159 citations · 308 across the 9 of their papers we have counts for
9 papers
Beyond Multilayer Perceptrons: Investigating Complex Topologies in Neural Networks
Tommaso Boccato, Matteo Ferrante, Andrea Duggento +1
In this study, we explore the impact of network topology on the approximation capabilities of artificial neural networks (ANNs), with a particular focus on complex topologies. We p…
Multimodal and multicontrast image fusion via deep generative models
Giovanna Maria Dimitri, Simeon Spasov, Andrea Duggento +3
Recently, it has become progressively more evident that classic diagnostic labels are unable to reliably describe the complexity and variability of several clinical phenotypes. Thi…
VAESim: A probabilistic approach for self-supervised prototype discovery
Matteo Ferrante, Tommaso Boccato, Simeon Spasov +2
In medicine, curated image datasets often employ discrete labels to describe what is known to be a continuous spectrum of healthy to pathological conditions, such as e.g. the Alzhe…
Contrastive learning for unsupervised medical image clustering and reconstruction
Matteo Ferrante, Tommaso Boccato, Simeon Spasov +2
The lack of large labeled medical imaging datasets, along with significant inter-individual variability compared to clinically established disease classes, poses significant challe…
4Ward: a Relayering Strategy for Efficient Training of Arbitrarily Complex Directed Acyclic Graphs
Tommaso Boccato, Matteo Ferrante, Andrea Duggento +1
Thanks to their ease of implementation, multilayer perceptrons (MLPs) have become ubiquitous in deep learning applications. The graph underlying an MLP is indeed multipartite, i.e.…
An intertwined neural network model for EEG classification in brain-computer interfaces
Andrea Duggento, Mario De Lorenzo, Stefano Bargione +4
The brain computer interface (BCI) is a nonstimulatory direct and occasionally bidirectional communication link between the brain and a computer or an external device. Classically,…
A Tutorial on Time-Evolving Dynamical Bayesian Inference
Tomislav Stankovski, Andrea Duggento, Peter V. E. McClintock +1
In view of the current availability and variety of measured data, there is an increasing demand for powerful signal processing tools that can cope successfully with the associated…
Dynamical Bayesian Inference of Time-evolving Interactions: From a Pair of Coupled Oscillators to Networks of Oscillators
Andrea Duggento, Tomislav Stankovski, Peter V. E. McClintock +1
Living systems have time-evolving interactions that, until recently, could not be identified accurately from recorded time series in the presence of noise. Stankovski et al. (Phys.…
Inference of Time-Evolving Coupled Dynamical Systems in the Presence of Noise
Tomislav Stankovski, Andrea Duggento, Peter V. E. McClintock +1
A new method is introduced for analysis of interactions between time-dependent coupled oscillators, based on the signals they generate. It distinguishes unsynchronized dynamics fro…