Timezone: »

 
Poster
Neural Dynamic Programming for Musical Self Similarity
Christian Walder · Dongwoo Kim

Thu Jul 12 09:15 AM -- 12:00 PM (PDT) @ Hall B #20
in Posters Thu »

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.

[ PDF] 

Author Information

Christian Walder (Data61, the Australian National University)
Dongwoo Kim (The Australian National University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors