Andreas Kirsch
Andreas Kirsch
Verified email at cs.ox.ac.uk - Homepage
Title
Cited by
Cited by
Year
Batchbald: Efficient and diverse batch acquisition for deep bayesian active learning
A Kirsch, J van Amersfoort, Y Gal
Advances in Neural Information Processing Systems, 7024-7035, 2019
772019
Unpacking information bottlenecks: Unifying information-theoretic objectives in deep learning
A Kirsch, C Lyle, Y Gal
arXiv preprint arXiv:2003.12537, 2020
22020
Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty
J Mukhoti, A Kirsch, J van Amersfoort, PHS Torr, Y Gal
arXiv preprint arXiv:2102.11582, 2021
2021
PowerEvaluationBALD: Efficient Evaluation-Oriented Deep (Bayesian) Active Learning with Stochastic Acquisition Functions
A Kirsch
arXiv preprint arXiv:2101.03552, 2021
2021
Scalable Training with Information Bottleneck Objectives
A Kirsch, C Lyle, Y Gal
Workshop Uncertainty & Robustness in Deep Learning at Int. Conf. on Machine …, 2020
2020
MDP environments for the OpenAI Gym
A Kirsch
arXiv preprint arXiv:1709.09069, 2017
2017
The system can't perform the operation now. Try again later.
Articles 1–6