Adaptive Elusion - an improvisation for pianist and real-time machine learning

Palle Dahlstedt

Proceedings of the International Conference on New Interfaces for Musical Expression

Abstract

A continuation of my experiments with minimal algorithms, investigating how small an interactive musical algorithm can be and still invoke the feeling of "somebody there". Here, a small set of adaptive algorithms react to a live pianist, trying to imitate, elude and counteract his playing, while at the same time being completely dependent on it as a source of patterns and sounds. The piece explores real-time training as a primary modus of interaction, in a cat-and-mouse game of sorts. It is also an example of what I call entangled musicianship. What the pianist plays is a reaction to what the algorithm plays, and at the same time shapes the future playing of the algorithm, hence entangling performance and control.The musical response is generated by a small machine-learning algorithm that starts empty and is trained in real-time on what I am playing. It can also gradually forget what it has learnt.

Citation

Palle Dahlstedt. 2025. Adaptive Elusion - an improvisation for pianist and real-time machine learning. Proceedings of the International Conference on New Interfaces for Musical Expression. DOI: 10.5281/zenodo.17801166 [PDF]

BibTeX Entry


@inproceedings{nime2025_music_36,
abstract = {A continuation of my experiments with minimal algorithms, investigating how small an interactive musical algorithm can be and still invoke the feeling of "somebody there". Here, a small set of adaptive algorithms react to a live pianist, trying to imitate, elude and counteract his playing, while at the same time being completely dependent on it as a source of patterns and sounds. The piece explores real-time training as a primary modus of interaction, in a cat-and-mouse game of sorts. It is also an example of what I call entangled musicianship. What the pianist plays is a reaction to what the algorithm plays, and at the same time shapes the future playing of the algorithm, hence entangling performance and control.The musical response is generated by a small machine-learning algorithm that starts empty and is trained in real-time on what I am playing. It can also gradually forget what it has learnt.},
address = {Canberra, Australia},
articleno = {36},
author = {Palle Dahlstedt},
booktitle = {Proceedings of the International Conference on New Interfaces for Musical Expression},
doi = {10.5281/zenodo.17801166},
editor = {Sophie Rose and Jos Mulder and Nicole Carroll},
issn = {2220-4806},
month = {June},
note = {Live Performance},
numpages = {3},
pages = {142--144},
presentation-video = {https://youtu.be/kclJz0j1cto?si=7Yw_-1b1zkPHSBZA},
title = {Adaptive Elusion - an improvisation for pianist and real-time machine learning},
track = {Music},
url = {http://nime.org/proceedings/2025/nime2025_music_36.pdf},
urlsuppl1 = {http://nime.org/proceedings/2025/nime2025_music_36_file01.mp4},
year = {2025}
}