The coupling effect of Lipschitz regularization in deep neural networks

04/12/2019
by   Nicolas Couellan, et al.
0

We investigate robustness of deep feed-forward neural networks when input data are subject to random uncertainties. More specifically, we consider regularization of the network by its Lipschitz constant and emphasize its role. We highlight the fact that this regularization is not only a way to control the magnitude of the weights but has also a coupling effect on the network weights accross the layers. We claim and show evidence on a dataset that this coupling effect brings a tradeoff between robustness and expressiveness of the network. This suggests that Lipschitz regularization should be carefully implemented so as to maintain coupling accross layers.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset