activity
20172026
most citedKafnets: kernel-based non-parametric activation functions for neural networks

2 citations · 3 across the 10 of their papers we have counts for

collaborators
Showing 2019Show all

6 papers · 1 filter

cs.LG2019

Efficient Continual Learning in Neural Networks with Embedding Regularization

Jary Pomponi, Simone Scardapane, Vincenzo Lomonaco +1

Continual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architec…

cs.LG2019

Compressing deep quaternion neural networks with targeted regularization

Riccardo Vecchi, Simone Scardapane, Danilo Comminiello +1

In recent years, hyper-complex deep networks (such as complex-valued and quaternion-valued neural networks) have received a renewed interest in the literature. They find applicatio…

stat.ML2019

Efficient data augmentation using graph imputation neural networks

Indro Spinelli, Simone Scardapane, Michele Scarpiniti +1

Recently, data augmentation in the semi-supervised regime, where unlabeled data vastly outnumbers labeled data, has received a considerable attention. In this paper, we describe an…

cs.LG2019

Missing Data Imputation with Adversarially-trained Graph Convolutional Networks

Indro Spinelli, Simone Scardapane, Aurelio Uncini

Missing data imputation (MDI) is a fundamental problem in many scientific disciplines. Popular methods for MDI use global statistics computed from the entire data set (e.g., the fe…

stat.ML2019

On the Stability and Generalization of Learning with Kernel Activation Functions

Michele Cirillo, Simone Scardapane, Steven Van Vaerenbergh +1

In this brief we investigate the generalization properties of a recently-proposed class of non-parametric activation functions, the kernel activation functions (KAFs). KAFs introdu…

cs.NE2019

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…