55 citations · 113 across the 25 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
stat.ML2019
Deep ReLU Networks Have Surprisingly Few Activation Patterns
Boris Hanin, David Rolnick
The success of deep networks has been attributed in part to their expressivity: per parameter, deep networks can approximate a richer class of functions than shallow networks. In R…
stat.ML2019★ 55 cited
Complexity of Linear Regions in Deep Networks
Boris Hanin, David Rolnick
It is well-known that the expressivity of a neural network depends on its architecture, with deeper networks expressing more complex functions. In the case of networks that compute…