James Urquhart Allingham
James Urquhart Allingham
Preverjeni e-poštni naslov na cam.ac.uk - Domača stran
Depth uncertainty in neural networks
J Antorán*, J Allingham*, JM Hernández-Lobato
Advances in neural information processing systems 33, 10620-10634, 2020
Bayesian deep learning via subnetwork inference
E Daxberger, E Nalisnick*, JU Allingham*, J Antorán*, ...
International Conference on Machine Learning, 2510-2521, 2021
Adapting the linearised laplace model evidence for modern deep learning
J Antorán, D Janz*, JU Allingham*, E Daxberger, RR Barbano, ...
International Conference on Machine Learning, 796-821, 2022
Sparse MoEs meet efficient ensembles
JU Allingham, F Wenzel, ZE Mariet, B Mustafa, J Puigcerver, N Houlsby, ...
Transactions on Machine Learning Research, 2021
A simple zero-shot prompt weighting technique to improve prompt ensembling in text-image models
JU Allingham*, J Ren*, MW Dusenberry, X Gu, Y Cui, D Tran, JZ Liu, ...
International Conference on Machine Learning, 547-568, 2023
Deep classifiers with label noise modeling and distance awareness
V Fortuin, M Collier, F Wenzel, J Allingham, J Liu, D Tran, ...
arXiv preprint arXiv:2110.02609, 2021
Linearised laplace inference in networks with normalisation layers and the neural g-prior
J Antorán, JU Allingham, D Janz, E Daxberger, E Nalisnick, ...
Fourth Symposium on Advances in Approximate Bayesian Inference, 2022
Variational depth search in ResNets
J Antorán, JU Allingham, JM Hernández-Lobato
arXiv preprint arXiv:2002.02797, 2020
Unsupervised automatic dataset repair
JU Allingham
Master’s thesis in advanced computer science, Computer Laboratory …, 2018
Addressing bias in active learning with depth uncertainty networks... or not
C Murray, JU Allingham, J Antorán, JM Hernández-Lobato
I (Still) Can't Believe It's Not Better! Workshop at NeurIPS 2021, 59-63, 2022
Model AI Assignments 2020
TW Neller, S Keeley, M Guerzhoy, W Hoenig, J Li, S Koenig, A Soni, ...
Proceedings of the AAAI conference on artificial intelligence 34 (09), 13509 …, 2020
Towards anytime classification in early-exit architectures by enforcing conditional monotonicity
M Jazbec, J Allingham, D Zhang, E Nalisnick
Advances in Neural Information Processing Systems 36, 2024
Learning Generative Models with Invariance to Symmetries
JU Allingham, J Antoran, S Padhy, E Nalisnick, JM Hernández-Lobato
NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations, 2022
A Product of Experts Approach to Early-Exit Ensembles
JU Allingham, E Nalisnick
Technical report, 2022
Depth Uncertainty Networks for Active Learning
C Murray, JU Allingham, J Antorán, JM Hernández-Lobato
arXiv preprint arXiv:2112.06796, 2021
A Generative Model of Symmetry Transformations
JU Allingham, BK Mlodozeniec, S Padhy, J Antorán, D Krueger, ...
arXiv preprint arXiv:2403.01946, 2024
Ensembling mixture-of-experts neural networks
R Jenatton, CR Ruiz, D Tran, JU Allingham, F Wenzel, ZE Mariet, ...
US Patent App. 17/960,780, 2023
Sistem trenutno ne more izvesti postopka. Poskusite znova pozneje.
Članki 1–17