Research papers · 2019
Safely Entering the Deep: A Review of Verification and Validation for Machine Learning and a Challenge Elicitation in the Automotive Industry
Safely Entering the Deep: A Review of Verification and Validation for Machine Learning and a Challenge Elicitation in the Automotive Industry
Overview
The review combines ML verification and validation literature with Swedish automotive perception workshops. It discusses challenges applying the contemporary ISO 26262 process and recommends system-level approaches including safety cages and simulated tests.
Author-supplied source information
Author-supplied information on arXiv.
Preprint of paper accepted for publication in Journal of Automotive Software Engineering: https://www.atlantis-press.com/journals/jase
Version: arXiv v1 — manuscript revision