9.27.2025
Research and find a project (experiments, websites, art installations, games, etc) that utilizes machine learning in a creative way. Consider the following:
Sougwen 愫君 Chung is a Chinese-Canadian artist and researcher who explores human–machine collaboration in her works. Her practice spans across mediums such as drawing, performance, sculpture, robotics, and machine learning. Drawing Operations Unit: Generation_2 (MEMORY), which is the work I researched about, is now in the permanent collection of the Victoria and Albert Museum, as the first AI-based artwork acquired by a major cultural institution.
Drawing Operations (2015) is an exploration of human–machine collaboration. In Generation 1: Mimicry, the artist used computer vision systems that allowed a robotic arm (D.O.U.G._1) to mimic her hand-drawn gestures in real time in order to produce synchronized marks on paper. Later in Generation 2: Memory, she expanded this collaboration by introducing machine learning. She trained neural networks on more than twenty years of her own drawing archives. This enabled the model to learn her style and carry that through as a trace of muscle memory when creating the marks. In this way, the robotic arm was no longer just imitating her marks, but rather producing new marks that reflect her style.
The training data was drawn from Chung’s personal body of work as well as live gestural recordings. This layered datasets of real time data combined with trained data allowed the machine to generate drawings that responded to both the artists movements and biofeedback in real time as well as the the archival data of her past works.
In this project, I think the artist raises important questions about the nature of authorship and collaboration. The choice to train the machine on previous data turned it into more of an active partner than merely a tool. It pushes me to reconsider what ownership means in art-making and whether creativity can be shared between human and machine.
https://sougwen.com/project/drawing-operations
https://sougwen.com/machinecollaboration
Using HandPose, following the examples above and the ml5.js documentation, experiment with controlling elements of a p5.js sketch (color, geometry, sound, text, etc) with the output of the model. Try to create an interaction that is surprising or one that is inspired by the project you find.