Towards a Framework for Deep Learning Certification in Safety-Critical Applications Using Inherently Safe Design and Run-Time Error Detection

arXiv:2403.14678v1 Announce Type: new
Abstract: Although an ever-growing number of applications employ deep learning based systems for prediction, decision-making, or state estimation, almost no certification processes have been established that would allow such systems to be deployed in safety-critical applications. In this work we consider real-world problems arising in aviation and other safety-critical areas, and investigate their requirements for a certified model. To this end, we investigate methodologies from the machine learning research community aimed towards verifying robustness and reliability …

abstract applications arxiv certification cs.lg decision deep learning design detection error framework making prediction processes safety safety-critical state systems type