The purpose of this project is to create a useful tool for musicians that utilizes the harmonic content of their playing to recommend new, relevant chords to play. This is done by training various Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) on the lead sheets of 100 different jazz standards. A total of 200 unique datasets were produced and tested, resulting in the prediction of nearly 51 million chords. A note-prediction accuracy of 82.1% and a chord-prediction accuracy of 34.5% were achieved across all datasets. Methods of data representation that were rooted in valid music theory frameworks were found to increase the efficacy of harmonic prediction by up to 6%. Optimal LSTM input sizes were also determined for each method of data representation.
In the face of deep disconnection and chaotic crises throughout our planet, I have identified five invitations for foundational actions and ways of living, that can lead to us deepening our connection with ourselves and with the Earth in individualized ways, while cultivating harmony on our shared world. These are; to listen, to express, to envision, to reciprocate, and to dance. An open mind and heart will make them most effective.