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 metadatas

Cited literature [7 references]  Display  Hide  Download

https://hal.inria.fr/hal-01665938
Contributor : Cecile Germain <>
Submitted on : Sunday, December 17, 2017 - 6:17:10 PM
Last modification on : Tuesday, December 10, 2019 - 4:20:04 PM

File

JDSEtemplate.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01665938, version 1

Citation

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⟩

Share

Metrics

Record views

426

Files downloads

341