655 citations
- Korea Electric Power Corporation (South Korea)KR8 papers
- University of CambridgeGB8 papers
- Centre National de la Recherche ScientifiqueFR7 papers
- Imperial College LondonGB7 papers
- Laboratoire de Physique des 2 Infinis Irène Joliot-CurieFR7 papers
- Centre de physique des particules de MarseilleFR6 papers
- Stanford UniversityUS6 papers
- Massachusetts Institute of TechnologyUS5 papers
- Meta (Israel)IL5 papers
- The University of MelbourneAU5 papers
- University of OxfordGB5 papers
- Cornell UniversityUS4 papers
Showing 2018 · stat.MLShow all
2 papers · 2 filters
stat.ML2018★ 16 cited
A Statistical Approach to Assessing Neural Network Robustness
Stefan Webb, Tom Rainforth, Yee Whye Teh +1
We present a new approach to assessing the robustness of neural networks based on estimating the proportion of inputs for which a property is violated. Specifically, we estimate th…
stat.ML2018★ 13 cited
BRUNO: A Deep Recurrent Model for Exchangeable Data
Iryna Korshunova, Jonas Degrave, Ferenc Huszár +3
We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations. Our model is provab…