Zobrazeno 1 - 10
of 123
pro vyhledávání: '"Mattar, Marcelo G"'
Understanding connections between artificial and biological intelligent systems can reveal fundamental principles of general intelligence. While many artificial intelligence models have a neuroscience counterpart, such connections are largely missing
Externí odkaz:
http://arxiv.org/abs/2405.14992
Replay is a powerful strategy to promote learning in artificial intelligence and the brain. However, the conditions to generate it and its functional advantages have not been fully recognized. In this study, we develop a modular reinforcement learnin
Externí odkaz:
http://arxiv.org/abs/2402.01467
While advances in artificial intelligence and neuroscience have enabled the emergence of neural networks capable of learning a wide variety of tasks, our understanding of the temporal dynamics of these networks remains limited. Here, we study the tem
Externí odkaz:
http://arxiv.org/abs/2311.05862
Autor:
Bailey, Duncan, Mattar, Marcelo G.
Any reinforcement learning system must be able to identify which past events contributed to observed outcomes, a problem known as credit assignment. A common solution to this problem is to use an eligibility trace to assign credit to recency-weighted
Externí odkaz:
http://arxiv.org/abs/2206.00303
Autor:
Yuan, Yizhi, Mattar, Marcelo G
Prioritized experience replay is a reinforcement learning technique whereby agents speed up learning by replaying useful past experiences. This usefulness is quantified as the expected gain from replaying the experience, a quantity often approximated
Externí odkaz:
http://arxiv.org/abs/2111.14331
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Bertolero, Maxwell A, Adebimpe, Azeez, Khambhati, Ankit N., Mattar, Marcelo G., Romer, Daniel, Thompson-Schill, Sharon L., Bassett, Danielle S.
Human learning is a complex process in which future behavior is altered via the reorganization of brain activity and connectivity. It remains unknown whether activity and connectivity differentially reorganize during learning, and, if so, how that di
Externí odkaz:
http://arxiv.org/abs/1810.08840
Autor:
Duma, Gian Marco, Danieli, Alberto, Mattar, Marcelo G., Baggio, Martina, Vettorel, Airis, Bonanni, Paolo, Mento, Giovanni
Publikováno v:
In Cortex December 2022 157:1-13
Autor:
Tang, Evelyn, Mattar, Marcelo G., Giusti, Chad, Thompson-Schill, Sharon L., Bassett, Danielle S.
Publikováno v:
Nature Neuroscience 22, 1000-1009 (2019)
A fundamental cognitive process is the ability to map value and identity onto objects as we learn about them. Exactly how such mental constructs emerge and what kind of space best embeds this mapping remains incompletely understood. Here we develop t
Externí odkaz:
http://arxiv.org/abs/1709.10045