Abstract: 

Supervised learning can be understood not only as a way to create accurate models of real-world phenomena, but also as a design tool that complements more traditional computer programming by enabling rapid prototyping, iterative refinement, and embodied engagement in the design of new software and hardware systems. Realising the creative potential of these algorithms requires a rethinking of the interfaces through which people provide data and build models, providing for tight interaction-feedback loops and efficient mechanisms for people to steer and explore algorithm behaviours. I will outline some of my research on better enabling creative practitioners, interaction designers, and software developers to employ supervised learning in the design of new real-time systems. I will demo some tools that I have created for this purpose, and I’ll highlight some of the research outcomes from nearly a decade of employing and observing others using machine learning in creative contexts.

About Rebecca

Dr. Rebecca Fiebrink is a Senior Lecturer at Goldsmiths, University of London. Her research focuses on designing new ways for humans to interact with computers in live music performance and other creative practice. She is the developer of the Wekinator software for interactive machine learning, and she recently taught the world’s first MOOC (“Massively open online course”) about machine learning for artists and musicians. She has worked with companies including Microsoft Research, Sun Microsystems Research Labs, Imagine Research, and Smule, where she helped to build the #1 iTunes app “I am T-Pain.” She holds a PhD in Computer Science from Princeton University in 2011. Prior to moving to Goldsmiths, she was an Assistant Professor at Princeton University, where she co-directed the Princeton Laptop Orchestra.