga, A Karlsson, HJ Steinhauer… - ACM Transactions on …, 2024‏ - dl.acm.org
Driver intention recognition (DIR) methods mostly rely on deep neural networks (DNNs). To
use DNNs in a safety-critical real-world environment it is essential to quantify how confident …

A rigorous uncertainty-aware quantification framework is essential for reproducible and replicable machine learning workflows

L Pouchard, KG Reyes, FJ Alexander, BJ Yoon - Digital Discovery, 2023‏ - pubs.rsc.org
The capability to replicate the predictions by machine learning (ML) or artificial intelligence
(AI) models and the results in scientific workflows that incorporate such ML/AI predictions is …