Abstract
The expressive power of movement is evident in our everyday lives. Previous research has shown how simple movement patterns, such as gait and arm movements, could be used to identify our internal states— and the expressive nature of movement is perhaps most clear in dance. As virtual agents and robots continue to become part of our daily lives, the need for them to efficiently convey emotion and intent increases.
In her talk, Wallace will give an overview of her work using deep learning to generate dance, the challenges that arise when giving the AI a physical body, and her findings on how humans respond to the weird, and sometimes wonderful, movements generated by AI.
Bio
Benedikte Wallace is a postdoctoral researcher at the RITMO Centre for Interdisciplinary Studies of Rhythm, Time, and Motion and the Department of Informatics at the University of Oslo. With a background in music production and a PhD in Informatics, her academic interests lie in the cross-section between art and science. Her work explores human-AI interaction through generative machine learning and the use of AI as a tool for pursuing and understanding creativity.