Search results
May 27, 2024 · [2] Yarin Gal and Zoubin Ghahramani. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In Maria Florina Balcan and Kilian Q. Weinberger, editors, Proceedings of The 33rd International Conference on Machine Learning , volume 48 of Proceedings of Machine Learning Research , pages 1050–1059, New York, New York ...
May 15, 2024 · We also thank Sami Lachgar, Lauren Winer and John Guilyard for their support with narratives and visuals. Finally, we are grateful to Michael Howell, James Manyika, Jeff Dean, Karen DeSalvo, Yossi Matias, Zoubin Ghahramani and Demis Hassabis for their support during the course of this project.
6 days ago · Gal and Ghahramani [2015] Yarin Gal and Zoubin Ghahramani. Bayesian convolutional neural networks with bernoulli approximate variational inference. arXiv preprint arXiv:1506.02158 , 2015.
May 13, 2024 · Tameem Adel, Zoubin Ghahramani, Adrian Weller; Proceedings of the 35th International Conference on Machine Learning, PMLR 80:50-59, 2018. Turing affiliated authors. Weller. Ghahramani. Research areas. Machine learning. Direct link. Interpretability of representations in both deep generative and discriminative models is highly desirable.
4 days ago · Yarin Gal and Zoubin Ghahramani. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In ICML, pages 1050-1059. PMLR, 2016. Google Scholar Digital Library; Audun Jsang. Subjective Logic: A formalism for reasoning under uncertainty. Springer Publishing Company, Incorporated, 2018. Google Scholar
May 6, 2024 · Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a Bayesian Approximation: Representing Model Uncertainty in deep Learning. In International Conference on Machine Learning.
May 10, 2024 · Although confidence estimation and calibration have been extensively studied in the broader machine learning literature (Gal & Ghahramani, 2016; Guo et al., 2017), previous work in the context of NLP mostly required extensive fine-tuning (Kong et al., 2020) or temperature-based scaling (Guo et al., 2017; Jiang et al., 2021), which can be ...
