Zobrazeno 1 - 10
of 11 444
pro vyhledávání: '"A. Dominici"'
The electric power sector is one of the largest contributors to greenhouse gas emissions in the world. In recent years, there has been an unprecedented increase in electricity demand driven by the so-called Artificial Intelligence (AI) revolution. Al
Externí odkaz:
http://arxiv.org/abs/2410.09029
Topological Deep Learning (TDL) has emerged as a paradigm to process and learn from signals defined on higher-order combinatorial topological spaces, such as simplicial or cell complexes. Although many complex systems have an asymmetric relational st
Externí odkaz:
http://arxiv.org/abs/2409.08389
Autor:
Koprucu, Nursena, Nigam, Meher Shashwat, Xu, Shicheng, Abere, Biruk, Dominici, Gabriele, Rodriguez, Andrew, Vadgama, Sharvaree, Inal, Berfin, Tono, Alberto
Inspired by Geoffrey Hinton emphasis on generative modeling, To recognize shapes, first learn to generate them, we explore the use of 3D diffusion models for object classification. Leveraging the density estimates from these models, our approach, the
Externí odkaz:
http://arxiv.org/abs/2408.06693
Autor:
Zorzetto, Dafne, Canale, Antonio, Mealli, Fabrizia, Dominici, Francesca, Bargagli-Stoffi, Falco J.
Principal stratification provides a causal inference framework that allows adjustment for confounded post-treatment variables when comparing treatments. Although the literature has focused mainly on binary post-treatment variables, there is a growing
Externí odkaz:
http://arxiv.org/abs/2405.17669
Autor:
Dominici, Gabriele, Barbiero, Pietro, Giannini, Francesco, Gjoreski, Martin, Langhenirich, Marc
Interpretable deep learning aims at developing neural architectures whose decision-making processes could be understood by their users. Among these techniqes, Concept Bottleneck Models enhance the interpretability of neural networks by integrating a
Externí odkaz:
http://arxiv.org/abs/2405.16508
Autor:
Dominici, Gabriele, Barbiero, Pietro, Zarlenga, Mateo Espinosa, Termine, Alberto, Gjoreski, Martin, Marra, Giuseppe, Langheinrich, Marc
Causal opacity denotes the difficulty in understanding the "hidden" causal structure underlying the decisions of deep neural network (DNN) models. This leads to the inability to rely on and verify state-of-the-art DNN-based systems, especially in hig
Externí odkaz:
http://arxiv.org/abs/2405.16507
Autor:
Fenoglio, Dario, Dominici, Gabriele, Barbiero, Pietro, Tonda, Alberto, Gjoreski, Martin, Langheinrich, Marc
Federated Learning (FL), a privacy-aware approach in distributed deep learning environments, enables many clients to collaboratively train a model without sharing sensitive data, thereby reducing privacy risks. However, enabling human trust and contr
Externí odkaz:
http://arxiv.org/abs/2405.15632
Autor:
Battiloro, Claudio, Karaismailoğlu, Ege, Tec, Mauricio, Dasoulas, George, Audirac, Michelle, Dominici, Francesca
Graph neural networks excel at modeling pairwise interactions, but they cannot flexibly accommodate higher-order interactions and features. Topological deep learning (TDL) has emerged recently as a promising tool for addressing this issue. TDL enable
Externí odkaz:
http://arxiv.org/abs/2405.15429
We construct new Carroll strings in flat space by considering the Carroll limit of equivalent relativistic string theories at classical level. In the limit these Carroll strings are no longer equivalent and have different degrees of freedom. This fac
Externí odkaz:
http://arxiv.org/abs/2403.02152
Autor:
Dominici, Gabriele, Barbiero, Pietro, Giannini, Francesco, Gjoreski, Martin, Marra, Giuseppe, Langheinrich, Marc
Current deep learning models are not designed to simultaneously address three fundamental questions: predict class labels to solve a given classification task (the "What?"), simulate changes in the situation to evaluate how this impacts class predict
Externí odkaz:
http://arxiv.org/abs/2402.01408