Quelle transparence pour les algorithmes d'apprentissage machine ?

Abstract : Recently, the concept of "transparency of algorithms" has become of primary importance in the public and scientific debates. In the light of the proliferation of uses of the term "transparency", we distinguish two families of fundamental uses of the concept: a descriptive family relating to intrinsic epistemic properties of programs, the first of which are intelligibility and explicability, and a prescriptive family that concerns the normative properties of their uses, the first of which are loyalty and fairness. Because one needs to understand an algorithm in order to explain it and carry out its audit, intelligibility is logically first in the philosophical study of transparency. In order to better determine the challenges of intelligibility in the public use of algorithms, we introduce a distinction between the intelligibility of the procedure and the intelligibility of outputs. Finally, we apply this distinction to the case of machine learning.
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/hal-01791021
Contributor : Issam Ibnouhsein <>
Submitted on : Monday, May 14, 2018 - 11:48:20 AM
Last modification on : Wednesday, July 4, 2018 - 1:12:49 AM
Long-term archiving on : Tuesday, September 25, 2018 - 11:22:38 AM

File

transparence_AM_pegny_ibnouhse...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01791021, version 1

Citation

Maël Pégny, Mohamed Issam Ibnouhsein. Quelle transparence pour les algorithmes d'apprentissage machine ?. 2018. ⟨hal-01791021⟩

Share

Metrics

Record views

665

Files downloads

1158