Empowering the trustworthiness of ML-based critical systems through engineering activities
It addresses the problem of ensuring trustworthiness in ML for critical systems, but is incremental as it reviews and organizes existing principles.
The paper reviews the engineering process for developing trustworthy machine learning algorithms in critical systems, organizing key components into a unified framework for design.
This paper reviews the entire engineering process of trustworthy Machine Learning (ML) algorithms designed to equip critical systems with advanced analytics and decision functions. We start from the fundamental principles of ML and describe the core elements conditioning its trust, particularly through its design: namely domain specification, data engineering, design of the ML algorithms, their implementation, evaluation and deployment. The latter components are organized in an unique framework for the design of trusted ML systems.