Zobrazeno 1 - 10
of 3 589
pro vyhledávání: '"Tiezzi A"'
Autor:
Melacci, Stefano, Betti, Alessandro, Casoni, Michele, Guidi, Tommaso, Tiezzi, Matteo, Gori, Marco
This paper proposes Hamiltonian Learning, a novel unified framework for learning with neural networks "over time", i.e., from a possibly infinite stream of data, in an online manner, without having access to future information. Existing works focus o
Externí odkaz:
http://arxiv.org/abs/2409.12038
Learning with neural networks from a continuous stream of visual information presents several challenges due to the non-i.i.d. nature of the data. However, it also offers novel opportunities to develop representations that are consistent with the inf
Externí odkaz:
http://arxiv.org/abs/2409.11441
Autor:
Fröhlich, Alek, Ramos, Thiago, Cabello, Gustavo, Buzatto, Isabela, Izbicki, Rafael, Tiezzi, Daniel
Correctly assessing the malignancy of breast lesions identified during ultrasound examinations is crucial for effective clinical decision-making. However, the current "golden standard" relies on manual BI-RADS scoring by clinicians, often leading to
Externí odkaz:
http://arxiv.org/abs/2408.15458
Autor:
Panda, Mahadev Prasad, Tiezzi, Matteo, Vilas, Martina, Roig, Gemma, Eskofier, Bjoern M., Zanca, Dario
We introduce Foveation-based Explanations (FovEx), a novel human-inspired visual explainability (XAI) method for Deep Neural Networks. Our method achieves state-of-the-art performance on both transformer (on 4 out of 5 metrics) and convolutional mode
Externí odkaz:
http://arxiv.org/abs/2408.02123
Effectively learning from sequential data is a longstanding goal of Artificial Intelligence, especially in the case of long sequences. From the dawn of Machine Learning, several researchers engaged in the search of algorithms and architectures capabl
Externí odkaz:
http://arxiv.org/abs/2406.09062
Autor:
Tiezzi, Matteo, Casoni, Michele, Betti, Alessandro, Guidi, Tommaso, Gori, Marco, Melacci, Stefano
A longstanding challenge for the Machine Learning community is the one of developing models that are capable of processing and learning from very long sequences of data. The outstanding results of Transformers-based networks (e.g., Large Language Mod
Externí odkaz:
http://arxiv.org/abs/2402.08132
Autor:
Betti, Alessandro, Casoni, Michele, Gori, Marco, Marullo, Simone, Melacci, Stefano, Tiezzi, Matteo
Optimal control deals with optimization problems in which variables steer a dynamical system, and its outcome contributes to the objective function. Two classical approaches to solving these problems are Dynamic Programming and the Pontryagin Maximum
Externí odkaz:
http://arxiv.org/abs/2312.09310
To react to unforeseen circumstances or amend abnormal situations in communication-centric systems, programmers are in charge of "undoing" the interactions which led to an undesired state. To assist this task, session-based languages can be endowed w
Externí odkaz:
http://arxiv.org/abs/2312.02851
Autor:
Bourr, Khalid, Tiezzi, Francesco
This paper introduces a novel method for translating Business Process Model and Notation (BPMN) diagrams into executable X-Klaim code for Multi-Robot Systems (MRSs). Merging the clarity of BPMN with the operational strength of X-Klaim, we enable the
Externí odkaz:
http://arxiv.org/abs/2311.04126
Autor:
Emmanuel A. Lozada-Soto, Christian Maltecca, Jicai Jiang, John B. Cole, Paul M. VanRaden, Francesco Tiezzi
Publikováno v:
Journal of Dairy Science, Vol 107, Iss 12, Pp 11149-11163 (2024)
ABSTRACT: Although genomic selection has led to considerable improvements in genetic gain, it has also seemingly led to increased rates of inbreeding and homozygosity, which can negatively affect genetic diversity and the long-term sustainability of
Externí odkaz:
https://doaj.org/article/892c5e68942241e98a37fd574008bfe5
