Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Faggi, Lapo"'
Autor:
Meloni, Enrico, Faggi, Lapo, Marullo, Simone, Betti, Alessandro, Tiezzi, Matteo, Gori, Marco, Melacci, Stefano
In this paper, we present PARTIME, a software library written in Python and based on PyTorch, designed specifically to speed up neural networks whenever data is continuously streamed over time, for both learning and inference. Existing libraries are
Externí odkaz:
http://arxiv.org/abs/2210.09147
Autor:
Tiezzi, Matteo, Marullo, Simone, Faggi, Lapo, Meloni, Enrico, Betti, Alessandro, Melacci, Stefano
Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented from leveragi
Externí odkaz:
http://arxiv.org/abs/2204.12193
Autor:
Meloni, Enrico, Betti, Alessandro, Faggi, Lapo, Marullo, Simone, Tiezzi, Matteo, Melacci, Stefano
Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. Trying to simulate this learning process in machines is a challenging task, also due to the inherent difficulty in creating condit
Externí odkaz:
http://arxiv.org/abs/2109.07855
We study the influence of angular momentum on quantum complexity for CFT states holographically dual to rotating black holes. Using the holographic complexity=action (CA) and complexity=volume (CV) proposals, we study the full time dependence of comp
Externí odkaz:
http://arxiv.org/abs/2108.09281
Publikováno v:
Neurocomputing, Elsevier, 2023
Fast reactions to changes in the surrounding visual environment require efficient attention mechanisms to reallocate computational resources to most relevant locations in the visual field. While current computational models keep improving their predi
Externí odkaz:
http://arxiv.org/abs/2006.11035
Publikováno v:
In Neurocomputing 1 December 2023 560
Autor:
Marullo, Simone, Tiezzi, Matteo, Betti, Alessandro, Faggi, Lapo, Meloni, Enrico, Melacci, Stefano
Publikováno v:
CoLLAs 2022-Conference on Lifelong Learning Agents
CoLLAs 2022-Conference on Lifelong Learning Agents, Aug 2022, Montreal, Canada
CoLLAs 2022-Conference on Lifelong Learning Agents, Aug 2022, Montreal, Canada
International audience; In the last few years there has been a growing interest in approaches that allow neural networks to learn how to predict optical flow, both in a supervised and, more recently, unsupervised manner. While this clearly opens up t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______165::d26eabd70ca475703af2634d837b9d1b
https://hal.science/hal-03881291/document
https://hal.science/hal-03881291/document
Autor:
Betti, Alessandro, Faggi, Lapo, Gori, Marco, Tiezzi, Matteo, Marullo, Simone, Meloni, Enrico, Melacci, Stefano
Publikováno v:
Proceedings of Machine Learning Research
CoLLAs 2022-Conference on Lifelong Learning Agents
CoLLAs 2022-Conference on Lifelong Learning Agents, Aug 2022, Montreal, Canada
CoLLAs 2022-Conference on Lifelong Learning Agents
CoLLAs 2022-Conference on Lifelong Learning Agents, Aug 2022, Montreal, Canada
International audience; Learning in a continual manner is one of the main challenges that the machine learning community is currently facing. The importance of the problem can be readily understood as soon as we consider settings where an agent is su
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______165::c575ff1e78a629df59633fde10e7a429
https://hal.science/hal-03881404/document
https://hal.science/hal-03881404/document