249 citations · 699 across the 39 of their papers we have counts for
3 papers · 1 filter
Scaling the Scattering Transform: Deep Hybrid Networks
Edouard Oyallon, Eugene Belilovsky, Sergey Zagoruyko
We use the scattering network as a generic and fixed ini-tialization of the first layers of a supervised hybrid deep network. We show that early layers do not necessarily need to b…
Multiscale Hierarchical Convolutional Networks
Jörn-Henrik Jacobsen, Edouard Oyallon, Stéphane Mallat +1
Deep neural network algorithms are difficult to analyze because they lack structure allowing to understand the properties of underlying transforms and invariants. Multiscale hierar…
Building a Regular Decision Boundary with Deep Networks
Edouard Oyallon
In this work, we build a generic architecture of Convolutional Neural Networks to discover empirical properties of neural networks. Our first contribution is to introduce a state-o…