HNHacker News
TopNewBestAskShowJobs

mcleavey

11 karma · joined November 28, 2018

submissionscomments
mcleavey··on Generating classical music with LSTM neural networks
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.
mcleavey··on Generating classical music with LSTM neural networks
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!
mcleavey··on Generating classical music with LSTM neural networks
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.