Continuous-Time Recurrent Neural Networks for Generative and Interactive Musical Performance

  • Oliver Bown
  • Sebastian Lexer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3907)


This paper describes an ongoing exploration into the use of Continuous-Time Recurrent Neural Networks (CTRNNs) as generative and interactive performance tools, and using Genetic Algorithms (GAs) to evolve specific CTRNN behaviours. We propose that even randomly generated CTRNNs can be used in musically interesting ways, and that evolution can be employed to produce networks which exhibit properties that are suitable for use in interactive improvisation by computer musicians. We argue that the development of musical contexts for the CTRNN is best performed by the computer musician user rather than the programmer, and suggest ways in which strategies for the evolution of CTRNN behaviour may be developed further for this context.


Hide Node Input State Input Pattern Recurrent Neural Network Input Node 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Todd, P.M., Werner, G.: Frankensteinian approaches to evolutionary music composition. In: Griffith, N., Todd, P.M. (eds.) Musical Networks: Parallel istributed Perception and Performance, pp. 313–339. MIT Press/Bradford Books (1999)Google Scholar
  2. 2.
    Miranda, E.: Composing Music with Computers. Focal Press (2001)Google Scholar
  3. 3.
  4. 4.
  5. 5.
  6. 6.
    Darwin, C.: On the origin of species by means of natural selection, or The preservation of favoured races in the struggle for life. D. Appleton and company (1860)Google Scholar
  7. 7.
    Grey Walter, W.: An imitation of life. Scientific American 182(4), 42–54 (1950)CrossRefGoogle Scholar
  8. 8.
    Slocum, A.C., Downey, D.C., Beer, R.D.: Further experiments in the evolution of minimally cognitive behavior: From perceiving affordances to selective attention. In: Meyer, J., Berthoz, A., Floreano, D., Roitblat, H., Wilson, S. (eds.) From Animals to Animats 6: Proceedings of the Sixth International Conference on Simulation of Adaptive Behavior, pp. 430–439. MIT Press, Cambridge (2000)Google Scholar
  9. 9.
    Beer, R.D.: The dynamics of active categorical perception in an evolved model agent. Adaptive Behavior 11(4), 209–243 (2003)CrossRefGoogle Scholar
  10. 10.
    Beer, R.D.: On the dynamics of small continuous recurrent neural networks. Adaptive Behavior 3(4), 469–509 (1995)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Kaplan, D., Glass, L.: Understanding Nonlinear Dynamics. Springer, Heidelberg (1995)zbMATHGoogle Scholar
  12. 12.
    Todd, P.M., Gareth Loy, D.: Music and Connectionism. MIT Press, Cambridge (1991)Google Scholar
  13. 13.
    Griffith, N., Todd, P.M. (eds.): Musical Networks. MIT Press, Cambridge (1999)Google Scholar
  14. 14.
    Mozer, M.C.: Neural network music composition by prediction: Exploring the benefits of psychoacoustic constraints and multi-scale processing. Connection Science 6(2-3), 247–280 (1994)CrossRefGoogle Scholar
  15. 15.
    Sims, K.: Evolving 3d morphology and behaviour by competition. In: Artificial Life IV Proceedings. MIT Press, Cambridge (1994)Google Scholar
  16. 16.
    Tilbury, J.: Feldman and the piano: the art of touch and celebration of contingency. In: Second Biennial International Conference On Twentieth-Century Music, Goldsmiths College, University of London (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Oliver Bown
    • 1
  • Sebastian Lexer
    • 2
  1. 1.Centre for Cognition, Computation and Culture 
  2. 2.Department of Music, Goldsmiths CollegeUniversity of LondonNew CrossUK

Personalised recommendations