Trade-offs in Metric Learning for Bearing Fault Diagnosis

Cody, Tyler; Adams, Stephen; Beling, Peter A.

doi:10.1109/icmla52953.2021.00180

Cited by 1 publication

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Drawing from abstract systems theory 17 and statistical learning theory, 18 abstract learning systems theory (ALST) was recently established as a formal study of general learning systems that is expressly independent of specific solution methods. [19][20][21][22][23][24][25][26][27][28][29] ALST has been applied to systems and test engineering research areas for AIES including test harnesses, [30][31][32][33][34][35] condition-based monitoring, [36][37][38][39] cyber defense, [40][41][42][43][44][45] and cognitive communications. 46,47 In ALST, a learning system S is defined as a relation on sets…”

Section: Abstract Learning Systems Theory (Alst)mentioning

confidence: 99%

On the role of loss-driven systems analysis in assessing AI ethics

Cody,

Freeman,

Beling

2024

Assurance and Security for AI-enabled Systems

View full text Add to dashboard Cite

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.

show abstract