Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Yarin Gal

Yarin Gal

Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

Nov 23, 2022
Neil Band, Tim G. J. Rudner, Qixuan Feng, Angelos Filos, Zachary Nado, Michael W. Dusenberry, Ghassen Jerfel, Dustin Tran, Yarin Gal

Figure 1 for Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

Figure 2 for Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

Figure 3 for Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

Figure 4 for Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

* Published in Neural Information Processing Systems (NeurIPS) 2021 Datasets and Benchmarks Track Proceedings. First two authors contributed equally. Code available at https://rebrand.ly/retina-benchmark

Access Paper or Ask Questions

Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels

Nov 13, 2022
Shreshth A. Malik, Nora L. Eisner, Chris J. Lintott, Yarin Gal

Figure 1 for Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels

Figure 2 for Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels

Figure 3 for Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels

Figure 4 for Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels

* Accepted at the Machine Learning and the Physical Sciences workshop, NeurIPS 2022

Access Paper or Ask Questions

Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translation

Aug 19, 2022
Valentina Salvatelli, Luiz F. G. dos Santos, Souvik Bose, Brad Neuberg, Mark C. M. Cheung, Miho Janvier, Meng Jin, Yarin Gal, Atilim Gunes Baydin

Figure 1 for Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translation

Figure 2 for Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translation

Figure 3 for Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translation

Figure 4 for Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translation

* 16 pages, 8 figures. To be published on ApJ (submitted on Feb 21st, accepted on July 28th)

Access Paper or Ask Questions

Unifying Approaches in Data Subset Selection via Fisher Information and Information-Theoretic Quantities

Aug 01, 2022
Andreas Kirsch, Yarin Gal

Figure 1 for Unifying Approaches in Data Subset Selection via Fisher Information and Information-Theoretic Quantities

Figure 2 for Unifying Approaches in Data Subset Selection via Fisher Information and Information-Theoretic Quantities

Figure 3 for Unifying Approaches in Data Subset Selection via Fisher Information and Information-Theoretic Quantities

Figure 4 for Unifying Approaches in Data Subset Selection via Fisher Information and Information-Theoretic Quantities

* 12.5 pages main paper, 23 pages total

Access Paper or Ask Questions

Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

Jun 16, 2022
Sören Mindermann, Jan Brauner, Muhammed Razzak, Mrinank Sharma, Andreas Kirsch, Winnie Xu, Benedikt Höltgen, Aidan N. Gomez, Adrien Morisot, Sebastian Farquhar, Yarin Gal

Figure 1 for Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

Figure 2 for Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

Figure 3 for Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

Figure 4 for Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

* ICML 2022 (Follow up to arXiv:2107.02565)

Access Paper or Ask Questions

Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling

May 18, 2022
Andreas Kirsch, Jannik Kossen, Yarin Gal

Figure 1 for Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling

Figure 2 for Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling

* 10 pages + references

Access Paper or Ask Questions