Zobrazeno 1 - 10
of 3 715
pro vyhledávání: '"Oliveira, P. L."'
Most active learning research has focused on methods which perform well when many labels are available, but can be dramatically worse than random selection when label budgets are small. Other methods have focused on the low-budget regime, but do poor
Externí odkaz:
http://arxiv.org/abs/2412.20644
The biological brain has inspired multiple advances in machine learning. However, most state-of-the-art models in computer vision do not operate like the human brain, simply because they are not capable of changing or improving their decisions/output
Externí odkaz:
http://arxiv.org/abs/2412.15734
It is established existence of solution with prescribed $L^p$ norm for the following nonlocal elliptic problem: \begin{equation*} \left\{\begin{array}{cc} \displaystyle (-\Delta)^s_p u\ +\ V (x) |u|^{p-2}u\ = \lambda |u|^{p - 2}u + \beta\left|u\right
Externí odkaz:
http://arxiv.org/abs/2412.14948
Surface roughness plays a crucial role in the accuracy of indentation experiments used to measure the elastic properties of materials. In this study, we present a computational analysis of how surface roughness, represented explicitly by fractal geom
Externí odkaz:
http://arxiv.org/abs/2410.17486
Autor:
de Oliveira, Bryan L. M., da Luz, Murilo L., Brandão, Bruno, Martins, Luana G. B., Soares, Telma W. de L., Melo, Luckeciano C.
Learning effective visual representations is crucial in open-world environments where agents encounter diverse and unstructured observations. This ability enables agents to extract meaningful information from raw sensory inputs, like pixels, which is
Externí odkaz:
http://arxiv.org/abs/2410.14038
Autor:
Riffel, Rogemar A., Souza-Oliveira, Gabriel L., Costa-Souza, José Henrique, Zakamska, Nadia L., Storchi-Bergmann, Thaisa, Riffel, Rogério
We use James Webb Space Telescope (JWST) Mid-Infrared Instrument (MIRI) medium-resolution spectrometer (MRS) observations of 3C 293 (UGC 8782), CGCG 012-070 and NGC 3884 to investigate the origin of the H$_2$ emission. These three nearby Active Galac
Externí odkaz:
http://arxiv.org/abs/2410.06960
While convolutional neural networks (CNNs) excel at clean image classification, they struggle to classify images corrupted with different common corruptions, limiting their real-world applicability. Recent work has shown that incorporating a CNN fron
Externí odkaz:
http://arxiv.org/abs/2409.16838
Autor:
Costa-Souza, J. H., Riffel, Rogemar A., Souza-Oliveira, Gabriel L., Zakamska, Nadia L., Bianchin, Marina, Storchi-Bergmann, Thaisa, Riffel, Rogério
We use the James Webb Space Telescope (JWST) Mid-Infrared Instrument (MIRI) medium-resolution spectrometer (MRS) observations of the radio loud AGN host UGC 8782 to map the warm molecular and ionized gas kinematics. The data reveal spatially resolved
Externí odkaz:
http://arxiv.org/abs/2408.06100
Autor:
Duarte, André V., Marques, João, Graça, Miguel, Freire, Miguel, Li, Lei, Oliveira, Arlindo L.
Modern NLP tasks increasingly rely on dense retrieval methods to access up-to-date and relevant contextual information. We are motivated by the premise that retrieval benefits from segments that can vary in size such that a content's semantic indepen
Externí odkaz:
http://arxiv.org/abs/2406.17526
Despite attaining high empirical generalization, the sharpness of models trained with sharpness-aware minimization (SAM) do not always correlate with generalization error. Instead of viewing SAM as minimizing sharpness to improve generalization, our
Externí odkaz:
http://arxiv.org/abs/2406.06700