Backpropagation and Bach´s 5th cello suite (Sarabande)

Summary form only given, as follows. An attempt is described to model the note-to-note tonal transitions in the music of J.S. Bach with a two-layer neural set. The learning phase employs the standard backpropagation algorithm, along with several minor modifications to improve performance. In the simulation or ´composition´ phase, where the goal is the production of a new piece of music possessing Bach-like qualities, a mixture of net realizations is proposed as a means of avoiding trivial cycling.<>