Zobrazeno 1 - 10
of 5 131
pro vyhledávání: '"Vezzani A."'
Finite-width one hidden layer networks with multiple neurons in the readout layer display non-trivial output-output correlations that vanish in the lazy-training infinite-width limit. In this manuscript we leverage recent progress in the proportional
Externí odkaz:
http://arxiv.org/abs/2412.15911
Autor:
Simoni, Alessandro, Marchetti, Francesco, Borghi, Guido, Becattini, Federico, Davoli, Davide, Garattoni, Lorenzo, Francesca, Gianpiero, Seidenari, Lorenzo, Vezzani, Roberto
Despite the recent advances in computer vision research, estimating the 3D human pose from single RGB images remains a challenging task, as multiple 3D poses can correspond to the same 2D projection on the image. In this context, depth data could hel
Externí odkaz:
http://arxiv.org/abs/2409.11104
Autor:
Di Nucci, Davide, Simoni, Alessandro, Tomei, Matteo, Ciuffreda, Luca, Vezzani, Roberto, Cucchiara, Rita
The three-dimensional representation of objects or scenes starting from a set of images has been a widely discussed topic for years and has gained additional attention after the diffusion of NeRF-based approaches. However, an underestimated prerequis
Externí odkaz:
http://arxiv.org/abs/2409.05407
Autor:
Ertl, Veronika, Vezzani, Alberto
We use motivic methods to give a quick proof of Berthelot's conjecture stating that the push-forward map in rigid cohomology of the structural sheaf along a smooth and proper map has a canonical structure of overconvergent F-isocrystal on the base.
Externí odkaz:
http://arxiv.org/abs/2406.02182
Publikováno v:
Chaos 34, 083144 (2024)
We study rare events in the extreme value statistics of stochastic symmetric jump processes with power tails in the distributions of the jumps, using the big-jump principle. The principle states that in the presence of stochastic processes with power
Externí odkaz:
http://arxiv.org/abs/2404.19406
Publikováno v:
Phys. Rev. Research 6, 033159 (2024)
Human behaviour strongly influences the spread of infectious diseases: understanding the interplay between epidemic dynamics and adaptive behaviours is essential to improve response strategies to epidemics, with the goal of containing the epidemic wh
Externí odkaz:
http://arxiv.org/abs/2402.09076
Millions of people around the world are infected with mosquito-borne diseases each year. One of the most dangerous species is Aedes aegypti, the main vector of viruses such as dengue, yellow fever, chikungunya, and Zika, among others. Mosquito preven
Externí odkaz:
http://arxiv.org/abs/2401.16258
We perform accurate numerical experiments with fully-connected (FC) one-hidden layer neural networks trained with a discretized Langevin dynamics on the MNIST and CIFAR10 datasets. Our goal is to empirically determine the regimes of validity of a rec
Externí odkaz:
http://arxiv.org/abs/2401.11004
Publikováno v:
Phys. Rev. Lett. 132, 187101 (2024)
Rare events in the first-passage distributions of jump processes are capable of triggering anomalous reactions or series of events. Estimating their probability is particularly important when the jump probabilities have broad-tailed distributions, an
Externí odkaz:
http://arxiv.org/abs/2309.16227
Autor:
Simoni, Alessandro, Marchetti, Francesco, Borghi, Guido, Becattini, Federico, Seidenari, Lorenzo, Vezzani, Roberto, Del Bimbo, Alberto
Technologies to enable safe and effective collaboration and coexistence between humans and robots have gained significant importance in the last few years. A critical component useful for realizing this collaborative paradigm is the understanding of
Externí odkaz:
http://arxiv.org/abs/2308.12914