activity
20172022
most citedOne Model To Learn Them All

258 citations · 952 across the 9 of their papers we have counts for

collaborators

13 papers

cs.LG20223 cited

Exploring Low Rank Training of Deep Neural Networks

Siddhartha Rao Kamalakara, Acyr Locatelli, Bharat Venkitesh +3

Training deep neural networks in low rank, i.e. with factorised layers, is of particular interest to the community: it offers efficiency over unfactorised training in terms of both…

cs.LG2022125 cited

Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval

Pascal Notin, Mafalda Dias, Jonathan Frazer +4

The ability to accurately model the fitness landscape of protein sequences is critical to a wide range of applications, from quantifying the effects of human variants on disease li…

cs.LG20219 cited

Robustness to Pruning Predicts Generalization in Deep Neural Networks

Lorenz Kuhn, Clare Lyle, Aidan N. Gomez +2

Existing generalization measures that aim to capture a model's simplicity based on parameter counts or norms fail to explain generalization in overparameterized deep neural network…

cs.LG2020

Improving compute efficacy frontiers with SliceOut

Pascal Notin, Aidan N. Gomez, Joanna Yoo +1

Pushing forward the compute efficacy frontier in deep learning is critical for tasks that require frequent model re-training or workloads that entail training a large number of mod…

cs.CL202019 cited

Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers

Tim Z. Xiao, Aidan N. Gomez, Yarin Gal

We detect out-of-training-distribution sentences in Neural Machine Translation using the Bayesian Deep Learning equivalent of Transformer models. For this we develop a new measure…

stat.ML201973 cited

A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks

Angelos Filos, Sebastian Farquhar, Aidan N. Gomez +6

Evaluation of Bayesian deep learning (BDL) methods is challenging. We often seek to evaluate the methods' robustness and scalability, assessing whether new tools give `better' unce…