An adaption of the schema theorem to various crossover and mutation operators for a music segmentation problem

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

3 Citations (Scopus)

Abstract

The schema theorem provides theoretical background for the effectiveness of genetic algorithms and serves as a formal model to explain their success. It describes the functionality of genetic algorithms under very restrictive limitations of a canonical genetic algorithm which applies a binary alphabet, individuals of equal length, fitness-proportional selection, single-point crossover, and gene-wise mutation. Applications of genetic algorithms, however, are often based on noncanonical variations and, therefore, are not verified by the theory of the traditional theorem. This paper describes the adaption of the theorem for various other crossover and mutation operators focusing on the application of genetic algorithms to a music segmentation problem.

Original languageEnglish
Title of host publicationGECCO'12 - Proceedings of the 14th International Conference on Genetic and Evolutionary Computation Companion
PublisherACM Sigevo
Pages469-476
Number of pages8
ISBN (Print)9781450311786
DOIs
Publication statusPublished - 2012
Event14th International Conference on Genetic and Evolutionary Computation, GECCO'12 - Philadelphia, PA, United States
Duration: 7 Jul 201211 Jul 2012

Publication series

NameGECCO'12 - Proceedings of the 14th International Conference on Genetic and Evolutionary Computation Companion

Conference

Conference14th International Conference on Genetic and Evolutionary Computation, GECCO'12
Country/TerritoryUnited States
CityPhiladelphia, PA
Period07.07.201211.07.2012

Keywords

  • Building block hypothesis
  • Genetic algorithms
  • Music Information Retrieval
  • Schema theorem

Fingerprint

Dive into the research topics of 'An adaption of the schema theorem to various crossover and mutation operators for a music segmentation problem'. Together they form a unique fingerprint.

Cite this