Zobrazeno 1 - 10
of 6 737
pro vyhledávání: '"Malatesta A"'
We analyze the problem of storing random pattern-label associations using two classes of continuous non-convex weights models, namely the perceptron with negative margin and an infinite-width two-layer neural network with non-overlapping receptive fi
Externí odkaz:
http://arxiv.org/abs/2410.06717
Autor:
Lauditi, Clarissa, Malatesta, Enrico M., Pittorino, Fabrizio, Baldassi, Carlo, Brunel, Nicolas, Zecchina, Riccardo
Multiple neurophysiological experiments have shown that dendritic non-linearities can have a strong influence on synaptic input integration. In this work we model a single neuron as a two-layer computational unit with non-overlapping sign-constrained
Externí odkaz:
http://arxiv.org/abs/2407.07572
Autor:
Kalaj, Silvio, Lauditi, Clarissa, Perugini, Gabriele, Lucibello, Carlo, Malatesta, Enrico M., Negri, Matteo
It has been recently shown that a learning transition happens when a Hopfield Network stores examples generated as superpositions of random features, where new attractors corresponding to such features appear in the model. In this work we reveal that
Externí odkaz:
http://arxiv.org/abs/2407.05658
Autor:
Giorgini, Ludovico T., Jentschura, Ulrich D., Malatesta, Enrico M., Rizzo, Tommaso, Zinn-Justin, Jean
Publikováno v:
Phys.Rev.D 110 (2024) 036003
We discuss numerical aspects of instantons in two- and three-dimensional $\phi^4$ theories with an internal $O(N)$ symmetry group, the so-called $N$-vector model. Combining asymptotic transseries expansions for large argument with convergence acceler
Externí odkaz:
http://arxiv.org/abs/2405.18191
Recent works demonstrated the existence of a double-descent phenomenon for the generalization error of neural networks, where highly overparameterized models escape overfitting and achieve good test performance, at odds with the standard bias-varianc
Externí odkaz:
http://arxiv.org/abs/2401.12610
Autor:
Raji, Ayoub, Caporale, Danilo, Gatti, Francesco, Giove, Andrea, Verucchi, Micaela, Malatesta, Davide, Musiu, Nicola, Toschi, Alessandro, Popitanu, Silviu Roberto, Bagni, Fabio, Bosi, Massimiliano, Liniger, Alexander, Bertogna, Marko, Morra, Daniele, Amerotti, Francesco, Bartoli, Luca, Martello, Federico, Porta, Riccardo
Publikováno v:
Field Robotics, January 2024, Volume 4
The Indy Autonomous Challenge (IAC) brought together for the first time in history nine autonomous racing teams competing at unprecedented speed and in head-to-head scenario, using independently developed software on open-wheel racecars. This paper p
Externí odkaz:
http://arxiv.org/abs/2310.18112
Autor:
Victoria Overbeck, Samantha Malatesta, Tara Carney, Bronwyn Myers, Charles D.H. Parry, Charles R. Horsburgh, Danie Theron, Laura F. White, Robin M. Warren, Karen R. Jacobson, Tara C. Bouton
Publikováno v:
BMC Infectious Diseases, Vol 24, Iss 1, Pp 1-10 (2024)
Abstract Background The COVID-19 pandemic negatively impacted tuberculosis (TB) treatment services, including directly observed therapy (DOT) programs used to promote medication adherence. We compared DOT adherence embedded in a research study before
Externí odkaz:
https://doaj.org/article/38bc401998d245ed8a0f4f30a207349f
Autor:
Malatesta, Enrico M.
In these pedagogic notes I review the statistical mechanics approach to neural networks, focusing on the paradigmatic example of the perceptron architecture with binary an continuous weights, in the classification setting. I will review the Gardner's
Externí odkaz:
http://arxiv.org/abs/2309.09240
Autor:
Malatesta, Ravyn, Uboldi, Lorenzo, Kumar, Evan J., Rojas-Gatjens, Esteban, Moretti, Luca, Cruz, Andy, Menon, Vinod, Cerullo, Giulio, Kandada, Ajay Ram Srimath
Optical microcavities are often proposed as platforms for spectroscopy in the single- and few-photon regime due to strong light-matter coupling. For classical-light spectroscopies, an empty microcavity simply acts as an optical filter. However, we fi
Externí odkaz:
http://arxiv.org/abs/2309.04751
Autor:
Annesi, Brandon Livio, Lauditi, Clarissa, Lucibello, Carlo, Malatesta, Enrico M., Perugini, Gabriele, Pittorino, Fabrizio, Saglietti, Luca
Empirical studies on the landscape of neural networks have shown that low-energy configurations are often found in complex connected structures, where zero-energy paths between pairs of distant solutions can be constructed. Here we consider the spher
Externí odkaz:
http://arxiv.org/abs/2305.10623