no code implementations • 27 Feb 2024 • Flavio Petruzzellis, Alberto Testolin, Alessandro Sperduti
Large Language Models (LLMs) have revolutionized the field of Natural Language Processing thanks to their ability to reuse knowledge acquired on massive text corpora on a wide variety of downstream tasks, with minimal (if any) tuning steps.
no code implementations • 27 Feb 2024 • Flavio Petruzzellis, Alberto Testolin, Alessandro Sperduti
Modern neural network architectures still struggle to learn algorithmic procedures that require to systematically apply compositional rules to solve out-of-distribution problem instances.
1 code implementation • 9 Jan 2024 • Alberto Testolin, Kuinan Hou, Marco Zorzi
Humans can readily judge the number of objects in a visual scene, even without counting, and such a skill has been documented in many animal species and babies prior to language development and formal schooling.
1 code implementation • 29 Jun 2023 • Flavio Petruzzellis, Alberto Testolin, Alessandro Sperduti
Solving symbolic reasoning problems that require compositionality and systematicity is considered one of the key ingredients of human intelligence.
no code implementations • 11 May 2023 • Lorenzo Tausani, Alberto Testolin, Marco Zorzi
Generative neural networks can produce data samples according to the statistical properties of their training distribution.
no code implementations • 14 Mar 2023 • Alberto Testolin
Creating learning models that can exhibit sophisticated reasoning skills is one of the greatest challenges in deep learning research, and mathematics is rapidly becoming one of the target domains for assessing scientific progress in this direction.
no code implementations • 17 Jan 2023 • Flavio Petruzzellis, Ling Xuan Chen, Alberto Testolin
Acquiring mathematical skills is considered a key challenge for modern Artificial Intelligence systems.
no code implementations • 28 Nov 2022 • Burla Nur Korkmaz, Roee Diamant, Gil Danino, Alberto Testolin
Effective conservation of maritime environments and wildlife management of endangered species require the implementation of efficient, accurate and scalable solutions for environmental monitoring.
no code implementations • 12 Jul 2022 • Matteo Zambra, Alberto Testolin, Marco Zorzi
Deep belief networks (DBNs) are stochastic neural networks that can extract rich internal representations of the environment from the sensory data.
1 code implementation • 6 Jul 2022 • Samuel Cognolato, Alberto Testolin
Mathematical reasoning is one of the most impressive achievements of human intellect but remains a formidable challenge for artificial intelligence systems.
no code implementations • 8 Mar 2021 • Federico Venturini, Federico Mason, Francesco Pase, Federico Chiariotti, Alberto Testolin, Andrea Zanella, Michele Zorzi
The proposed framework relies on the possibility for the UAVs to exchange some information through a communication channel, in order to achieve context-awareness and implicitly coordinate the swarm's actions.
no code implementations • 25 Jan 2020 • Mattia Lecci, Paolo Testolina, Mattia Rebato, Alberto Testolin, Michele Zorzi
With the advent of millimeter wave (mmWave) communications, the combination of a detailed 5G network simulator with an accurate antenna radiation model is required to analyze the realistic performance of complex cellular scenarios.
1 code implementation • 27 Dec 2019 • Matteo Zambra, Alberto Testolin, Amos Maritan
Network science can offer fundamental insights into the structural and functional properties of complex systems.
no code implementations • 29 Aug 2019 • Paolo Testolina, Mattia Lecci, Mattia Rebato, Alberto Testolin, Jonathan Gambini, Roberto Flamini, Christian Mazzucco, Michele Zorzi
Therefore, it is possible to perform a global numerical optimization over the vast multi-dimensional parameter space, in a fraction of the time that would be required by a simple brute-force search.
no code implementations • 31 Jul 2019 • Alberto Cenzato, Alberto Testolin, Marco Zorzi
In recent years, a variety of approaches have been proposed for learning to predict the physical dynamics of objects interacting in a visual scene.
no code implementations • 16 Jul 2019 • Alberto Testolin, Serena Dolfi, Mathijs Rochus, Marco Zorzi
Numerosity perception is foundational to mathematical learning, but its computational bases are strongly debated.
no code implementations • 28 Sep 2018 • Alberto Testolin, Michele Piccolini, Samir Suweis
Thanks to the availability of large scale digital datasets and massive amounts of computational power, deep learning algorithms can learn representations of data by exploiting multiple levels of abstraction.