Embedded Machine Learning in Musical Instrument Design, by Chris Kiefer

Seminar at the MTG (UPF) - December 5th 2024
Embedded Machine Learning in Musical Instrument Design
Chris Kiefer, University of Sussex

Abstract:
The 'Musically Embodied Machine Learning' project is currently running at University of Sussex, exploring the challenges and creative opportunities that arise when the processes of training and inference in machine learning are embedded within hybrid musical instruments. It attempts to resolve dissonant approaches that occur when creative machine learning is divided between musical instruments and data science environments, exploring design strategies for integrating ML processes into physical instruments. The talk will describe motivations behind the project, demonstrate some prototype instruments, and present results from a recent workshop.