no code implementations • 22 Dec 2023 • Raffaele Marino, Lorenzo Buffoni, Lorenzo Chicchi, Lorenzo Giambagli, Duccio Fanelli
EODECA (Engineered Ordinary Differential Equations as Classification Algorithm) is a novel approach at the intersection of machine learning and dynamical systems theory, presenting a unique framework for classification tasks [1].
no code implementations • 12 Dec 2023 • Lorenzo Chicchi, Lorenzo Giambagli, Lorenzo Buffoni, Raffaele Marino, Duccio Fanelli
This paper presents a novel approach to advancing artificial intelligence (AI) through the development of the Complex Recurrent Spectral Network ($\mathbb{C}$-RSN), an innovative variant of the Recurrent Spectral Network (RSN) model.
no code implementations • 17 Nov 2023 • Raffaele Marino, Lorenzo Giambagli, Lorenzo Chicchi, Lorenzo Buffoni, Duccio Fanelli
Recognizing the deep parallels between dense neural networks and dynamical systems, particularly in the light of non-linearities and successive transformations, this manuscript introduces the Engineered Ordinary Differential Equations as Classification Algorithms (EODECAs).
1 code implementation • NeurIPS 2023 • Lorenzo Giambagli, Lorenzo Buffoni, Lorenzo Chicchi, Duccio Fanelli
In theoretical ML, the teacher-student paradigm is often employed as an effective metaphor for real-life tuition.
no code implementations • 19 Apr 2023 • Giuseppe de Vito, Lapo Turrini, Chiara Fornetto, Elena Trabalzini, Pietro Ricci, Duccio Fanelli, Francesco Vanzi, Francesco Saverio Pavone
Our data show that brain-wide nonlinear light-sheet imaging represents a useful tool to investigate circadian rhythm effects on neuronal activity.
no code implementations • 9 Feb 2022 • Lorenzo Chicchi, Duccio Fanelli, Lorenzo Giambagli, Lorenzo Buffoni, Timoteo Carletti
A novel strategy to automated classification is introduced which exploits a fully trained dynamical system to steer items belonging to different categories toward distinct asymptotic attractors.
no code implementations • 17 Jun 2021 • Lorenzo Chicchi, Lorenzo Giambagli, Lorenzo Buffoni, Timoteo Carletti, Marco Ciavarella, Duccio Fanelli
Deep neural networks can be trained in reciprocal space, by acting on the eigenvalues and eigenvectors of suitable transfer operators in direct space.
no code implementations • 16 Feb 2021 • Lorenzo Chicchi, Lorenzo Giambagli, Lorenzo Buffoni, Duccio Fanelli
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.
Disordered Systems and Neural Networks
no code implementations • 17 Dec 2020 • Giuseppe de Vito, Lapo Turrini, Caroline Müllenbroich, Pietro Ricci, Giuseppe Sancataldo, Giacomo Mazzamuto, Natascia Tiso, Leonardo Sacconi, Duccio Fanelli, Ludovico Silvestri, Francesco Vanzi, Francesco Saverio Pavone
Light-sheet fluorescence microscopy (LSFM) enables real-time whole-brain functional imaging in zebrafish larvae.
1 code implementation • 29 May 2020 • Lorenzo Giambagli, Lorenzo Buffoni, Timoteo Carletti, Walter Nocentini, Duccio Fanelli
Interestingly, spectral learning limited to the eigenvalues returns a distribution of the predicted weights which is close to that obtained when training the neural network in direct space, with no restrictions on the parameters to be tuned.