Predicting Reinforcement of Pitch Sequences via LSTM and TD

International Computer Music Conference, ICMC Proceedings

Volumn , Issue , 2004, Pages

  Franklin, Judy A ^a  

^a SMITH COLLEGE   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

FORECASTING; MUSIC;

LARGE SYSTEM; MEMORY NETWORK; PREDICTION ALGORITHMS; TEMPORAL DIFFERENCES;

LONG SHORT-TERM MEMORY;

EID: 33746261949     PISSN: 22233881     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (20)

1. Bakker, B. (2002). Reinforcement learning with long short-term memory. In T. Dietterich, S. Becker, and Z. Ghahramani (Eds.), Neural Information Processing Systems, 14. MIT Press, Cambridge, MA.
2. Berg, S. (1990). Jazz Improvisation: the Goal-Note Method, Second Ed. Delevan, NY: Kendor Music, Inc.
3. Campolucci, P. (1998). A Circuit Theory Approach to Recurrent Neural Network Architectures and Learning Methods. Universita Degli Studi di Bologna: Dottorato di Ricerca in Ingegneria Elettrotecnica.
4. Dannenberg, R., B. Thom, and D. Watson (1997). A machine learning approach to musical style recognition. In Proceedings of International Computer Music Conference. ICMA.
5. Eck, D. and J. Schmidhuber (2002). Learning the long-term structure of the blues. In Proceedings of International Conference on Artificial Neural Networks, pp. 284–289. ICANN.
6. Franklin, J. A. (2000). Multi-phase learning for jazz improvisation and interaction. In Proc. 8th Biennial Connecticut College Symposium on Arts and Technology. CT College, New London CT.
7. Franklin, J. A. (2001). Learning and improvisation. In T. Dietterich, S. Becker, and Z. Ghahramani (Eds.), Neural Information Processing Systems 14. MIT Press, Cambridge, MA.
8. Franklin, J. A. (2004a). Computational models for learning pitch and duration using lstm recurrent neural networks. In Proc. of the International Conference on Musical Perception and Cognition 8.
9. Franklin, J. A. (2004b). Recurrent neural networks and pitch representations for music tasks. In Proc. of the Florida Artificial Intelligence Research Symposium (FLAIRS) 2004.
10. Gers, F. A., J. Schmidhuber, and F. Cummins (2000). Learning to forget: Continual prediction with lstm. Neural Computation 12(10), 2451–2471.
11. Griffith, N. G. and P. M. Todd (1999). Musical Networks: Parallel Distributed Perception and Performance. Cambridge, Massachusetts: The MIT Press.
12. Jordan, M. (1986). Attractor dynamics and parallelism in a connectionist sequential machine. In Proc. Eighth Annual Conf. of the Cognitive Science Society, Amherst, MA.
13. Laden, B. and D. H. Keefe (1991). The representation of pitch in a neural net model of chord classification. In P. Todd and E. Loy (Eds.), Music and Connectionism, Cambridge, Massachusetts. The MIT Press.
14. Mozer, M. C. (1994). Neural network music composition by prediction: Exploring the benefits of psychophysical constraints and multiscale processing. Connection Science 6, 247–280.
15. Rumelhart, D., G. Hinton, and R. Williams (1986). Learning internal representations by error propagation. Parallel Distributed Processing 1, 318–362.
16. Sutton, R. S. and A. G. Barto (1998). Reinforcement Learning. Cambridge, Massachusetts: The MIT Press.
17. Tesauro, G. J. (1994). Td-gammon, a self-teaching backgammon program, achieves master-level play. Neural Computation 6(2), 215–219.
18. Todd, P. M. (1991). A connectionist approach to algorithmic composition. Music and Connectionism.
19. Todd, P. M. and E. D. Loy (1991). Music and Connectionism. Cambridge, Massachusetts: The MIT Press.
20. Williams, R. J. and D. Zipser (1988). A learning algorithm for continually running fully recurrent networks. San Diego, La Jolla, CA: Tech Report ICS-8805, Univ of Calif.