Join IxDA Pittsburgh (virtually) as we talk about AI explainability with Meg Kurdziolek, UX Researcher at Google. “Doors open” at 5:30, and the talk will start at 5:45.

About the Talk

There is a growing problem facing ML-driven product designers and engineers. Products and services increasingly generate and rely on larger, more complex datasets. As datasets grow in breadth and volume, the ML models built on them are increasing in complexity. But as ML model complexity grows, they become increasingly opaque. Without a means of understanding ML model decision making, end-users are less likely to trust and adopt the technology. Furthermore, the audiences for ML model explanations come from varied backgrounds, have different levels of experience with mathematics and statistics, and will rely on these technologies in a variety of contexts. In order to show the “whys” behind complex machine learning decision making, technologists will need to employ “Explainable AI.” In this literature review, I sketch out “the basics” of Explainable AI (XAI) and describe, at a high level, popular methods and techniques. Then I describe the current challenges facing the field, and how UX can advocate for better experiences in ML driven products.

About Meg

Meg is currently a UX Researcher for Google Cloud AI and Industry Solutions, where she focuses her research on Explainable AI and Model Understanding. She has had a varied career working for start-ups and large corporations alike, in fields as varied as EdTech, weather forecasting, and commercial robotics. She has published articles on topics such as user research, information visualization, educational-technology design, human-robot interaction (HRI), and voice user interface (VUI) design. Meg is also a proud alumnus of Virginia Tech, where she received her Ph.D. in HCI, and would have become a professional student if that were a legitimate career choice.You can find Meg on Twitter at @megak.