[dncrane]

Thanks, that's a really good point. I agree that the patterns generated could be improved, but haven't come up with a good automated way to generate an unlimited amount of better ones. Please email me any thoughts you have about the best way to do this, I'm definitely interested in improving these (my email is on my profile page).

[knicholes]

I've been listening to the Stanford NLP deep learning lectures, and while I know hardly anything about it compared to most, "deep learning" is screaming at me. If you could generate a "corpus" of musical progressions based off of real music, you could very easily sample from a model to generate progressions that are likely to "co-occur."

This was posted three months ago on HN, but one person used it to generate music. http://karpathy.github.io/2015/05/21/rnn-effectiveness/

The folk music generation is located at https://soundcloud.com/seaandsailor/sets/char-rnn-composes-i.... I could imagine you could do something similar.

[philsnow]

Do you need to generate an unlimited number of them ? Could you just listen to the radio for a few hours and write down some patterns?

I know next to nothing about music theory.

[thornofmight]

In the example he listed each note goes either up or down one note to the next chord.