Search Results for author: Carlos Eduardo Rosar Kos Lassance

Found 3 papers, 1 papers with code

Laplacian Networks: Bounding Indicator Function Smoothness for Neural Network Robustness

no code implementations24 May 2018 Carlos Eduardo Rosar Kos Lassance, Vincent Gripon, Antonio Ortega

For the past few years, Deep Neural Network (DNN) robustness has become a question of paramount importance.

Matching Convolutional Neural Networks without Priors about Data

1 code implementation27 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.

Data Augmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.