The Self-Supervising Machine
Benjamin D. Smith, and Guy E. Garnett
Proceedings of the International Conference on New Interfaces for Musical Expression
- Year: 2011
- Location: Oslo, Norway
- Pages: 108–111
- Keywords: NIME, machine learning, interactive computer music, machine listening, improvisation, adaptive resonance theory
- DOI: 10.5281/zenodo.1178169 (Link to paper)
- PDF link
Abstract:
Supervised machine learning enables complex many-to-manymappings and control schemes needed in interactive performance systems. One of the persistent problems in theseapplications is generating, identifying and choosing inputoutput pairings for training. This poses problems of scope(limiting the realm of potential control inputs), effort (requiring significant pre-performance training time), and cognitive load (forcing the performer to learn and remember thecontrol areas). We discuss the creation and implementationof an automatic "supervisor", using unsupervised machinelearning algorithms to train a supervised neural networkon the fly. This hierarchical arrangement enables networktraining in real time based on the musical or gestural control inputs employed in a performance, aiming at freeing theperformer to operate in a creative, intuitive realm, makingthe machine control transparent and automatic. Three implementations of this self supervised model driven by iPod,iPad, and acoustic violin are described.
Citation:
Benjamin D. Smith, and Guy E. Garnett. 2011. The Self-Supervising Machine. Proceedings of the International Conference on New Interfaces for Musical Expression. DOI: 10.5281/zenodo.1178169BibTeX Entry:
@inproceedings{Smith2011, abstract = {Supervised machine learning enables complex many-to-manymappings and control schemes needed in interactive performance systems. One of the persistent problems in theseapplications is generating, identifying and choosing inputoutput pairings for training. This poses problems of scope(limiting the realm of potential control inputs), effort (requiring significant pre-performance training time), and cognitive load (forcing the performer to learn and remember thecontrol areas). We discuss the creation and implementationof an automatic "supervisor", using unsupervised machinelearning algorithms to train a supervised neural networkon the fly. This hierarchical arrangement enables networktraining in real time based on the musical or gestural control inputs employed in a performance, aiming at freeing theperformer to operate in a creative, intuitive realm, makingthe machine control transparent and automatic. Three implementations of this self supervised model driven by iPod,iPad, and acoustic violin are described.}, address = {Oslo, Norway}, author = {Smith, Benjamin D. and Garnett, Guy E.}, booktitle = {Proceedings of the International Conference on New Interfaces for Musical Expression}, doi = {10.5281/zenodo.1178169}, issn = {2220-4806}, keywords = {NIME, machine learning, interactive computer music, machine listening, improvisation, adaptive resonance theory }, pages = {108--111}, title = {The Self-Supervising Machine}, url = {http://www.nime.org/proceedings/2011/nime2011_108.pdf}, year = {2011} }