Predicting Reinforcement of Pitch Sequences via LSTM and TD.
Judy A. Franklin · University of Michigan Library Repository · 2004
We examine the use of a recurrent neural network called Long Short-Term Memory (LSTM) with a prediction algorithm called temporal difference (TD) to predict the outcome of a music pitch sequence, while the sequence is being played. This is part of a larger system that will use this prediction in order to choose pitches to play. We describe our previous results using the LSTM network for musical tasks and then show its ability to predict a positive or negative outcome for a short musical task of chromatic lead-in to a chord tone. Then we describe its ability to predict positive outcomes when certain chord tones are played on the last beat of each bar of ii-V-I