4.7k citations · 10.6k across the 33 of their papers we have counts for
1 paper · 1 filter
Moustapha Cisse, Piotr Bojanowski, Edouard Grave +2
We introduce Parseval networks, a form of deep neural networks in which the Lipschitz constant of linear, convolutional and aggregation layers is constrained to be smaller than 1.…