442 citations · 1.6k across the 20 of their papers we have counts for
Showing 2015Show all
2 papers · 1 filter
stat.ML2015★ 251 cited
Adding Gradient Noise Improves Learning for Very Deep Networks
Arvind Neelakantan, Luke Vilnis, Quoc V. Le +4
Deep feedforward and recurrent networks have achieved impressive results in many perception and language processing applications. This success is partially attributed to architectu…
cs.LG2015★ 442 cited
Optimizing Neural Networks with Kronecker-factored Approximate Curvature
James Martens, Roger Grosse
We propose an efficient method for approximating natural gradient descent in neural networks which we call Kronecker-Factored Approximate Curvature (K-FAC). K-FAC is based on an ef…