Masked Bayesian neural networks: Theoretical guarantee and its posterior inference

I Kong, D Yang, J Lee, I Ohn… - … on Machine Learning, 2023 - proceedings.mlr.press
Bayesian approaches for learning deep neural networks (BNN) have been received much
attention and successfully applied to various applications. Particularly, BNNs have the merit …

Posterior Uncertainty Quantification in Neural Networks using Data Augmentation

L Wu, SA Williamson - International Conference on Artificial …, 2024 - proceedings.mlr.press
In this paper, we approach the problem of uncertainty quantification in deep learning
through a predictive framework, which captures uncertainty in model parameters by …

Optimizing a deep learning framework for accurate detection of the Earth's ionospheric plasma structures from all-sky airglow images

S Chakrabarti, D Patgiri, R Rathi, G Dixit… - Advances in Space …, 2024 - Elsevier
The ionosphere, part of the Earth's atmosphere, where different plasma
irregularities/structures are generated through various electrodynamical processes. Airglow …

Bag of Tricks for In-Distribution Calibration of Pretrained Transformers

J Kim, D Na, S Choi, S Lim - ar**_Deep_Neural_Network/21542988/1/files/38183658.pdf" data-clk="hl=ca&sa=T&oi=gga&ct=gga&cd=9&d=16130694768508619301&ei=JYG1Z5aLBJ-bieoPirWwkQI" data-clk-atid="JUo1iW29298J" target="_blank">[PDF] purdue.edu

A Graybox Defense Through Bootstrap** Deep Neural Network

K Sullivan - 2022 - search.proquest.com
Building a robust deep neural network (DNN) framework turns out to be a very difficult task
as adaptive attacks are developed that break a robust DNN strategy. In this work we first …