Neural Dynamic Programming for Musical Self Similarity

Christian Walder, Dongwoo Kim
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:5105-5113, 2018.

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-walder18a, title = {Neural Dynamic Programming for Musical Self Similarity}, author = {Walder, Christian and Kim, Dongwoo}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {5105--5113}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/walder18a/walder18a.pdf}, url = {https://proceedings.mlr.press/v80/walder18a.html}, 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.} }
Endnote
%0 Conference Paper %T Neural Dynamic Programming for Musical Self Similarity %A Christian Walder %A Dongwoo Kim %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-walder18a %I PMLR %P 5105--5113 %U https://proceedings.mlr.press/v80/walder18a.html %V 80 %X 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.
APA
Walder, C. & Kim, D.. (2018). Neural Dynamic Programming for Musical Self Similarity. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:5105-5113 Available from https://proceedings.mlr.press/v80/walder18a.html.

Related Material