Zobrazeno 1 - 10
of 1 174
pro vyhledávání: '"Rodríguez, Natalia"'
In this work, we investigate the means of using curiosity on replay buffers to improve offline multi-task continual reinforcement learning when tasks, which are defined by the non-stationarity in the environment, are non labeled and not evenly expose
Externí odkaz:
http://arxiv.org/abs/2312.03177
Autor:
Díaz-Rodríguez, Natalia, Del Ser, Javier, Coeckelbergh, Mark, de Prado, Marcos López, Herrera-Viedma, Enrique, Herrera, Francisco
Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system's entire life cycle: it should be (1) lawful, (2) ethical, and (3) robust, both from a techni
Externí odkaz:
http://arxiv.org/abs/2305.02231
Publikováno v:
Knowledge-Based Systems 260 (2023) 110189
A quantitative assessment of the global importance of an agent in a team is as valuable as gold for strategists, decision-makers, and sports coaches. Yet, retrieving this information is not trivial since in a cooperative task it is hard to isolate th
Externí odkaz:
http://arxiv.org/abs/2212.03041
Although Deep Neural Networks (DNNs) have great generalization and prediction capabilities, their functioning does not allow a detailed explanation of their behavior. Opaque deep learning models are increasingly used to make important predictions in
Externí odkaz:
http://arxiv.org/abs/2209.14974
Rendering programs have changed the design process completely as they permit to see how the products will look before they are fabricated. However, the rendering process is complicated and takes a significant amount of time, not only in the rendering
Externí odkaz:
http://arxiv.org/abs/2207.08989
Autor:
Del Ser, Javier, Barredo-Arrieta, Alejandro, Díaz-Rodríguez, Natalia, Herrera, Francisco, Holzinger, Andreas
There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on the transparency of decisions in human-critical applications. Besides
Externí odkaz:
http://arxiv.org/abs/2205.10232
Scene graph generation from images is a task of great interest to applications such as robotics, because graphs are the main way to represent knowledge about the world and regulate human-robot interactions in tasks such as Visual Question Answering (
Externí odkaz:
http://arxiv.org/abs/2202.10201
Autor:
Bennetot, Adrien, Donadello, Ivan, Qadi, Ayoub El, Dragoni, Mauro, Frossard, Thomas, Wagner, Benedikt, Saranti, Anna, Tulli, Silvia, Trocan, Maria, Chatila, Raja, Holzinger, Andreas, Garcez, Artur d'Avila, Díaz-Rodríguez, Natalia
Last years have been characterized by an upsurge of opaque automatic decision support systems, such as Deep Neural Networks (DNNs). Although they have great generalization and prediction skills, their functioning does not allow obtaining detailed exp
Externí odkaz:
http://arxiv.org/abs/2111.14260
Autor:
El-Ayadi, Moatasem, Druivenga, Kyra, Perwein, Thomas, Nussbaumer, Gunther, Spreafico, Filippo, Massimino, Maura, Fadel, Shady, Amayiri, Nisreen, Khoubila, Nisrine, Hessissen, Laila, Chamdine, Omar, Rodríguez, Natàlia, Valls, Gemma Calaf, Morales la Madrid, Andres, Dahl, Christine, Hargrave, Darren, Szychot, Elwira, Bailey, Simon, van Vuurden, Dannis G., Benesch, Martin, Hunger, Ina, Kühnle, Ingrid, Mascher, Simone, Maggio, Albane Bertha Rosa, von Bueren, André O., Kramm, Christof M.
Publikováno v:
In EJC Paediatric Oncology June 2024 3