Evaluating Bayesian Deep Learning for Radio Galaxy Classification
Abstract
The radio astronomy community is rapidly adopting deep learning techniques to deal with the huge data volumes expected from the next generation of radio observatories. Bayesian neural networks (BNNs) provide a principled way to model uncertainty in the predictions made by such deep learning models and will play an important role in extracting well-calibrated uncertainty estimates on their outputs. In this work, we evaluate the performance of different BNNs against the following criteria: predictive performance, uncertainty calibration and distribution-shift detection for the radio galaxy classification problem.
Cite
Text
Mohan and Scaife. "Evaluating Bayesian Deep Learning for Radio Galaxy Classification." Uncertainty in Artificial Intelligence, 2024.Markdown
[Mohan and Scaife. "Evaluating Bayesian Deep Learning for Radio Galaxy Classification." Uncertainty in Artificial Intelligence, 2024.](https://mlanthology.org/uai/2024/mohan2024uai-evaluating/)BibTeX
@inproceedings{mohan2024uai-evaluating,
title = {{Evaluating Bayesian Deep Learning for Radio Galaxy Classification}},
author = {Mohan, Devina and Scaife, Anna M. M.},
booktitle = {Uncertainty in Artificial Intelligence},
year = {2024},
pages = {2587-2597},
volume = {244},
url = {https://mlanthology.org/uai/2024/mohan2024uai-evaluating/}
}