KEYWORDS: Artificial intelligence, Machine learning, Safety, Modeling, Systems modeling, Control systems, Telecommunications, Unmanned aerial vehicles, Sensors, Education and training
As machine learning (ML) models are integrated more and more into critical systems, questions regarding their ethical use intensify. This paper advocates for a loss-driven engineering approach, incorporating concepts from systems-theoretic process analysis (STPA), to identify external systems, technologies, and processes essential for ethical ML deployment and therefore crticial to assessing AI ethics. STPA facilitates a deep analysis of potential hazards and system-level vulnerabilities, generating actionable insights for designing support systems and safeguards. Resilience engineering principles can be utilized to convert these insights into testable requirements for assessing AI ethics. This innovative, multi-disciplinary approach addresses a critical gap in current ML practices by extending ethical evaluation beyond the model, offering a robust framework for the responsible development and deployment of AI technologies.
KEYWORDS: Data modeling, Machine learning, Systems modeling, Performance modeling, Data fusion, Algorithm development, Systems engineering, System integration, Testing and analysis
Multi-domain operations (MDO) are characterized by simultaneous and sequential operations; rapid and continuous integration; and surprise. Machine learning (ML) for MDO is no different. Translated into ML, MDO requires highly assured yet rapid data and model fusion. Assurance demands robustness, reliability, and explain-ability, while speed demands computational efficiency and sample efficiency. Combinatorial interaction testing offers explainable and rigorous techniques to ML for fusing data and models with runtime guarantees. But such methods are underexplored in the literature. Combinatorial coverage has been applied to neuron- and layer-levels of neural networks, but only recently to ML in general. There are also ongoing debates of efficacy in the literature, but these debates are scoped to explainable deep learning. This work presents a framework for using combinatorial coverage for multi-domain operations. We discuss how coverage metrics can incorporate multi-modal meta-data and mission context into fusion processes, how coverage is oriented towards identifying gaps in and between sets of data, and how coverage can identify cases where performance is expected to be difficult. We conclude that combinatorial coverage should be considered a core capability for supporting ML in MDO.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.