Zobrazeno 1 - 10
of 691
pro vyhledávání: '"Alexandre, Luís A."'
The $k$-nearest neighbor ($k$-NN) algorithm is one of the most popular methods for nonparametric classification. However, a relevant limitation concerns the definition of the number of neighbors $k$. This parameter exerts a direct impact on several p
Externí odkaz:
http://arxiv.org/abs/2409.05084
Autor:
Correia, André, Alexandre, Luís A.
Recent advancements in imitation learning have been largely fueled by the integration of sequence models, which provide a structured flow of information to effectively mimic task behaviours. Currently, Decision Transformer (DT) and subsequently, the
Externí odkaz:
http://arxiv.org/abs/2405.07943
Autor:
Correia, André, Alexandre, Luís A.
Synthesising appropriate choreographies from music remains an open problem. We introduce MDLT, a novel approach that frames the choreography generation problem as a translation task. Our method leverages an existing data set to learn to translate seq
Externí odkaz:
http://arxiv.org/abs/2403.15569
Energy consumption is a fundamental concern in mobile application development, bearing substantial significance for both developers and end-users. Main objective of this research is to propose a novel neural network-based framework, enhanced by a met
Externí odkaz:
http://arxiv.org/abs/2309.12484
Energy consumption plays a vital role in mobile App development for developers and end-users, and it is considered one of the most crucial factors for purchasing a smartphone. In addition, in terms of sustainability, it is essential to find methods t
Externí odkaz:
http://arxiv.org/abs/2306.09931
Autor:
Correia, André, Alexandre, Luís
Deploying reinforcement learning agents in the real world can be challenging due to the risks associated with learning through trial and error. We propose a task-agnostic method that leverages small sets of safe and unsafe demonstrations to improve t
Externí odkaz:
http://arxiv.org/abs/2305.04727
Neural Architecture Search (NAS) benchmarks significantly improved the capability of developing and comparing NAS methods while at the same time drastically reduced the computational overhead by providing meta-information about thousands of trained n
Externí odkaz:
http://arxiv.org/abs/2303.16938
Cloud Robotics is helping to create a new generation of robots that leverage the nearly unlimited resources of large data centers (i.e., the cloud), overcoming the limitations imposed by on-board resources. Different processing power, capabilities, r
Externí odkaz:
http://arxiv.org/abs/2303.12876
Autor:
Correia, André, Alexandre, Luís A.
With the fast improvement of machine learning, reinforcement learning (RL) has been used to automate human tasks in different areas. However, training such agents is difficult and restricted to expert users. Moreover, it is mostly limited to simulati
Externí odkaz:
http://arxiv.org/abs/2303.11191