A system for evolving art using supervised learning and aesthetic analogies

Aidan Breen, Colm O’Riordan

Research output: Chapter in Book or Conference Publication/ProceedingChapterpeer-review

Abstract

Aesthetic experience is an important aspect of creativity and our perception of the world around us. Analogy is a tool we use as part of the creative process to translate our perceptions into creative works of art. In this paper we present our research on the development of an artificially intelligent system for the creation of art in the form of real-time visual displays to accompany a given music piece. The presented system achieves this by using Grammatical Evolution, a form of Evolutionary Computation, to evolve Mapping Expressions. These expressions form part of a conceptual structure, described herein, which allows aesthetic data to be gathered and analogies to be made between music and visuals. The system then uses the evolved mapping expressions to generate visuals in real-time, given some musical input. The output is a novel visual display, similar to concert or stage lighting which is reactive to input from a performer.

Original languageEnglish
Title of host publicationStudies in Computational Intelligence
PublisherSpringer-Verlag
Pages45-65
Number of pages21
DOIs
Publication statusPublished - 2019

Publication series

NameStudies in Computational Intelligence
Volume792
ISSN (Print)1860-949X

Keywords

  • Aesthetics
  • Computational analogy
  • Evolutionary art and design
  • Genetic algorithms
  • Genetic programming
  • Hybrid systems

Fingerprint

Dive into the research topics of 'A system for evolving art using supervised learning and aesthetic analogies'. Together they form a unique fingerprint.

Cite this