Robust deep learning: A case study - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Documents Associated With Scientific Events Year : 2017

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.
Fichier principal
Vignette du fichier
JDSEtemplate.pdf (318.47 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01665938 , version 1 (17-12-2017)

Identifiers

  • HAL Id : hal-01665938 , version 1

Cite

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⟩
341 View
276 Download

Share

Gmail Facebook X LinkedIn More