Skip to Main content Skip to Navigation
Conference papers

A testing approach for dependable Machine Learning systems

Abstract : In order to be used into a critical system, a software or an hardware component must come with strong evidences that the designer's intents have been correctly captured and implemented. This activity is already complex and expensive for classical systems despite a very large corpus of verification methods and tools. But it is even more complicated for systems embedding Machine Learning (ML) algorithms due to the very nature of the functions being implemented using ML and the very nature of the ML algorithms. This paper focuses on one specific verification technique, testing, for which we propose a four-pronged approach combining performance testing, robustness testing, worst-case testing, and bias testing.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03694805
Contributor : Camille Chapdelaine Connect in order to contact the contributor
Submitted on : Tuesday, June 14, 2022 - 10:01:56 AM
Last modification on : Saturday, June 18, 2022 - 4:11:45 AM

File

Test ML - ERTS - paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03694805, version 1

Collections

Citation

Cyril Cappi, Camille Chapdelaine, Laurent Gardes, Eric Jenn, Baptiste Lefevre, et al.. A testing approach for dependable Machine Learning systems. 11th European Congress on Embedded Real Time Systems (ERTS), Jun 2022, Toulouse, France. ⟨hal-03694805⟩

Share

Metrics

Record views

7

Files downloads

23