31 citations · 31 across the 3 of their papers we have counts for
3 papers
Stable Parametrization of Continuous and Piecewise-Linear Functions
Alexis Goujon, Joaquim Campos, Michael Unser
Rectified-linear-unit (ReLU) neural networks, which play a prominent role in deep learning, generate continuous and piecewise-linear (CPWL) functions. While they provide a powerful…
Measuring Complexity of Learning Schemes Using Hessian-Schatten Total Variation
Shayan Aziznejad, Joaquim Campos, Michael Unser
In this paper, we introduce the Hessian-Schatten total variation (HTV) -- a novel seminorm that quantifies the total "rugosity" of multivariate functions. Our motivation for defini…
Deep Neural Networks with Trainable Activations and Controlled Lipschitz Constant
Shayan Aziznejad, Harshit Gupta, Joaquim Campos +1
We introduce a variational framework to learn the activation functions of deep neural networks. Our aim is to increase the capacity of the network while controlling an upper-bound…