September 26, 2018 17:20

Abstract

Speaker: Dr. Christian Walder (Data61, Australia)

Title: Neural Dynamic Programming for Musical Self Similarity

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.

More Information

Date October 10, 2018 (Wed) 14:00 - 15:30
URL https://c5dc59ed978213830355fc8978.doorkeeper.jp/events/80323

Venue

Nihonbashi 1-chome Mitsui Building, 15th floor, 1-4-1 Nihonbashi, Chuo-ku, Tokyo 103-0027, Japan