4.7k citations · 5.8k across the 13 of their papers we have counts for
7 papers · 1 filter
Unbounded cache model for online language modeling with open vocabulary
Edouard Grave, Moustapha Cisse, Armand Joulin
Recently, continuous cache models were proposed as extensions to recurrent neural network language models, to adapt their predictions to local changes in the data distribution. The…
ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
Pierre Stock, Moustapha Cisse
ConvNets and Imagenet have driven the recent success of deep learning for image classification. However, the marked slowdown in performance improvement combined with the lack of ro…
Countering Adversarial Images using Input Transformations
Chuan Guo, Mayank Rana, Moustapha Cisse +1
This paper investigates strategies that defend against adversarial-example attacks on image-classification systems by transforming the inputs before feeding them to the system. Spe…
mixup: Beyond Empirical Risk Minimization
Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin +1
Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple le…
Houdini: Fooling Deep Structured Prediction Models
Moustapha Cisse, Yossi Adi, Natalia Neverova +1
Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and…
Parseval Networks: Improving Robustness to Adversarial Examples
Moustapha Cisse, Piotr Bojanowski, Edouard Grave +2
We introduce Parseval networks, a form of deep neural networks in which the Lipschitz constant of linear, convolutional and aggregation layers is constrained to be smaller than 1.…
Kronecker Recurrent Units
Cijo Jose, Moustpaha Cisse, Francois Fleuret
Our work addresses two important issues with recurrent neural networks: (1) they are over-parameterized, and (2) the recurrence matrix is ill-conditioned. The former increases the…