Recent advances and applications of deep learning methods in materials science

K Choudhary, B DeCost, C Chen, A Jain… - npj Computational …, 2022 - nature.com
Deep learning (DL) is one of the fastest-growing topics in materials data science, with
rapidly emerging applications spanning atomistic, image-based, spectral, and textual data …

[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 …

Quantifying uncertainty in answers from any language model and enhancing their trustworthiness

J Chen, J Mueller - Proceedings of the 62nd Annual Meeting of the …, 2024 - aclanthology.org
We introduce BSDetector, a method for detecting bad and speculative answers from a
pretrained Large Language Model by estimating a numeric confidence score for any output …

Uncertainty estimation of transformer predictions for misclassification detection

A Vazhentsev, G Kuzmin, A Shelmanov… - Proceedings of the …, 2022 - aclanthology.org
Uncertainty estimation (UE) of model predictions is a crucial step for a variety of tasks such
as active learning, misclassification detection, adversarial attack detection, out-of-distribution …

Quantifying uncertainty in answers from any language model via intrinsic and extrinsic confidence assessment

J Chen, J Mueller - arxiv preprint arxiv:2308.16175, 2023 - arxiv.org
We introduce BSDetector, a method for detecting bad and speculative answers from a
pretrained Large Language Model by estimating a numeric confidence score for any output …

Stochastic neural radiance fields: Quantifying uncertainty in implicit 3d representations

J Shen, A Ruiz, A Agudo… - … Conference on 3D …, 2021 - ieeexplore.ieee.org
Neural Radiance Fields (NeRF) has become a popular framework for learning implicit 3D
representations and addressing different tasks such as novel-view synthesis or depth-map …

Diversity and generalization in neural network ensembles

LA Ortega, R Cabañas… - … Conference on Artificial …, 2022 - proceedings.mlr.press
Ensembles are widely used in machine learning and, usually, provide state-of-the-art
performance in many prediction tasks. From the very beginning, the diversity of an ensemble …

Fast, accurate, and simple models for tabular data via augmented distillation

R Fakoor, JW Mueller, N Erickson… - Advances in …, 2020 - proceedings.neurips.cc
Automated machine learning (AutoML) can produce complex model ensembles by stacking,
bagging, and boosting many individual models like trees, deep networks, and nearest …

Neural ensemble search for uncertainty estimation and dataset shift

S Zaidi, A Zela, T Elsken, CC Holmes… - Advances in Neural …, 2021 - proceedings.neurips.cc
Ensembles of neural networks achieve superior performance compared to standalone
networks in terms of accuracy, uncertainty calibration and robustness to dataset shift. Deep …

Bayesian uncertainty analysis for underwater 3D reconstruction with neural radiance fields

H Lian, X Li, Y Qu, J Du, Z Meng, J Liu… - Applied Mathematical …, 2025 - Elsevier
Neural radiance fields (NeRFs) are a deep learning technique that generates novel views of
3D scenes from multi-view images. As an extension of NeRFs, SeaThru-NeRF mitigates the …