Timezone: »
Poster
Neural Dynamic Programming for Musical Self Similarity
Christian Walder · Dongwoo Kim
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.
Author Information
Christian Walder (Data61, the Australian National University)
Dongwoo Kim (The Australian National University)
Related Events (a corresponding poster, oral, or spotlight)
-
2018 Oral: Neural Dynamic Programming for Musical Self Similarity »
Thu Jul 12th 12:30 -- 12:50 PM Room Victoria
More from the Same Authors
-
2019 Poster: Monge blunts Bayes: Hardness Results for Adversarial Training »
Zac Cranko · Aditya Menon · Richard Nock · Cheng Soon Ong · Zhan Shi · Christian Walder -
2019 Oral: Monge blunts Bayes: Hardness Results for Adversarial Training »
Zac Cranko · Aditya Menon · Richard Nock · Cheng Soon Ong · Zhan Shi · Christian Walder -
2018 Poster: Self-Bounded Prediction Suffix Tree via Approximate String Matching »
Dongwoo Kim · Christian Walder -
2018 Oral: Self-Bounded Prediction Suffix Tree via Approximate String Matching »
Dongwoo Kim · Christian Walder -
2017 Poster: Fast Bayesian Intensity Estimation for the Permanental Process »
Christian Walder · Adrian N Bishop -
2017 Talk: Fast Bayesian Intensity Estimation for the Permanental Process »
Christian Walder · Adrian N Bishop