no code implementations • 1 May 2019 • Myriam Bontonou, Carlos Lassance, Jean-Charles Vialatte, Vincent Gripon
Convolutional Neural Networks are very efficient at processing signals defined on a discrete Euclidean space (such as images).
1 code implementation • 27 Feb 2018 • Carlos Eduardo Rosar Kos Lassance, Jean-Charles Vialatte, Vincent Gripon
We propose an extension of Convolutional Neural Networks (CNNs) to graph-structured data, including strided convolutions and data augmentation on graphs.
no code implementations • 27 Oct 2017 • Bastien Pasdeloup, Vincent Gripon, Jean-Charles Vialatte, Dominique Pastor, Pascal Frossard
We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure.
no code implementations • 8 Jun 2017 • Jean-Charles Vialatte, Vincent Gripon, Gilles Coppin
We propose a simple and generic layer formulation that extends the properties of convolutional layers to any domain that can be described by a graph.
no code implementations • 18 Apr 2017 • Jean-Charles Vialatte, François Leduc-Primeau
For many types of integrated circuits, accepting larger failure rates in computations can be used to improve energy efficiency.
no code implementations • 3 Jun 2016 • Jean-Charles Vialatte, Vincent Gripon, Grégoire Mercier
Convolutional Neural Networks (CNNs) have become the state-of-the-art in supervised learning vision tasks.