60 citations · 192 across the 18 of their papers we have counts for
19 papers
Cup and Cap Topological Neural Network
Marta Niedostatek, Ferran Hernandez Caralt, Runyue Wang +4
Topological Deep Learning (TDL) is designed to learn features associated not only with nodes but also with edges, triangles and higher dimensional simplices. However, most TDL appr…
Spectral Architecture Search for Neural Network Models
Gianluca Peri, Lorenzo Chicchi, Duccio Fanelli +1
Architecture design and optimization are challenging problems in the field of artificial neural networks. Working in this context, we here present SPARCS (SPectral ARchiteCture Sea…
Extending the RANGE of Graph Neural Networks: Relaying Attention Nodes for Global Encoding
Alessandro Caruso, Jacopo Venturin, Lorenzo Giambagli +3
Graph Neural Networks (GNNs) are routinely used in molecular physics, social sciences, and economics to model many-body interactions in graph-like systems. However, GNNs are inhere…
Global Topological Dirac Synchronization
Timoteo Carletti, Lorenzo Giambagli, Riccardo Muolo +1
Synchronization is a fundamental dynamical state of interacting oscillators, observed in natural biological rhythms and in the brain. Global synchronization which occurs when non-l…
Deterministic versus stochastic dynamical classifiers: opposing random adversarial attacks with noise
Lorenzo Chicchi, Duccio Fanelli, Diego Febbe +4
The Continuous-Variable Firing Rate (CVFR) model, widely used in neuroscience to describe the intertangled dynamics of excitatory biological neurons, is here trained and tested as…
Turing patterns on discrete topologies: from networks to higher-order structures
Riccardo Muolo, Lorenzo Giambagli, Hiroya Nakao +2
Nature is a blossoming of regular structures, signature of self-organization of the underlying microscopic interacting agents. Turing theory of pattern formation is one of the most…
Learning in Wilson-Cowan model for metapopulation
Raffaele Marino, Lorenzo Buffoni, Lorenzo Chicchi +4
The Wilson-Cowan model for metapopulation, a Neural Mass Network Model, treats different subcortical regions of the brain as connected nodes, with connections representing various…
Estimating Global Input Relevance and Enforcing Sparse Representations with a Scalable Spectral Neural Network Approach
Lorenzo Chicchi, Lorenzo Buffoni, Diego Febbe +3
In machine learning practice it is often useful to identify relevant input features. Isolating key input elements, ranked according their respective degree of relevance, can help t…
Complex Recurrent Spectral Network
Lorenzo Chicchi, Lorenzo Giambagli, Lorenzo Buffoni +2
This paper presents a novel approach to advancing artificial intelligence (AI) through the development of the Complex Recurrent Spectral Network (-RSN), an innovative v…
Engineered Ordinary Differential Equations as Classification Algorithm (EODECA): thorough characterization and testing
Raffaele Marino, Lorenzo Buffoni, Lorenzo Chicchi +2
EODECA (Engineered Ordinary Differential Equations as Classification Algorithm) is a novel approach at the intersection of machine learning and dynamical systems theory, presenting…
How a student becomes a teacher: learning and forgetting through Spectral methods
Lorenzo Giambagli, Lorenzo Buffoni, Lorenzo Chicchi +1
In theoretical ML, the teacher-student paradigm is often employed as an effective metaphor for real-life tuition. The above scheme proves particularly relevant when the student net…
Stable Attractors for Neural networks classification via Ordinary Differential Equations (SA-nODE)
Raffaele Marino, Lorenzo Giambagli, Lorenzo Chicchi +2
A novel approach for supervised classification is presented which sits at the intersection of machine learning and dynamical systems theory. At variance with other methodologies th…
Non-parametric analysis of the Hubble Diagram with Neural Networks
Lorenzo Giambagli, Duccio Fanelli, Guido Risaliti +1
The recent extension of the Hubble diagram of Supernovae and quasars to redshifts much higher than 1 prompted a revived interest in non-parametric approaches to test cosmological m…
Global topological synchronization on simplicial and cell complexes
Timoteo Carletti, Lorenzo Giambagli, Ginestra Bianconi
Topological signals, i.e., dynamical variables defined on nodes, links, triangles, etc. of higher-order networks, are attracting increasing attention. However the investigation of…
Diffusion-driven instability of topological signals coupled by the Dirac operator
Lorenzo Giambagli, Lucille Calmon, Riccardo Muolo +2
The study of reaction-diffusion systems on networks is of paramount relevance for the understanding of nonlinear processes in systems where the topology is intrinsically discrete,…
Recurrent Spectral Network (RSN): shaping the basin of attraction of a discrete map to reach automated classification
Lorenzo Chicchi, Duccio Fanelli, Lorenzo Giambagli +2
A novel strategy to automated classification is introduced which exploits a fully trained dynamical system to steer items belonging to different categories toward distinct asymptot…
On the training of sparse and dense deep neural networks: less parameters, same performance
Lorenzo Chicchi, Lorenzo Giambagli, Lorenzo Buffoni +3
Deep neural networks can be trained in reciprocal space, by acting on the eigenvalues and eigenvectors of suitable transfer operators in direct space. Adjusting the eigenvalues, wh…
Mobility-based prediction of SARS-CoV-2 spreading
Lorenzo Chicchi, Lorenzo Giambagli, Lorenzo Buffoni +1
The rapid spreading of SARS-CoV-2 and its dramatic consequences, are forcing policymakers to take strict measures in order to keep the population safe. At the same time, societal a…
Machine learning in spectral domain
Lorenzo Giambagli, Lorenzo Buffoni, Timoteo Carletti +2
Deep neural networks are usually trained in the space of the nodes, by adjusting the weights of existing links via suitable optimization protocols. We here propose a radically new…