Print Email Facebook Twitter Safety through Machine Learning Applications Title Safety through Machine Learning Applications: A Safety Case Analysis Author Jacobs, Freek (TU Delft Technology, Policy and Management) Contributor Verbraeck, Alexander (mentor) Cunningham, Scott (mentor) van Gelder, Pieter (mentor) Degree granting institution Delft University of Technology Date 2018-10-26 Abstract Machine learning applications are increasingly being implemented in socio-technical safety-critical systems, but the safety of these applications is not well understood. This thesis used a mixed-method design and applied four methods to explore the field of machine learning and safety. With the results of these four methods, a framework was constructed for the risk analysis of machine learning applications. All findings were synthesised in two ways: by drawing conclusions about machine learning capabilities, and by drawing conclusions about organisational capabilities. This approach provided a way to think conceptually about how far we can take machine learning to increase safety in socio-technical safety-critical systems. Subject Machine LearningSafetyRiskUncertaintysafety assessment To reference this document use: http://resolver.tudelft.nl/uuid:ce5c73ef-8ad0-426f-926e-7d7ef3e197c3 Part of collection Student theses Document type master thesis Rights © 2018 Freek Jacobs Files PDF Freek_Jacobs_Thesis.pdf 4.36 MB Close viewer /islandora/object/uuid:ce5c73ef-8ad0-426f-926e-7d7ef3e197c3/datastream/OBJ/view