Evaluating Bayesian deep learning for radio galaxy classification

Devina Mohan, Anna M. M. Scaife
Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence, PMLR 244:2587-2597, 2024.

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 this Paper

BibTeX
@InProceedings{pmlr-v244-mohan24a, title = {Evaluating Bayesian deep learning for radio galaxy classification}, author = {Mohan, Devina and Scaife, Anna M. M.}, booktitle = {Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence}, pages = {2587--2597}, year = {2024}, editor = {Kiyavash, Negar and Mooij, Joris M.}, volume = {244}, series = {Proceedings of Machine Learning Research}, month = {15--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v244/main/assets/mohan24a/mohan24a.pdf}, url = {https://proceedings.mlr.press/v244/mohan24a.html}, 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.} }
Endnote
%0 Conference Paper %T Evaluating Bayesian deep learning for radio galaxy classification %A Devina Mohan %A Anna M. M. Scaife %B Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2024 %E Negar Kiyavash %E Joris M. Mooij %F pmlr-v244-mohan24a %I PMLR %P 2587--2597 %U https://proceedings.mlr.press/v244/mohan24a.html %V 244 %X 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.
APA
Mohan, D. & Scaife, A.M.M.. (2024). Evaluating Bayesian deep learning for radio galaxy classification. Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 244:2587-2597 Available from https://proceedings.mlr.press/v244/mohan24a.html.

Related Material