Machine Learning (ML) and Artificial Intelligence (AI) are being used more than ever for personal and commercial applications. There is intense interest in using ML and AI in safety critical tasks as well. To address the unique risks of ML and AI in safety critical tasks, recent functional safety standards and technical reports have been published. But how to address ML and AI risks when designing, developing, and validating learning models in safety critical tasks remains an open problem. In this talk, we will go over three challenges for deploying ML or AI in safety critical tasks and discuss techniques to address these challenges.
exida Recorded Webinars
Bridging the Gap between AI Standards and Safe AI
Recording Date: February 2025
About the Presenter:
Dr. Molly O’Brien
Dr. O’Brien is a Senior Safety Engineer who performs System FMEAs, Electrical FMEAs, and Electrical FMEDAs for exida Certification. She also performs Hardware and Software certification assessments. Molly is part of a team of experts at exida who are developing a certification scheme for Safety Functions that include Machine Learning. Molly defended her Ph.D. in Computer Science at Johns Hopkins University, and her doctoral thesis focuses on predicting Neural Network performance in novel operating domains. She has research experience in perception, robotics, and medical imaging. Molly received a Bachelor of Science in Electrical Engineering and a Bachelor of Science in French and Francophone Studies from Pennsylvania State University.