Applications of AI for Accessibility

Abstract:

Machine learning works well when patterns can be identified, yet this can lead to an obsession with norms and averages. Although common, disability often gets represented as an outlier in large-scale data sets that are used to model human behavior. In this talk, I will discuss why it is important for machine learning models to better incorporate disability and the challenges of doing so. I will focus on two applications of machine learning in my current work – autonomous vehicles for people with vision impairments and voice assistants for older adults.

Bio:

Robin Brewer is an Assistant Professor in the School of Information and Computer Science and Engineering at the University of Michigan. Her research is at the intersection of human-computer interaction, accessibility, and social computing. Robin completed her PhD in a joint Computer Science and Communication Studies program at Northwestern University.