M
Moustapha Cisse
Researcher at Facebook
Publications - 22
Citations - 7172
Moustapha Cisse is an academic researcher from Facebook. The author has contributed to research in topics: Artificial neural network & Perplexity. The author has an hindex of 14, co-authored 22 publications receiving 4127 citations. Previous affiliations of Moustapha Cisse include Google & University of Paris.
Papers
More filters
Proceedings Article
mixup: Beyond Empirical Risk Minimization
TL;DR: This work proposes mixup, a simple learning principle that trains a neural network on convex combinations of pairs of examples and their labels, which improves the generalization of state-of-the-art neural network architectures.
Posted Content
mixup: Beyond Empirical Risk Minimization
TL;DR: Mixup as discussed by the authors trains a neural network on convex combinations of pairs of examples and their labels, and regularizes the neural network to favor simple linear behavior in between training examples, which improves the generalization of state-of-the-art neural network architectures.
Proceedings Article
Parseval networks: improving robustness to adversarial examples
TL;DR: Parseval Networks as discussed by the authors is a form of deep neural networks in which the Lipschitz constant of linear, convolutional and aggregation layers is constrained to be smaller than 1.
Posted Content
Houdini: Fooling Deep Structured Prediction Models.
TL;DR: This work introduces a novel flexible approach named Houdini for generating adversarial examples specifically tailored for the final performance measure of the task considered, be it combinatorial and non-decomposable.
Posted Content
Parseval Networks: Improving Robustness to Adversarial Examples
TL;DR: Parseval Networks as discussed by the authors is a form of deep neural networks in which the Lipschitz constant of linear, convolutional and aggregation layers is constrained to be smaller than 1.