Zobrazeno 1 - 10
of 191
pro vyhledávání: '"Tudisco, Francesco"'
Adversarial attacks on deep neural network models have seen rapid development and are extensively used to study the stability of these networks. Among various adversarial strategies, Projected Gradient Descent (PGD) is a widely adopted method in comp
Externí odkaz:
http://arxiv.org/abs/2410.12607
Autor:
Sikdar, Satyaki, Venturini, Sara, Charpignon, Marie-Laure, Kumar, Sagar, Rinaldi, Francesco, Tudisco, Francesco, Fortunato, Santo, Majumder, Maimuna S.
Publikováno v:
Nat. Hum. Behav. 8 (2024) 1631-1634
Authors of COVID-19 papers produced during the pandemic were overwhelmingly not subject matter experts. Such a massive inflow of scholars from different expertise areas is both an asset and a potential problem. Domain-informed scientific collaboratio
Externí odkaz:
http://arxiv.org/abs/2410.01838
Using drones to perform human-related tasks can play a key role in various fields, such as defense, disaster response, agriculture, healthcare, and many others. The drone delivery packing problem (DDPP) arises in the context of logistics in response
Externí odkaz:
http://arxiv.org/abs/2406.08430
Autor:
Sittoni, Pietro, Tudisco, Francesco
Implicit-depth neural networks have grown as powerful alternatives to traditional networks in various applications in recent years. However, these models often lack guarantees of existence and uniqueness, raising stability, performance, and reproduci
Externí odkaz:
http://arxiv.org/abs/2403.00720
We propose a novel methodology to solve a key eigenvalue optimization problem which arises in the contractivity analysis of neural ODEs. When looking at contractivity properties of a one layer weight-tied neural ODE $\dot{u}(t)=\sigma(Au(t)+b)$ (with
Externí odkaz:
http://arxiv.org/abs/2402.13092
Autor:
Zangrando, Emanuele, Deidda, Piero, Brugiapaglia, Simone, Guglielmi, Nicola, Tudisco, Francesco
Recent work in deep learning has shown strong empirical and theoretical evidence of an implicit low-rank bias: weight matrices in deep networks tend to be approximately low-rank and removing relatively small singular values during training or from av
Externí odkaz:
http://arxiv.org/abs/2402.03991
Techniques based on $k$-th order Hodge Laplacian operators $L_k$ are widely used to describe the topology as well as the governing dynamics of high-order systems modeled as simplicial complexes. In all of them, it is required to solve a number of lea
Externí odkaz:
http://arxiv.org/abs/2401.15492
Core-periphery detection aims to separate the nodes of a complex network into two subsets: a core that is densely connected to the entire network and a periphery that is densely connected to the core but sparsely connected internally. The definition
Externí odkaz:
http://arxiv.org/abs/2310.19697
Dynamical systems on hypergraphs can display a rich set of behaviours not observable for systems with pairwise interactions. Given a distributed dynamical system with a putative hypergraph structure, an interesting question is thus how much of this h
Externí odkaz:
http://arxiv.org/abs/2306.01813
With the growth of model and data sizes, a broad effort has been made to design pruning techniques that reduce the resource demand of deep learning pipelines, while retaining model performance. In order to reduce both inference and training costs, a
Externí odkaz:
http://arxiv.org/abs/2306.01485