← Search

Moustapha M Cisse

2 accepted papers

2017

Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples

NeurIPS 2017poster

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 are not designed to alter the true performance measure of the problem at hand. We introduce a novel flexible approach na…

Cited by 226SourcePDFScholar
2017

Unbounded cache model for online language modeling with open vocabulary

NeurIPS 2017poster

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. These models only capture the local context, of up to a few thousands tokens. In this paper, we propose an extension of con…