154 citations · 487 across the 15 of their papers we have counts for
Showing 2018Show all
2 papers · 1 filter
stat.ML2018★ 12 cited
Probabilistic Meta-Representations Of Neural Networks
Theofanis Karaletsos, Peter Dayan, Zoubin Ghahramani
Existing Bayesian treatments of neural networks are typically characterized by weak prior and approximate posterior distributions according to which all the weights are drawn indep…
cs.LG2018★ 21 cited
Fast Parametric Learning with Activation Memorization
Jack W Rae, Chris Dyer, Peter Dayan +1
Neural networks trained with backpropagation often struggle to identify classes that have been observed a small number of times. In applications where most class labels are rare, s…