Skip to Main content Skip to Navigation
New interface
Documents associated with scientific events

Robust deep learning: A case study

Abstract : We report on an experiment on robust classification. The literature proposes adversarial and generative learning, as well as feature construction with auto-encoders. In both cases, the context is domain-knowledge-free performance. As a consequence, the robustness quality relies on the representativity of the training dataset wrt the possible perturbations. When domain-specific a priori knowledge is available, as in our case, a specific flavor of DNN called Tangent Propagation is an effective and less data-intensive alternative.
Document type :
Documents associated with scientific events
Complete list of metadata

Cited literature [7 references]  Display  Hide  Download
Contributor : Cecile Germain Connect in order to contact the contributor
Submitted on : Sunday, December 17, 2017 - 6:17:10 PM
Last modification on : Saturday, November 19, 2022 - 3:36:14 AM


Files produced by the author(s)


  • HAL Id : hal-01665938, version 1


Victor Estrade, Cécile Germain, Isabelle Guyon, David Rousseau. Robust deep learning: A case study. JDSE 2017 - 2nd Junior Conference on Data Science and Engineering, Sep 2017, Orsay, France. , pp.1-5, 2017. ⟨hal-01665938⟩



Record views


Files downloads