309 citations · 896 across the 12 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 1 cited
Robo-PlaNet: Learning to Poke in a Day
Maxime Chevalier-Boisvert, Guillaume Alain, Florian Golemo +1
Recently, the Deep Planning Network (PlaNet) approach was introduced as a model-based reinforcement learning method that learns environment dynamics directly from pixel observation…
cs.LG2019★ 23 cited
Negative eigenvalues of the Hessian in deep neural networks
Guillaume Alain, Nicolas Le Roux, Pierre-Antoine Manzagol
The loss function of deep networks is known to be non-convex but the precise nature of this nonconvexity is still an active area of research. In this work, we study the loss landsc…