My doctoral project revolves around explanations for predictions from AI models in linguistic interaction between human and computer. For example, a certain computer model may predict how a patient will feel one year after back surgery. My project concerns what kind of explanations people want for predictions of this kind, what kind of explanations that can actually be obtained from AI models, how explanations are managed in similar kinds of dialogues between humans, and how explanatory dialogue can be modelled and implemented.
Outstanding Student
EvoStar
Recognised for the following paper: Berman, A. and James, V. "Learning as Performance: Autoencoding and Generating Dance Movements in Real Time." International Conference on Computational Intelligence in Music, Sound, Art and Design. Springer, Cham.