[HTML][HTML] A review of uncertainty quantification in deep learning: Techniques, applications and challenges

M Abdar, F Pourpanah, S Hussain, D Rezazadegan… - Information fusion, 2021 - Elsevier
Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

Hands-on Bayesian neural networks—A tutorial for deep learning users

LV Jospin, H Laga, F Boussaid… - IEEE Computational …, 2022 - ieeexplore.ieee.org
Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of
challenging problems. However, since deep learning methods operate as black boxes, the …

A survey of machine unlearning

TT Nguyen, TT Huynh, Z Ren, PL Nguyen… - arXiv preprint arXiv …, 2022 - arxiv.org
Today, computer systems hold large amounts of personal data. Yet while such an
abundance of data allows breakthroughs in artificial intelligence, and especially machine …

Uncertainty quantification in scientific machine learning: Methods, metrics, and comparisons

AF Psaros, X Meng, Z Zou, L Guo… - Journal of Computational …, 2023 - Elsevier
Neural networks (NNs) are currently changing the computational paradigm on how to
combine data with mathematical laws in physics and engineering in a profound way …

Bayesian deep learning and a probabilistic perspective of generalization

AG Wilson, P Izmailov - Advances in neural information …, 2020 - proceedings.neurips.cc
The key distinguishing property of a Bayesian approach is marginalization, rather than using
a single setting of weights. Bayesian marginalization can particularly improve the accuracy …

Conformal time-series forecasting

K Stankeviciute, AM Alaa… - Advances in neural …, 2021 - proceedings.neurips.cc
Current approaches for multi-horizon time series forecasting using recurrent neural networks
(RNNs) focus on issuing point estimates, which is insufficient for decision-making in critical …

Artificial intelligence for science in quantum, atomistic, and continuum systems

X Zhang, L Wang, J Helwig, Y Luo, C Fu, Y Xie… - arXiv preprint arXiv …, 2023 - arxiv.org
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …

Bayesian deep ensembles via the neural tangent kernel

B He, B Lakshminarayanan… - Advances in neural …, 2020 - proceedings.neurips.cc
We explore the link between deep ensembles and Gaussian processes (GPs) through the
lens of the Neural Tangent Kernel (NTK): a recent development in understanding the …

Evaluating scalable uncertainty estimation methods for deep learning-based molecular property prediction

G Scalia, CA Grambow, B Pernici, YP Li… - Journal of chemical …, 2020 - ACS Publications
Advances in deep neural network (DNN)-based molecular property prediction have recently
led to the development of models of remarkable accuracy and generalization ability, with …

A survey on learning to reject

XY Zhang, GS Xie, X Li, T Mei… - Proceedings of the IEEE, 2023 - ieeexplore.ieee.org
Learning to reject is a special kind of self-awareness (the ability to know what you do not
know), which is an essential factor for humans to become smarter. Although machine …