PhD defence: Handling non-standard cases in computing - from user and model perspectives

to

PLEASE NOTE: The candidate gives a layman's talk, therefore the livestream will start fifteen minutes earlier.

Technology surrounds us; yet, systems often fail when facing unexpected situations. The core idea is that well-functioning systems work in cycles, taking in information, responding, and adjusting their behavior based on the feedback they receive. However, when they meet situations they were not designed for, this cycle can break down. I studied this problem from two complementary perspectives: the user’s and the model’s.

From the user's perspective, I focused on people whose abilities differ from what systems commonly expect. Through user studies, I showed that offering multiple ways to interact makes technology equally accessible regardless of a person's abilities.  Then, I built a framework that lets systems automatically detect those abilities and adapt on their own, shifting the burden of adapting away from users. This framework was validated in the context of visual impairments. I also co-designed a tool for people who stutter. Here, technology did not only adapt to users; but, actively supported them.

From the model's perspective, I examined how AI struggles when the data it encounters does not match the data it was trained with. I introduced a measure to accurately quantify such data imbalance and its impact on performance. I also analysed why AI fails to generalise, identifying weaknesses and proposing concrete improvements.

Together, these contributions offer practical steps toward robust, inclusive AI that works for the full diversity of people and conditions, not just for the majority.

Start date and time
End date and time
Location
Hybride: online (livestream link) and for invited guests in the Utrecht University Hall, Domplein 29
PhD candidate
J.R. Pivin-Bachler
Dissertation
Handling non-standard cases in computing - from user and model perspectives
PhD supervisor(s)
prof. dr. E.L. van den Van den Broek
Co-supervisor(s)
dr. R. Gomez
More information
Full text via Utrecht University Repository