no code implementations • 4 Dec 2019 • Nicholas Wilkins, Michael Johnson, Ifeoma Nwogu
While several methods for predicting uncertainty on deep networks have been recently proposed, they do not readily translate to large and complex datasets.
no code implementations • 9 Aug 2019 • Michael Johnson, Jiongyi Cao, Hyunseung Kang
There is an increasing interest in estimating heterogeneity in causal effects in randomized and observational studies.
no code implementations • 5 Mar 2019 • Brendan Fong, Michael Johnson
Lenses are a well-established structure for modelling bidirectional transformations, such as the interactions between a database and a view of it.
1 code implementation • 3 May 2018 • Dimitrios Psaltis, Michael Johnson, Ramesh Narayan, Lia Medeiros, Lindy Blackburn, Geoff Bower
For expected values of the inner scale, the scattering kernel for all models is markedly non-Gaussian at 1. 3 mm but is straightforward to calculate and depends only weakly on the assumed model for the wandering of the magnetic field direction.
High Energy Astrophysical Phenomena