This is part 12 of my loose and varied analyses of the folk-rnn v2 model, which have included parts 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, and 11. In this part, I continue looking at beam search for sampling from the model. We will now investigate restricting the search of the sample […]

This is part 11 of my loose and varied analyses of the folk-rnn v2 model, which have included parts 1, 2, 3, 4, 5, 6, 7, 8, 9, and 10! Findings from these have appeared in my MuMu 2018 paper, “What do these 5,599,881 parameters mean? An analysis of a specific LSTM music transcription model, […]

This is part 10 of my loose and varied analyses of the folk-rnn v2 model, which have included parts 1, 2, 3, 4, 5, 6, 7, 8 and 9. In the last part we looked at the similarities of the activations inside folkrnn v2 as it generated a particular transcription. Today we are looking at […]

This is part 9 of my loose and varied analyses of the folk-rnn v2 model, which have included parts 1, 2, 3, 4, 5, 6, 7, and 8. As a brief review, the folkrnn v2 model maps elements of the standard basis of onto the positive surface of the unit L1-ball in by a series […]

The winning piece in the first folk-rnn composition competition is Gwyl Werin for mixed quartet by Derri Joseph Lewis. He used a tune generated by folk-rnn as a basis for both melodic fragments and harmonic construction in his piece. He chose the model trained without the repeat signs, a 9/8 meter, C mixolydian mode, an […]

Luca Turchet will be performing his composition, “Dialogues with folk-rnn”, at the June 5 concert of NIME 2018. A version of this work was premiered at the Nov. 20 2017 concert in London. He constructed this work from 19 transcriptions generated by folk-rnn, all available in the “folk-rnn v2 Session Book, volume 1 (of 10)“. […]

The Tune of the Month for May at Melodeon.net is the Tip Top Polka. So I decided to learn the tune and see what folk-rnn v2 would generate when primed with its first four bars (but transposed to minor to contrast with the happy polka). After many trials (folk-rnn v2 doesn’t seem to like duple […]

Spread the news far and wide! The aim of this competition is to explore an application of machine learning to music — in particular the online tool at folkrnn.org. This model is an example of artificial intelligence trained on traditional tunes, mainly Irish and English. The web interface allows users to generate new melodies using […]

This is part 8 of what is turning out to be a raft ride on a stream-of-consciousness analysis of the folk-rnn v2 model. After parts 1, 2, 3, 4, 5, 6 and 7 of this series, I don’t feel much closer to answering how it’s working its magic. It’s almost as if this little folk-rnn […]

Over the holiday break I started to dig into the music transcription models that we trained and used since 2016, and figure out what the ~6,000,000 parameters actually mean. In particular, we have been looking at the “version 2” model (see parts 1, 2, 3, 4, 5 and 6 of this series), which generated all […]