mcleavey
Re:Generating classical music with LSTM neural networks
on Wednesday November 28, 2018 @03:12PM (#18555173)
Transformer is working really well- I'm very excited. I'll probably be sharing results soon. Yes, the attention makes a huge difference & the pieces are both more creative and more coherent.
Re:Generating classical music with LSTM neural networks
on Wednesday November 28, 2018 @02:49PM (#18554990)
Haha, very true. It was Charlie's question in this interview that made me realize the 62 key limit was an old fix that I no longer needed, so now I'm trying out expanding my dataset and also expanding to the full 88 keys!
Re:Generating classical music with LSTM neural networks
on Wednesday November 28, 2018 @02:46PM (#18554963)
That's so interesting - you're totally right that setting constraints often leads to really creative ideas. It reminds me of the "crab canons" by Mozart and Bach: https://en.wikipedia.org/wiki/Crab_canon .
I also think there's room for other creative encodings for music - possibly expanding these notewise/chordwise ideas, or possibly going in a totally new direction. It's fascinating to me how much the generations are affected by the encoding.