A Short Review on Novel Approaches for Maximum Clique Problem: from Classical algorithms to Graph Neural Networks and Quantum algorithms

R Marino, L Buffoni, B Zavalnij - arxiv preprint arxiv:2403.09742, 2024 - arxiv.org
This manuscript provides a comprehensive review of the Maximum Clique Problem, a
computational problem that involves finding subsets of vertices in a graph that are all …

Stable attractors for neural networks classification via ordinary differential equations (SA-nODE)

R Marino, L Buffoni, L Chicchi… - Machine Learning …, 2024 - iopscience.iop.org
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 that …

Engineered ordinary differential equations as classification algorithm (eodeca): thorough characterization and testing

R Marino, L Buffoni, L Chicchi, L Giambagli… - arxiv preprint arxiv …, 2023 - arxiv.org
EODECA (Engineered Ordinary Differential Equations as Classification Algorithm) is a novel
approach at the intersection of machine learning and dynamical systems theory, presenting …

Learning in Wilson-Cowan model for metapopulation

R Marino, L Buffoni, L Chicchi, F Di Patti… - arxiv preprint arxiv …, 2024 - arxiv.org
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 …

Automatic Input Feature Relevance via Spectral Neural Networks

L Chicchi, L Buffoni, D Febbe, L Giambagli… - arxiv preprint arxiv …, 2024 - arxiv.org
Working with high-dimensional data is a common practice, in the field of machine learning.
Identifying relevant input features is thus crucial, so as to obtain compact dataset more prone …

Deterministic versus stochastic dynamical classifiers: opposing random adversarial attacks with noise

L Chicchi, D Fanelli, D Febbe, L Buffoni… - arxiv preprint arxiv …, 2024 - arxiv.org
The Continuous-Variable Firing Rate (CVFR) model, widely used in neuroscience to
describe the intertangled dynamics of excitatory biological neurons, is here trained and …