Papers
Topics
Authors
Recent
2000 character limit reached

Evaluating Bayesian deep learning for radio galaxy classification

Published 28 May 2024 in cs.LG and astro-ph.IM | (2405.18351v1)

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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. The seventh data release of the sloan digital sky survey. The Astrophysical Journal Supplement Series, 182(2):543, 2009.
  2. Proximity variational inference. In International Conference on Artificial Intelligence and Statistics, pages 1961–1969. PMLR, 2018.
  3. A K Aniyan and K Thorat. Classifying Radio Galaxies with the Convolutional Neural Network. The Astrophysical Journal Supplement Series, 230(2):20, 2017. ISSN 1538-4365. 10.3847/1538-4365/aa7333. URL http://dx.doi.org/10.3847/1538-4365/aa7333.
  4. The FIRST Survey: Faint Images of the Radio Sky at Twenty Centimeters. Astrophysical Journal, 450:559, September 1995. 10.1086/176166.
  5. On the fundamental dichotomy in the local radio-AGN population: accretion, evolution and host galaxy properties. Monthly Notices of the Royal Astronomical Society, 421(2):1569–1582, 4 2012. ISSN 0035-8711. 10.1111/j.1365-2966.2012.20414.x. URL https://doi.org/10.1111/j.1365-2966.2012.20414.x.
  6. Michael Betancourt. A conceptual introduction to hamiltonian monte carlo. arXiv preprint arXiv:1701.02434, 2017.
  7. Variational Inference: A Review for Statisticians. arXiv e-prints, art. arXiv:1601.00670, January 2016.
  8. Weight Uncertainty in Neural Networks. arXiv e-prints, art. arXiv:1505.05424, May 2015.
  9. Attention-gating for improved radio galaxy classification. Monthly Notices of the Royal Astronomical Society, 501(3):4579–4595, 2021.
  10. Unlabelled data improves bayesian uncertainty calibration under covariate shift. In International Conference on Machine Learning, pages 1392–1402. PMLR, 2020.
  11. Scaling hamiltonian monte carlo inference for bayesian neural networks with symmetric splitting. In Uncertainty in Artificial Intelligence, pages 675–685. PMLR, 2021.
  12. The NRAO VLA Sky Survey. Astronomical Journal, 115(5):1693–1716, May 1998. 10.1086/300337.
  13. Laplace redux-effortless bayesian deep learning. Advances in Neural Information Processing Systems, 34:20089–20103, 2021.
  14. The morphology of extragalactic radio sources of high and low luminosity. Monthly Notices of the Royal Astronomical Society, 167:31P–36P, May 1974. 10.1093/mnras/167.1.31P.
  15. The morphology of extragalactic radio sources of high and low luminosity. Monthly Notices of the Royal Astronomical Society, 167(1):31P–36P, 1974.
  16. Bayesian convolutional neural networks with bernoulli approximate variational inference. arXiv preprint arXiv:1506.02158, 2015.
  17. Inference from iterative simulation using multiple sequences. Statistical science, pages 457–472, 1992.
  18. Gopal-Krishna and P. J. Wiita. Extragalactic radio sources with hybrid morphology: implications for the Fanaroff-Riley dichotomy. Astronomy and Astrophysics, 363:507–516, November 2000.
  19. Alex Graves. Practical variational inference for neural networks. In Proceedings of the 24th International Conference on Neural Information Processing Systems, NIPS’11, page 2348–2356, Red Hook, NY, USA, 2011. Curran Associates Inc. ISBN 9781618395993.
  20. Mightee: total intensity radio continuum imaging and the cosmos/xmm-lss early science fields. Monthly Notices of the Royal Astronomical Society, 509(2):2150–2168, 2022.
  21. Data analysis recipes: Using markov chain monte carlo. The Astrophysical Journal Supplement Series, 236(1):11, 2018.
  22. Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods. Machine Learning, 110:457–506, 2021.
  23. Scalable marginal likelihood estimation for model selection in deep learning. In International Conference on Machine Learning, pages 4563–4573. PMLR, 2021.
  24. What are bayesian neural network posteriors really like? In International conference on machine learning, pages 4629–4640. PMLR, 2021.
  25. The bayesian learning rule. arXiv preprint arXiv:2107.04562, 2021.
  26. On the convergence of black-box variational inference. Advances in Neural Information Processing Systems (to Appear), 36:1–2, 2023.
  27. Improving model calibration with accuracy versus uncertainty optimization. Advances in Neural Information Processing Systems, 33:18237–18248, 2020.
  28. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems, 30, 2017.
  29. Well-calibrated model uncertainty with temperature scaling for dropout variational inference. arXiv preprint arXiv:1909.13550, 2019.
  30. A tutorial on energy-based learning. Predicting structured data, 1(0), 2006.
  31. Energy-based out-of-distribution detection. Advances in neural information processing systems, 33:21464–21475, 2020.
  32. Morphological classification of radio galaxies: capsule networks versus convolutional neural networks. Monthly Notices of the Royal Astronomical Society, 487(2):1729–1744, August 2019. 10.1093/mnras/stz1289.
  33. David J. C. MacKay. A Practical Bayesian Framework for Backpropagation Networks. Neural Computation, 4(3):448–472, 05 1992a. ISSN 0899-7667. 10.1162/neco.1992.4.3.448. URL https://doi.org/10.1162/neco.1992.4.3.448.
  34. David J. C. MacKay. The evidence framework applied to classification networks. Neural Computation, 4(5):720–736, 1992b. 10.1162/neco.1992.4.5.720.
  35. Andrés R Masegosa. Learning under model misspecification: Applications to variational and ensemble methods. arXiv preprint arXiv:1912.08335, 2019.
  36. Revisiting the fanaroff–riley dichotomy and radio-galaxy morphology with the lofar two-metre sky survey (lotss). Monthly Notices of the Royal Astronomical Society, 488(2):2701–2721, 2019.
  37. H. Miraghaei and P. N. Best. The nuclear properties and extended morphologies of powerful radio galaxies: The roles of host galaxy and environment. Monthly Notices of the Royal Astronomical Society, 466(4):4346–4363, 5 2017. ISSN 13652966. 10.1093/mnras/stx007.
  38. Quantifying uncertainty in deep learning approaches to radio galaxy classification. Monthly Notices of the Royal Astronomical Society, 511(3):3722–3740, 2022.
  39. A view of the em algorithm that justifies incremental, sparse, and other variants. In Learning in graphical models, pages 355–368. Springer, 1998.
  40. Radford M Neal et al. Mcmc using hamiltonian dynamics. Handbook of markov chain monte carlo, 2(11):2, 2011.
  41. Disentangling the roles of curation, data-augmentation and the prior in the cold posterior effect. Advances in Neural Information Processing Systems, 34:12738–12748, 2021.
  42. VLA observations of 57 sources in clusters of galaxies. Astronomical Journal, 90:927–953, June 1985. 10.1086/113801.
  43. Mirabest: a data set of morphologically classified radio galaxies for machine learning. RAS Techniques and Instruments, 2(1):293–306, 2023.
  44. Good initializations of variational bayes for deep models. In International Conference on Machine Learning, pages 5487–5497. PMLR, 2019.
  45. L. Rudnick and F. N. Owen. Head-tail radio sources in clusters of galaxies. Astrophysical Journal, Letters, 203:L107–L111, February 1976. 10.1086/182030.
  46. Fanaroff–riley classification of radio galaxies using group-equivariant convolutional neural networks. Monthly Notices of the Royal Astronomical Society, 503(2):2369–2379, 2021.
  47. Radio galaxies with a ‘double-double morphology’ - I. Analysis of the radio properties and evidence for interrupted activity in active galactic nuclei. Monthly Notices of the Royal Astronomical Society, 315(2):371–380, June 2000. 10.1046/j.1365-8711.2000.03430.x.
  48. Beyond deep ensembles–a large-scale evaluation of bayesian deep learning under distribution shift. arXiv preprint arXiv:2306.12306, 2023.
  49. Variational learning is effective for large deep networks. arXiv preprint arXiv:2402.17641, 2024.
  50. Radio galaxy zoo: using semi-supervised learning to leverage large unlabelled data sets for radio galaxy classification under data set shift. Monthly Notices of the Royal Astronomical Society, 514(2):2599–2613, 2022.
  51. Radio galaxy zoo: towards building the first multipurpose foundation model for radio astronomy with self-supervised learning. RAS Techniques and Instruments, 3(1):19–32, 2024.
  52. Ursabench: A system for comprehensive benchmarking of bayesian deep neural network models and inference methods. Proceedings of Machine Learning and Systems, 4:217–237, 2022.
  53. Galaxy zoo decals: Detailed visual morphology measurements from volunteers and deep learning for 314 000 galaxies. Monthly Notices of the Royal Astronomical Society, 509(3):3966–3988, 2022.
  54. Bayesian learning via stochastic gradient langevin dynamics. In Proceedings of the 28th international conference on machine learning (ICML-11), pages 681–688. Citeseer, 2011.
  55. How good is the bayes posterior in deep neural networks really? In Proceedings of the 37th International Conference on Machine Learning, ICML’20. JMLR.org, 2020.
  56. Evaluating approximate inference in bayesian deep learning. In NeurIPS 2021 Competitions and Demonstrations Track, pages 113–124. PMLR, 2022.
  57. Quantifying aleatoric and epistemic uncertainty in machine learning: Are conditional entropy and mutual information appropriate measures? In Uncertainty in Artificial Intelligence, pages 2282–2292. PMLR, 2023.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now

Whiteboard

Paper to Video (Beta)

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Tweets

Sign up for free to view the 2 tweets with 18 likes about this paper.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up for Free