Zobrazeno 1 - 10
of 439
pro vyhledávání: '"Pérez, Nieves"'
In recent years, newly developed methods to train spiking neural networks (SNNs) have rendered them as a plausible alternative to Artificial Neural Networks (ANNs) in terms of accuracy, while at the same time being much more energy efficient at infer
Externí odkaz:
http://arxiv.org/abs/2305.08879
Autor:
Adaptive Agent Team, Bauer, Jakob, Baumli, Kate, Baveja, Satinder, Behbahani, Feryal, Bhoopchand, Avishkar, Bradley-Schmieg, Nathalie, Chang, Michael, Clay, Natalie, Collister, Adrian, Dasagi, Vibhavari, Gonzalez, Lucy, Gregor, Karol, Hughes, Edward, Kashem, Sheleem, Loks-Thompson, Maria, Openshaw, Hannah, Parker-Holder, Jack, Pathak, Shreya, Perez-Nieves, Nicolas, Rakicevic, Nemanja, Rocktäschel, Tim, Schroecker, Yannick, Sygnowski, Jakub, Tuyls, Karl, York, Sarah, Zacherl, Alexander, Zhang, Lei
Foundation models have shown impressive adaptation and scalability in supervised and self-supervised learning problems, but so far these successes have not fully translated to reinforcement learning (RL). In this work, we demonstrate that training an
Externí odkaz:
http://arxiv.org/abs/2301.07608
Autor:
Mguni, David Henry, Jafferjee, Taher, Wang, Jianhong, Slumbers, Oliver, Perez-Nieves, Nicolas, Tong, Feifei, Yang, Li, Zhu, Jiangcheng, Yang, Yaodong, Wang, Jun
Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agent systems, coordinated exploration and behaviour is critical for agents to jointly achieve optimal outcomes. In this paper, we introduce a new general
Externí odkaz:
http://arxiv.org/abs/2112.02618
Autor:
Brett McQueen, Robert, Perez-Nieves, Magaly, Todd Alonso, G., Fan, Ludi, Hankosky, Emily R., Shah, Viral N., Yan, Yuer, Ellis, Samuel L., Juneja, Rattan
Publikováno v:
In Diabetes Research and Clinical Practice June 2024 212
Publikováno v:
Advances in Neural Information Processing Systems (NeurIPS, 2021)
There is an increasing interest in emulating Spiking Neural Networks (SNNs) on neuromorphic computing devices due to their low energy consumption. Recent advances have allowed training SNNs to a point where they start to compete with traditional Arti
Externí odkaz:
http://arxiv.org/abs/2105.08810
Autor:
Mguni, David, Jafferjee, Taher, Wang, Jianhong, Perez-Nieves, Nicolas, Yang, Tianpei, Taylor, Matthew, Song, Wenbin, Tong, Feifei, Chen, Hui, Zhu, Jiangcheng, Wang, Jun, Yang, Yaodong
Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engineered shaping-reward functions whose construction is time-consuming a
Externí odkaz:
http://arxiv.org/abs/2103.09159
Autor:
Novo-Veleiro, Ignacio, Mateos-Díaz, Ana-M., Rosón-Hernández, Beatriz, Medina-García, José-A., Muga, Roberto, Fernández-Solá, Joaquim, Martín-González, M.-Candelaria, Seco-Hernández, Elena, Suárez-Cuervo, Carlos, Monte-Secades, Rafael, Machado-Prieto, Begoña, Puerta-Louro, Rubén, Prada-González, Cristina, Fernández-Rial, Álvaro, Sabio-Repiso, Patricia, Vázquez-Vigo, Rocío, Antolí-Royo, Ana-C., Gomila-Grange, Aina, Felipe-Pérez, Nieves-C., Sanvisens-Bergé, Arantza, Antúnez-Jorge, Emilia, Fernández-Rodríguez, Camino-M., Alvela-Suárez, Lucia, Fidalgo-Navarro, Alba, Castro, Joaquín, Polvorosa-Gómez, María-A., Valle-Sánchez, Mario Del, López-Castro, José, Chamorro, Antonio-J., Marcos, Miguel
Publikováno v:
In Drug and Alcohol Dependence 1 November 2023 252
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.