Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Perone, Christian S."'
Autor:
Pini, Stefano, Perone, Christian S., Ahuja, Aayush, Ferreira, Ana Sofia Rufino, Niendorf, Moritz, Zagoruyko, Sergey
The goal of autonomous vehicles is to navigate public roads safely and comfortably. To enforce safety, traditional planning approaches rely on handcrafted rules to generate trajectories. Machine learning-based systems, on the other hand, scale with d
Externí odkaz:
http://arxiv.org/abs/2211.02131
Autor:
Kumar, Eesha, Zhang, Yiming, Pini, Stefano, Stent, Simon, Ferreira, Ana, Zagoruyko, Sergey, Perone, Christian S.
The imitation learning of self-driving vehicle policies through behavioral cloning is often carried out in an open-loop fashion, ignoring the effect of actions to future states. Training such policies purely with Empirical Risk Minimization (ERM) can
Externí odkaz:
http://arxiv.org/abs/2210.02174
Uncertainty quantification for deep neural networks has recently evolved through many techniques. In this work, we revisit Laplace approximation, a classical approach for posterior approximation that is computationally attractive. However, instead of
Externí odkaz:
http://arxiv.org/abs/2107.04695
Autor:
Perone, Christian S.
This article contains a series of analyses done for the SARS-CoV-2 outbreak in Rio Grande do Sul (RS) in the south of Brazil. These analyses are focused on the high-incidence cities such as the state capital Porto Alegre and at the state level. We pr
Externí odkaz:
http://arxiv.org/abs/2007.10486
Autor:
AskariHemmat, MohammadHossein, Honari, Sina, Rouhier, Lucas, Perone, Christian S., Cohen-Adad, Julien, Savaria, Yvon, David, Jean-Pierre
Model quantization is leveraged to reduce the memory consumption and the computation time of deep neural networks. This is achieved by representing weights and activations with a lower bit resolution when compared to their high precision floating poi
Externí odkaz:
http://arxiv.org/abs/1908.01073
Semantic segmentation is a crucial task in biomedical image processing, which recent breakthroughs in deep learning have allowed to improve. However, deep learning methods in general are not yet widely used in practice since they require large amount
Externí odkaz:
http://arxiv.org/abs/1907.05143
The cost of wind energy can be reduced by using SCADA data to detect faults in wind turbine components. Normal behavior models are one of the main fault detection approaches, but there is a lack of consensus in how different input features affect the
Externí odkaz:
http://arxiv.org/abs/1906.12329
Recent advances in deep learning methods have come to define the state-of-the-art for many medical imaging applications, surpassing even human judgment in several tasks. Those models, however, when trained to reduce the empirical risk on a single dom
Externí odkaz:
http://arxiv.org/abs/1811.06042
Recently proposed techniques for semi-supervised learning such as Temporal Ensembling and Mean Teacher have achieved state-of-the-art results in many important classification benchmarks. In this work, we expand the Mean Teacher approach to segmentati
Externí odkaz:
http://arxiv.org/abs/1807.04657
Despite the fast developmental pace of new sentence embedding methods, it is still challenging to find comprehensive evaluations of these different techniques. In the past years, we saw significant improvements in the field of sentence embeddings and
Externí odkaz:
http://arxiv.org/abs/1806.06259