Zobrazeno 1 - 10
of 27 920
pro vyhledávání: '"P. A. Antunes"'
Autor:
Nunes, Davide, Antunes, Luis
One goal of Artificial Intelligence is to learn meaningful representations for natural language expressions, but what this entails is not always clear. A variety of new linguistic behaviours present themselves embodied as computers, enhanced humans,
Externí odkaz:
http://arxiv.org/abs/2412.07975
We report the crystal structures, magnetic and thermodynamic properties of two magnetically frustrated $A$'$A$"$M_2$F$_7$-type antiferromagnets, NaCdNi$_2$F$_7$ and NaCdMn$_2$F$_7$. While NaCdNi$_2$F$_7$ forms a stable pyrochlore structure (SG: $Fd \
Externí odkaz:
http://arxiv.org/abs/2411.11579
Communication primitives play a central role in modern computing. They offer a panel of reliability and ordering guarantees for messages, enabling the implementation of complex distributed interactions. In particular, atomic broadcast is a pivotal ab
Externí odkaz:
http://arxiv.org/abs/2410.01901
Autor:
Soares, Filipe, Antunes, José, Vergez, Christophe, Debut, Vincent, Cochelin, Bruno, Silva, Fabrice
A cantilever beam under axial flow, confined or not, is known to develop self-sustained oscillations at sufficiently large flow velocities. In recent decades, the analysis of this archetypal system has been mostly pursued under linearized conditions,
Externí odkaz:
http://arxiv.org/abs/2410.08213
Reinforcement learning (RL) has seen significant research and application results but often requires large amounts of training data. This paper proposes two data-efficient off-policy RL methods that use parametrized Q-learning. In these methods, the
Externí odkaz:
http://arxiv.org/abs/2409.11986
The Covid-19 pandemic has affected the world at multiple levels. Data sharing was pivotal for advancing research to understand the underlying causes and implement effective containment strategies. In response, many countries have promoted the availab
Externí odkaz:
http://arxiv.org/abs/2408.17378
Autor:
Novello, Mario, Antunes, Vicente
We present solutions corresponding to rotational configurations in the recently proposed Geometric Scalar Gravity (GSG) theory. The solutions obtained here have the important property that the associated closed time-like curves are always restricted
Externí odkaz:
http://arxiv.org/abs/2407.09663
Sharing private data for learning tasks is pivotal for transparent and secure machine learning applications. Many privacy-preserving techniques have been proposed for this task aiming to transform the data while ensuring the privacy of individuals. S
Externí odkaz:
http://arxiv.org/abs/2406.16456
Adversarial examples, designed to trick Artificial Neural Networks (ANNs) into producing wrong outputs, highlight vulnerabilities in these models. Exploring these weaknesses is crucial for developing defenses, and so, we propose a method to assess th
Externí odkaz:
http://arxiv.org/abs/2406.14073
Multiple synthetic data generation models have emerged, among which deep learning models have become the vanguard due to their ability to capture the underlying characteristics of the original data. However, the resemblance of the synthetic to the or
Externí odkaz:
http://arxiv.org/abs/2406.02736