2 citations · 3 across the 6 of their papers we have counts for
5 papers · 1 filter
Why should we add early exits to neural networks?
Simone Scardapane, Michele Scarpiniti, Enzo Baccarelli +1
Deep neural networks are generally designed as a stack of differentiable layers, in which a prediction is obtained only after running the full stack. Recently, some contributions h…
Widely Linear Kernels for Complex-Valued Kernel Activation Functions
Simone Scardapane, Steven Van Vaerenbergh, Danilo Comminiello +1
Complex-valued neural networks (CVNNs) have been shown to be powerful nonlinear approximators when the input data can be properly modeled in the complex domain. One of the major ch…
Recurrent Neural Networks with Flexible Gates using Kernel Activation Functions
Simone Scardapane, Steven Van Vaerenbergh, Danilo Comminiello +2
Gated recurrent neural networks have achieved remarkable results in the analysis of sequential data. Inside these networks, gates are used to control the flow of information, allow…
Improving Graph Convolutional Networks with Non-Parametric Activation Functions
Simone Scardapane, Steven Van Vaerenbergh, Danilo Comminiello +1
Graph neural networks (GNNs) are a class of neural networks that allow to efficiently perform inference on data that is associated to a graph structure, such as, e.g., citation net…
Complex-valued Neural Networks with Non-parametric Activation Functions
Simone Scardapane, Steven Van Vaerenbergh, Amir Hussain +1
Complex-valued neural networks (CVNNs) are a powerful modeling tool for domains where data can be naturally interpreted in terms of complex numbers. However, several analytical pro…