no code implementations • 4 Dec 2023 • Taha Yassine, Baptiste Chatelier, Vincent Corlay, Matthieu Crussière, Stephane Paquelet, Olav Tirkkonen, Luc Le Magoarou
In non-standalone or cell-free systems, chart locations computed at a given base station can be transmitted to several other base stations (possibly operating at different frequency bands) for them to predict which beams to use.
no code implementations • 28 Aug 2023 • Baptiste Chatelier, Luc Le Magoarou, Vincent Corlay, Matthieu Crussière
In order to overcome this limitation, this paper presents a frugal, model-based network that separates the low frequency from the high frequency components of the target mapping function.
no code implementations • 28 Feb 2023 • Vincent Corlay, Jean-Christophe Sibel
Standard Markov decision process (MDP) and reinforcement learning algorithms optimize the policy with respect to the expected gain.
no code implementations • 13 Dec 2020 • Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, Loïc Brunel
It is exponential in the space dimension $n$, which induces shallow neural networks of exponential size.
no code implementations • 28 Feb 2019 • Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, Loic Brunel
We prove that they can be computed by ReLU networks with quadratic depth and linear width in the space dimension.
no code implementations • 6 Feb 2019 • Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, Loic Brunel
Lattice decoding in Rn, known as the closest vector problem (CVP), becomes a classification problem in the fundamental parallelotope with a piecewise linear function defining the boundary.
no code implementations • 4 Dec 2018 • Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, Loïc Brunel
A quasi-static flat multiple-antenna channel is considered.