Chord classifications by artificial neural networks revisited: internal representations of circles of major thirds and minor thirds

  • Authors:

  • Vanessa Yaremchuk;Michael R. W. Dawson

  • Affiliations:

  • Biological Computation Project, Department of Psychology, University of Alberta, Edmonton, Alberta, Canada;Biological Computation Project, Department of Psychology, University of Alberta, Edmonton, Alberta, Canada

  • Venue:
  • ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes an artificial neural network that can be viewed as an extension of a pioneering network described by Laden and Keefe. This network was trained to classify sets of four musical notes into four different chord classes, regardless of the musical key or the form (inversion) of the chord. This new network has a slightly modified training set; after successful training the internal structure was analyzed and was found to be unique. That is, rather than using the 12 musical notes of Western music, the network used only 4 musical notes based upon circles of major thirds and of minor thirds[1].