Zobrazeno 1 - 10
of 36 155
pro vyhledávání: '"A, Steinmetz"'
Autor:
Kich, Victor Augusto, Bottega, Jair Augusto, Steinmetz, Raul, Grando, Ricardo Bedin, Yorozu, Ayano, Ohya, Akihisa
In this work, we present Curled-Dreamer, a novel reinforcement learning algorithm that integrates contrastive learning into the DreamerV3 framework to enhance performance in visual reinforcement learning tasks. By incorporating the contrastive loss f
Externí odkaz:
http://arxiv.org/abs/2408.05781
Autor:
Kich, Victor Augusto, Bottega, Jair Augusto, Steinmetz, Raul, Grando, Ricardo Bedin, Yorozu, Ayano, Ohya, Akihisa
Kolmogorov-Arnold Networks (KANs) have shown potential as an alternative to Multi-Layer Perceptrons (MLPs) in neural networks, providing universal function approximation with fewer parameters and reduced memory usage. In this paper, we explore the us
Externí odkaz:
http://arxiv.org/abs/2408.04841
Autor:
Vanka, Soumya Sai, Steinmetz, Christian, Rolland, Jean-Baptiste, Reiss, Joshua, Fazekas, George
Mixing style transfer automates the generation of a multitrack mix for a given set of tracks by inferring production attributes from a reference song. However, existing systems for mixing style transfer are limited in that they often operate only on
Externí odkaz:
http://arxiv.org/abs/2407.08889
Autor:
Khalatyan, A., Anders, F., Chiappini, C., Queiroz, A. B. A., Nepal, S., Ponte, M. dal, Jordi, C., Guiglion, G., Valentini, M., Elipe, G. Torralba, Steinmetz, M., Pantaleoni-González, M., Malhotra, S., Jiménez-Arranz, Ó., Enke, H., Casamiquela, L., Ardèvol, J.
We explore the feasibility of using machine-learning regression as a method of extracting basic stellar parameters and line-of-sight extinctions, given spectro-photometric data. To this end, we build a stable gradient-boosted random-forest regressor
Externí odkaz:
http://arxiv.org/abs/2407.06963
Autor:
Richard, Johan, Giroud, Rémi, Laurent, Florence, Krajnović, Davor, Jeanneau, Alexandre, Bacon, Roland, Abreu, Manuel, Adamo, Angela, Araujo, Ricardo, Bouché, Nicolas, Brinchmann, Jarle, Cai, Zhemin, Castro, Norberto, Calcines, Ariadna, Chapuis, Diane, Claeyssens, Adélaïde, Cortese, Luca, Daddi, Emanuele, Davison, Christopher, Goodwin, Michael, Harris, Robert, Hayes, Matthew, Jauzac, Mathilde, Kelz, Andreas, Kneib, Jean-Paul, Lanotte, Audrey A., Lawrence, Jon, Bouteiller, Vianney Le, Breton, Rémy Le, Lehnert, Matthew, Sanchez, Angel Lopez, McGregor, Helen, McLeod, Anna F., Monteiro, Manuel, Morris, Simon, Opitom, Cyrielle, Pécontal, Arlette, Robertson, David, Roth, Martin M., van de Sande, Jesse, Smith, Russell, Steinmetz, Matthias, Swinbank, Mark, Urrutia, Tanya, Verhamme, Anne, Weilbacher, Peter M., Wendt, Martin, Wildi, François, Zheng, Jessica, consortium, The BlueMUSE
BlueMUSE is a blue-optimised, medium spectral resolution, panoramic integral field spectrograph under development for the Very Large Telescope (VLT). With an optimised transmission down to 350 nm, spectral resolution of R$\sim$3500 on average across
Externí odkaz:
http://arxiv.org/abs/2406.13914
Autor:
Jung, Alexander Louis-Ferdinand, Steinmetz, Jannik, Gietz, Jonathan, Lübeck, Konstantin, Bringmann, Oliver
Statistical models are widely used to estimate the performance of commercial off-the-shelf (COTS) AI hardware accelerators. However, training of statistical performance models often requires vast amounts of data, leading to a significant time investm
Externí odkaz:
http://arxiv.org/abs/2406.08330
Autor:
Grando, Ricardo B., Steinmetz, Raul, Kich, Victor A., Kolling, Alisson H., Furik, Pablo M., de Jesus, Junior C., Guterres, Bruna V., Gamarra, Daniel T., Guerra, Rodrigo S., Drews-Jr, Paulo L. J.
Deep Reinforcement Learning (DRL) has emerged as a promising approach to enhancing motion control and decision-making through a wide range of robotic applications. While prior research has demonstrated the efficacy of DRL algorithms in facilitating a
Externí odkaz:
http://arxiv.org/abs/2406.01952
Autor:
Steinmetz, Raul, Kich, Victor A., Krever, Henrique, Mazzarolo, Joao D. Rigo, Grando, Ricardo B., Marini, Vinicius, Trois, Celio, Nieuwenhuizen, Ard
Deep learning, particularly Convolutional Neural Networks (CNNs), has gained significant attention for its effectiveness in computer vision, especially in agricultural tasks. Recent advancements in instance segmentation have improved image classifica
Externí odkaz:
http://arxiv.org/abs/2406.00313
Autor:
Kich, Victor A., Bottega, Jair A., Steinmetz, Raul, Grando, Ricardo B., Yorozu, Ayanori, Ohya, Akihisa
This paper introduces YamaS, a simulator integrating Unity3D Engine with Robotic Operating System for robot navigation research and aims to facilitate the development of both Deep Reinforcement Learning (Deep-RL) and Natural Language Processing (NLP)
Externí odkaz:
http://arxiv.org/abs/2405.16818
Autor:
Bacon, Roland, Maineiri, Vincenzo, Randich, Sofia, Cimatti, Andrea, Kneib, Jean-Paul, Brinchmann, Jarle, Ellis, Richard, Tolstoi, Eline, Smiljanic, Rodolfo, Hill, Vanessa, Anderson, Richard, Saez, Paula Sanchez, Opitom, Cyrielle, Bryson, Ian, Dierickx, Philippe, Garilli, Bianca, Gonzalez, Oscar, de Jong, Roelof, Lee, David, Mieske, Steffen, Otarola, Angel, Schipani, Pietro, Travouillon, Tony, Vernet, Joel, Bryant, Julia, Casali, Marc, Colless, Matthew, Couch, Warrick, Driver, Simon, Fontana, Adriano, Lehnert, Matthew, Magrini, Laura, Montet, Ben, Pasquini, Luca, Roth, Martin, Sanchez-Janssen, Ruben, Steinmetz, Matthias, Tresse, Laurence, Yeche, Christophe, Ziegler, Bodo
In this paper, we describe the wide-field spectroscopic survey telescope (WST) project. WST is a 12-metre wide-field spectroscopic survey telescope with simultaneous operation of a large field-of-view (3 sq. degree), high-multiplex (20,000) multi-obj
Externí odkaz:
http://arxiv.org/abs/2405.12518