A System for Evolving Art Using Supervised Learning and Aesthetic Analogies
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
- PDF / 597,778 Bytes
- 21 Pages / 439.37 x 666.142 pts Page_size
- 43 Downloads / 158 Views
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. Keywords Genetic algorithms · Evolutionary art and design · Genetic programming · Hybrid systems · Computational analogy · Aesthetics
1 Introduction Analogy is the comparison of separate domains. The process of analogy has strong applications in communication, logical reasoning, and creativity. A human artist will often take some source material as inspiration and create an equivalent, or related art piece in their chosen artistic domain. This process of metaphor is the equivalent of making an artistic analogy and has been used successfully in a literal form by artists like Klee [1], Kandinsky [2] and more recently Snibbe [3]. Similar approaches A. Breen (B) · C. O’Riordan National University of Ireland, Galway, Ireland e-mail: [email protected] URL: http://www3.it.nuigalway.ie/cirg/ C. O’Riordan e-mail: [email protected] © Springer Nature Switzerland AG 2019 J. J. Merelo et al. (eds.), Computational Intelligence, Studies in Computational Intelligence 792, https://doi.org/10.1007/978-3-319-99283-9_3
45
46
A. Breen and C. O’Riordan
are often taken in a less direct form by stage lighting designers or film soundtrack composers. Our aim is to make computational analogies between the domains of music and visuals by making use of aesthetic models, computational analogy, and grammatical evolution. This work has direct practical applications for live performance and stage lighting design. The work in this paper may also have less direct applications in user interface and user experience design with particular use in the automatic generation of user interfaces and subconscious feedback mechanisms. Beyond these application domains, our research motivation also includes gaining insight into aesthetics and analogical reasoning.
1.1 Creating Aesthetic Analogies One of the major challenges of computational art is to understand what makes an art piece good. Indeed the cultural and contextual influences of an art piece may define what makes it emotive, such as Duchamp’s Fountain [4] or René Magritte’s The Treachery of Images [5], but beyond that we rely on the aesthetics of an obje
Data Loading...
