Zobrazeno 1 - 10
of 84
pro vyhledávání: '"Antonelo, Eric A."'
Autor:
Toledo, Rafael S., Oliveira, Cristiano S., Oliveira, Vitor H. T., Antonelo, Eric A., von Wangenheim, Aldo
Autonomous driving needs good roads, but 85% of Brazilian roads have damages that deep learning models may not regard as most semantic segmentation datasets for autonomous driving are high-resolution images of well-maintained urban roads. A represent
Externí odkaz:
http://arxiv.org/abs/2411.16295
Neural networks, while powerful, often lack interpretability. Physics-Informed Neural Networks (PINNs) address this limitation by incorporating physics laws into the loss function, making them applicable to solving Ordinary Differential Equations (OD
Externí odkaz:
http://arxiv.org/abs/2403.02289
Deriving robust control policies for realistic urban navigation scenarios is not a trivial task. In an end-to-end approach, these policies must map high-dimensional images from the vehicle's cameras to low-level actions such as steering and throttle.
Externí odkaz:
http://arxiv.org/abs/2302.04823
Neural networks achieved high performance over different tasks, i.e. image identification, voice recognition and other applications. Despite their success, these models are still vulnerable regarding small perturbations, which can be used to craft th
Externí odkaz:
http://arxiv.org/abs/2301.12001
Echo State Networks (ESN) are a type of Recurrent Neural Network that yields promising results in representing time series and nonlinear dynamic systems. Although they are equipped with a very efficient training procedure, Reservoir Computing strateg
Externí odkaz:
http://arxiv.org/abs/2211.17179
Autor:
Toledo, Rafael S., Antonelo, Eric A.
Variational AutoEncoders (VAE) employ deep learning models to learn a continuous latent z-space that is subjacent to a high-dimensional observed dataset. With that, many tasks are made possible, including face reconstruction and face synthesis. In th
Externí odkaz:
http://arxiv.org/abs/2112.02139
Reinforcement learning methods for continuous control tasks have evolved in recent years generating a family of policy gradient methods that rely primarily on a Gaussian distribution for modeling a stochastic policy. However, the Gaussian distributio
Externí odkaz:
http://arxiv.org/abs/2111.02202
Publikováno v:
2021 IEEE Symposium Series on Computational Intelligence (SSCI)
Autonomous driving is a complex task, which has been tackled since the first self-driving car ALVINN in 1989, with a supervised learning approach, or behavioral cloning (BC). In BC, a neural network is trained with state-action pairs that constitute
Externí odkaz:
http://arxiv.org/abs/2110.08586
Autor:
Antonelo, Eric Aislan, Camponogara, Eduardo, Seman, Laio Oriel, Jordanou, Jean Panaioti, de Souza, Eduardo Rehbein, Hübner, Jomi Fred
Publikováno v:
In Neurocomputing 28 April 2024 579
Autor:
Antonelo, Eric Aislan, Camponogara, Eduardo, Seman, Laio Oriel, de Souza, Eduardo Rehbein, Jordanou, Jean P., Hubner, Jomi F.
Physics-informed neural networks (PINNs) impose known physical laws into the learning of deep neural networks, making sure they respect the physics of the process while decreasing the demand of labeled data. For systems represented by Ordinary Differ
Externí odkaz:
http://arxiv.org/abs/2104.02556