Improvisation and Learning

Abstract

This article presents a 2-phase computational learning model and appli- cation. As a demonstration, a system has been built, called CHIME for Computer Human Interacting Musical Entity. In phase 1 of training, re- current back-propagationtrains the machine to reproduce 3 jazz melodies. The recurrent network is expanded and is further trained in phase 2 with a reinforcement learning algorithm and a critique produced by a set of basic rules for jazz improvisation. After each phase CHIME can interactively improvise with a human in real time.

Cite

Text

Franklin. "Improvisation and Learning." Neural Information Processing Systems, 2001.

Markdown

[Franklin. "Improvisation and Learning." Neural Information Processing Systems, 2001.](https://mlanthology.org/neurips/2001/franklin2001neurips-improvisation/)

BibTeX

@inproceedings{franklin2001neurips-improvisation,
  title     = {{Improvisation and Learning}},
  author    = {Franklin, Judy A},
  booktitle = {Neural Information Processing Systems},
  year      = {2001},
  pages     = {1377-1384},
  url       = {https://mlanthology.org/neurips/2001/franklin2001neurips-improvisation/}
}