research
∙
10/06/2021
Disentangling deep neural networks with rectified linear units using duality
Despite their success deep neural networks (DNNs) are still largely cons...
research
∙
02/10/2020
Deep Gated Networks: A framework to understand training and generalisation in deep learning
Understanding the role of (stochastic) gradient descent in training and ...
research
∙
09/12/2017