A study of various representations using NEXTPITCH: A learning classifier system.

Title: A study of various representations using NEXTPITCH: A learning classifier system.
Identifier: AAI9707087
identifier: 9707087
Creator: Federman, Francine.
Contributor: Adviser: Jacqueline A. Jones
Date: 1996
Language: English
Publisher: City University of New York.
Subject: Computer Science | Artificial Intelligence | Music
Abstract: Our model, NEXTPITCH, a learning classifier system using genetic algorithms, inductively learns to predict the next note in a nursery melody. Just as a listener develops expectations of what is to follow based on what has been heard, NEXTPITCH models human music learning by developing the rules that represent actual pitch transitions in the melody.;The focal point of this research is to compare and analyze different representations of specific features of Western tonal music within the construct of a learning classifier system. The rationale for the specific note representations merges ideas from learning classifier systems and genetic algorithms with concepts espoused by the music cognition community.;The areas of study addressed are representation of music, classifier format and the number of classifiers to use. Our results are correlated by analyses of classes so that we may examine the applicability of the results from one set of melodies to another.
Type: dissertation
Source: PQT Legacy CUNY.xlsx
degree: Ph.D.

Media: A study of various representations using NEXTPITCH: A learning classifier system.