ægo is a musical performance for one learning machine and person, co-created with Axel Chemla—Romeu-Santos.
“Then the answers, instead of coming from my likes and dislikes, come from chance operations, and that has the effect of opening me to possibilities that I hadn’t considered. Chance-determined answers will open my mind to the world around.” — John Cage, 1982.
ægo is a performance that stages a person and a machine that learn to improvise in music. The machine uncertainly explores a spectral latent space, while the person communicates positive or negative reinforcement, turning their hands front or back, in an attempt to teach the machine how to explore this space. Gradually, the person gives up communicating consistent reinforcement to the machine, leaving the machine’s learning undetermined. Freed from the obligation to record their preferences into the machine, the person engages in deep listening through sound, and learns to improvise in music.
ægo results from a research-creation project led with two deep learning models: VSChaos and Co-Explorer.
Year
2019—2022
Credits
The project was developed in collaboration with the ISMM and ACIDS groups of IRCAM, in the context of a PhD thesis at Sorbonne Université.
Events
Performance @ Cirque Électrique, Paris, Fr (November 2022)
Performance @ Friche La Belle de Mai, Marseille, Fr (October 2019)
Music program at CMMR 2019
Performance @ Conservatoire Pierre Barbizet, Marseille, Fr (May 2022)
Music program at TENOR 2022