Assured Machine Learning: A Theoretically-Grounded Framework for High-Stakes Domains

Explore a theoretically-grounded framework for assured machine learning in high-stakes domains through this 36-minute conference talk by Visar Berisha from Arizona State University's Metacog AI. Delve into the critical aspects of implementing reliable and trustworthy machine learning systems for applications where accuracy and safety are paramount. Gain insights into the latest advancements in the field of assured ML, including methodologies for risk assessment, robustness, and accountability. Learn how these principles can be applied to create more dependable AI systems in sectors such as healthcare, finance, and autonomous vehicles. This talk, part of the November 2023 ARO Metacognitive AI workshop, offers valuable knowledge for researchers, practitioners, and decision-makers working on high-stakes AI applications.