Zobrazeno 1 - 10
of 714
pro vyhledávání: '"Chicchi, A."'
Autor:
Marino, Raffaele, Buffoni, Lorenzo, Chicchi, Lorenzo, Di Patti, Francesca, Febbe, Diego, Giambagli, Lorenzo, Fanelli, Duccio
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 types of structural, functional, or effective neuronal connectivity be
Externí odkaz:
http://arxiv.org/abs/2406.16453
Autor:
Chicchi, Lorenzo, Buffoni, Lorenzo, Febbe, Diego, Giambagli, Lorenzo, Marino, Raffaele, Fanelli, Duccio
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 for effective numerical handling. Further, by isolating pivotal
Externí odkaz:
http://arxiv.org/abs/2406.01183
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]. This method stands o
Externí odkaz:
http://arxiv.org/abs/2312.14681
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. The $\mathbb{C}$
Externí odkaz:
http://arxiv.org/abs/2312.07296
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 employ ordinary differential equations for classification purposes,
Externí odkaz:
http://arxiv.org/abs/2311.10387
Publikováno v:
NeurIPS 2023
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 network is overparameterized as compared to the teacher network. Under th
Externí odkaz:
http://arxiv.org/abs/2310.12612
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. These latter are incorporated into the model by taking
Externí odkaz:
http://arxiv.org/abs/2202.04497
Publikováno v:
In Chaos, Solitons and Fractals: the interdisciplinary journal of Nonlinear Science, and Nonequilibrium and Complex Phenomena July 2024 184
Autor:
Federico Chicchi, Marco Marrone
Publikováno v:
Work Organisation, Labour and Globalisation, Vol 17, Iss 2, Pp 197-204 (2023)
Externí odkaz:
https://doaj.org/article/4c92308eb7ba47cf88944fa950bbb572
Publikováno v:
Sci Rep 12, 11201 (2022)
Training of neural networks can be reformulated in spectral space, by allowing eigenvalues and eigenvectors of the network to act as target of the optimization instead of the individual weights. Working in this setting, we show that the eigenvalues c
Externí odkaz:
http://arxiv.org/abs/2108.00940