A self-learning musical grammar, or 'associative memory of the second kind'

@article{Kohonen1989ASM,
  title={A self-learning musical grammar, or 'associative memory of the second kind'},
  author={T. Kohonen},
  journal={International 1989 Joint Conference on Neural Networks},
  year={1989},
  pages={1-5 vol.1}
}
  • T. Kohonen
  • Published 1989
  • Computer Science
  • International 1989 Joint Conference on Neural Networks
A context-sensitive generative grammar that learns its production rules automatically from examples and optimizes the length of context for each individual production rule on the basis of conflicts occurring in the source material is described. The grammar has been applied to the generation of new melodic passages and counterpoint according to a certain style. This report describes some of the principal ideas and the work that was done. Music produced by this method generally sounds smooth… Expand
Connectionist Music Composition Based on Melodic and Stylistic Constraints
Generation of Folk Song Melodies using Bayes Transforms
Harmonizing Music the Boltzmann Way
Composing Music with Neural Networks and Probabilistic Finite-State Machines
Coupled Recurrent Models for Polyphonic Music Composition
Performance Following: Real-Time Prediction of Musical Sequences Without a Score
...
1
2
...

References

SHOWING 1-5 OF 5 REFERENCES
An Expert System for Harmonizing Four-Part Chorales
Self-Learning Inference Rules by Dynamically Expanding Context
  • Proc. of the IEEE 5. Why should this method be discussed in the First Annual International Conference on Neural Networks,
  • 1987
Dynamically Expanding Context, with Application to the Correction of Symbol Strings in the Recognition of Continuous Speech
  • Proc. of the Eighth International Conference on Pattern Recognition
  • 1986
Expanding Context, with Application to the Correction of Symbol Strings in the Recognition of Continuous Speech
  • Proc. of the Eighth International Conference on Pattern Recognition,
  • 1986
Certainly the present method does not belong to the pure Neural Network algorithms. It is rather to be regarded as an abstract scheme which exemplifies the competence of idealized learning algorithms