Let's set up our system for the model:
- In Piano, the lowest note is 24 and the highest is 102; hence, the range of notes is 78. Thus, the number of columns in the encoded matrix is 156 (that is, 78 for note-on and 78 for note-off):
lowest_note = 24L highest_note = 102L note_range = highest_note-lowest_note
- We will create notes for 15 number of steps at a time with 2,340 nodes in the input layer and 50 nodes in the hidden layer:
num_timesteps = 15L num_input = 2L*note_range*num_timesteps num_hidden = 50L
- The learning rate (alpha) is 0.1:
alpha<-0.1