Sotabase

Career

· Turing AI Fellow, Alan Turing Institute2018–
· Research Fellow in Computer Science, University of Cambridge2018–
· Professor of Machine Learning, University of Oxford2018–
· Tutorial Fellow in Computer Science, Oxford University, Christ Church2012–
· Expert Advisor, UK Government’s AI Security Institute (AISI)

Publications (260)

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
International Conference on Machine Learning · 2015
10,867
cited
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
Neural Information Processing Systems · 2017
5,478
cited
Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2017
3,677
cited
Deep Bayesian Active Learning with Image Data
International Conference on Machine Learning · 2017
1,891
cited
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
Neural Information Processing Systems · 2015
1,701
cited
Uncertainty in Deep Learning
2016
1,606
cited
Inferring the effectiveness of government interventions against COVID-19
Science · 2020
884
cited
Detecting hallucinations in large language models using semantic entropy
Nature · 2024
879
cited
Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
arXiv.org · 2015
806
cited
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
Neural Information Processing Systems · 2019
714
cited
Concrete Dropout
Neural Information Processing Systems · 2017
647
cited
Disease variant prediction with deep generative models of evolutionary data
Nature · 2021
645
cited
Real Time Image Saliency for Black Box Classifiers
Neural Information Processing Systems · 2017
624
cited
AI models collapse when trained on recursively generated data
Nature · 2024
558
cited
Learning Invariant Representations for Reinforcement Learning without Reconstruction
International Conference on Learning Representations · 2020
539
cited
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
International Conference on Learning Representations · 2023
510
cited
Uncertainty Estimation Using a Single Deep Deterministic Neural Network
International Conference on Machine Learning · 2020
500
cited
The Curse of Recursion: Training on Generated Data Makes Models Forget
arXiv.org · 2023
413
cited
Understanding Measures of Uncertainty for Adversarial Example Detection
Conference on Uncertainty in Artificial Intelligence · 2018
397
cited
Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning
International Joint Conference on Artificial Intelligence · 2017
334
cited
Sotabase