Maturation of Determining the Limits of AI Robustness (MDLAR)
Abstract
MDLAR: Military Application: The Department of Defense (DoD): Is increasingly relying on machine learning (ML) systems for a variety of mission and support functions; Requires rapid adaptation to new situations, environments, and threats; Needs confidence that, when deploying ML systems, they will perform accurately; Needs to know when to wait for data to retrain/boost before their continued use. This one-year project focused on: Developing an approach for determining the robustness of artificial intelligence (AI) solutions; Building an application (prototype) to do just that within a narrow domain.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 14, 2022
- Accession Number
- AD1180836
Entities
People
- Michael D. Konrad
Organizations
- Carnegie Mellon University