3 citations · 11 across the 10 of their papers we have counts for
5 papers · 1 filter
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…
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…
Kafnets: kernel-based non-parametric activation functions for neural networks
Simone Scardapane, Steven Van Vaerenbergh, Simone Totaro +1
Neural networks are generally built by interleaving (adaptable) linear layers with (fixed) nonlinear activation functions. To increase their flexibility, several authors have propo…
Stochastic Training of Neural Networks via Successive Convex Approximations
Simone Scardapane, Paolo Di Lorenzo
This paper proposes a new family of algorithms for training neural networks (NNs). These are based on recent developments in the field of non-convex optimization, going under the g…
Recursive Multikernel Filters Exploiting Nonlinear Temporal Structure
Steven Van Vaerenbergh, Simone Scardapane, Ignacio Santamaria
In kernel methods, temporal information on the data is commonly included by using time-delayed embeddings as inputs. Recently, an alternative formulation was proposed by defining a…