Primal-improv

Towards co-evolutionary musical improvisation

Marco Scirea, Peter Eklund, Julian Togelius, Sebastian Risi

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    This paper describes a work in progress on co-evolving Artificial Neural Networks (ANNs) for music improvisation. Using this neuro-evolutionary approach the ANNs adapt to the changes in the human player's music as input, while still maintaining some of the structure of the musical piece previously evolved. The system is called Primal-Improv and evolves modules that are composed of two ANNs, one controlling pitch and one controlling rhythm. The results of a quantitative study show that, by only introducing simple rules as fitness functions, the system is able to generate more interesting arrangements than ANNs evolved without a specific objective. The emerging and interesting musical patterns that are produced by the evolved ANNs hint at the promising potential of the system.

    Original languageEnglish (US)
    Title of host publication2017 9th Computer Science and Electronic Engineering Conference, CEEC 2017 - Proceedings
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages172-177
    Number of pages6
    ISBN (Electronic)9781538630075
    DOIs
    StatePublished - Nov 8 2017
    Event9th Computer Science and Electronic Engineering Conference, CEEC 2017 - Colchester, United Kingdom
    Duration: Sep 27 2017Sep 29 2017

    Other

    Other9th Computer Science and Electronic Engineering Conference, CEEC 2017
    CountryUnited Kingdom
    CityColchester
    Period9/27/179/29/17

    Fingerprint

    Neural networks

    ASJC Scopus subject areas

    • Computer Science (miscellaneous)
    • Computer Networks and Communications
    • Computer Science Applications
    • Electrical and Electronic Engineering

    Cite this

    Scirea, M., Eklund, P., Togelius, J., & Risi, S. (2017). Primal-improv: Towards co-evolutionary musical improvisation. In 2017 9th Computer Science and Electronic Engineering Conference, CEEC 2017 - Proceedings (pp. 172-177). [8101620] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CEEC.2017.8101620

    Primal-improv : Towards co-evolutionary musical improvisation. / Scirea, Marco; Eklund, Peter; Togelius, Julian; Risi, Sebastian.

    2017 9th Computer Science and Electronic Engineering Conference, CEEC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 172-177 8101620.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Scirea, M, Eklund, P, Togelius, J & Risi, S 2017, Primal-improv: Towards co-evolutionary musical improvisation. in 2017 9th Computer Science and Electronic Engineering Conference, CEEC 2017 - Proceedings., 8101620, Institute of Electrical and Electronics Engineers Inc., pp. 172-177, 9th Computer Science and Electronic Engineering Conference, CEEC 2017, Colchester, United Kingdom, 9/27/17. https://doi.org/10.1109/CEEC.2017.8101620
    Scirea M, Eklund P, Togelius J, Risi S. Primal-improv: Towards co-evolutionary musical improvisation. In 2017 9th Computer Science and Electronic Engineering Conference, CEEC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 172-177. 8101620 https://doi.org/10.1109/CEEC.2017.8101620
    Scirea, Marco ; Eklund, Peter ; Togelius, Julian ; Risi, Sebastian. / Primal-improv : Towards co-evolutionary musical improvisation. 2017 9th Computer Science and Electronic Engineering Conference, CEEC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 172-177
    @inproceedings{a9735155393449539159cf51c61ade76,
    title = "Primal-improv: Towards co-evolutionary musical improvisation",
    abstract = "This paper describes a work in progress on co-evolving Artificial Neural Networks (ANNs) for music improvisation. Using this neuro-evolutionary approach the ANNs adapt to the changes in the human player's music as input, while still maintaining some of the structure of the musical piece previously evolved. The system is called Primal-Improv and evolves modules that are composed of two ANNs, one controlling pitch and one controlling rhythm. The results of a quantitative study show that, by only introducing simple rules as fitness functions, the system is able to generate more interesting arrangements than ANNs evolved without a specific objective. The emerging and interesting musical patterns that are produced by the evolved ANNs hint at the promising potential of the system.",
    author = "Marco Scirea and Peter Eklund and Julian Togelius and Sebastian Risi",
    year = "2017",
    month = "11",
    day = "8",
    doi = "10.1109/CEEC.2017.8101620",
    language = "English (US)",
    pages = "172--177",
    booktitle = "2017 9th Computer Science and Electronic Engineering Conference, CEEC 2017 - Proceedings",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    address = "United States",

    }

    TY - GEN

    T1 - Primal-improv

    T2 - Towards co-evolutionary musical improvisation

    AU - Scirea, Marco

    AU - Eklund, Peter

    AU - Togelius, Julian

    AU - Risi, Sebastian

    PY - 2017/11/8

    Y1 - 2017/11/8

    N2 - This paper describes a work in progress on co-evolving Artificial Neural Networks (ANNs) for music improvisation. Using this neuro-evolutionary approach the ANNs adapt to the changes in the human player's music as input, while still maintaining some of the structure of the musical piece previously evolved. The system is called Primal-Improv and evolves modules that are composed of two ANNs, one controlling pitch and one controlling rhythm. The results of a quantitative study show that, by only introducing simple rules as fitness functions, the system is able to generate more interesting arrangements than ANNs evolved without a specific objective. The emerging and interesting musical patterns that are produced by the evolved ANNs hint at the promising potential of the system.

    AB - This paper describes a work in progress on co-evolving Artificial Neural Networks (ANNs) for music improvisation. Using this neuro-evolutionary approach the ANNs adapt to the changes in the human player's music as input, while still maintaining some of the structure of the musical piece previously evolved. The system is called Primal-Improv and evolves modules that are composed of two ANNs, one controlling pitch and one controlling rhythm. The results of a quantitative study show that, by only introducing simple rules as fitness functions, the system is able to generate more interesting arrangements than ANNs evolved without a specific objective. The emerging and interesting musical patterns that are produced by the evolved ANNs hint at the promising potential of the system.

    UR - http://www.scopus.com/inward/record.url?scp=85040771181&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85040771181&partnerID=8YFLogxK

    U2 - 10.1109/CEEC.2017.8101620

    DO - 10.1109/CEEC.2017.8101620

    M3 - Conference contribution

    SP - 172

    EP - 177

    BT - 2017 9th Computer Science and Electronic Engineering Conference, CEEC 2017 - Proceedings

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -