Neural dynamic programming for musical self similarity

Christian J. Walder*, Dongwoo Kim

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    We present a neural sequence model designed specifically for symbolic music. The model is based on a learned edit distance mechanism which generalises a classic recursion from computer science, leading to a neural dynamic program. Repeated motifs are detected by learning the transformations between them. We represent the arising computational dependencies using a novel data structure, the edit tree; this perspective suggests natural approximations which afford the scaling up of our otherwise cubic time algorithm. We demonstrate our model on real and synthetic data; in all cases it out-performs a strong stacked long short-term memory benchmark.

    Original languageEnglish
    Title of host publication35th International Conference on Machine Learning, ICML 2018
    EditorsAndreas Krause, Jennifer Dy
    PublisherInternational Machine Learning Society (IMLS)
    Pages8088-8096
    Number of pages9
    ISBN (Electronic)9781510867963
    Publication statusPublished - 2018
    Event35th International Conference on Machine Learning, ICML 2018 - Stockholm, Sweden
    Duration: 10 Jul 201815 Jul 2018

    Publication series

    Name35th International Conference on Machine Learning, ICML 2018
    Volume11

    Conference

    Conference35th International Conference on Machine Learning, ICML 2018
    Country/TerritorySweden
    CityStockholm
    Period10/07/1815/07/18

    Fingerprint

    Dive into the research topics of 'Neural dynamic programming for musical self similarity'. Together they form a unique fingerprint.

    Cite this