EvoWorkshops2003
6th European Evolutionary Computing Workshops
14-16 April 2003

Menu
Home
EvoBIO
EvoCOP
EvoIASP
EvoMUSART
EvoROB
EvoSTIM

Post conference pages
2004 announcement
Awards
Photos
Feature articles
Proceedings

Joint event pages
Registration
Travel bursaries
Information for authors
Travel information
Where to stay
Local information
Programme overview
All accepted papers

Main contacts
EvoWorkshops chair
Günther Raidl
Local co-chairs
Edward Tsang
Riccardo Poli

EuroGP2003

EvoMUSART2003
1st European Workshop on Evolutionary Music and Art

Introduction

EvoMUSART2003 is the first workshop of the newly formed EvoNet working group on evolutionary music and art.

The idea of using computers for artistic activities springs from the first studies of what an intelligent machine could do. Nowadays, the worlds of music and art and the world of computational science are getting closer. This is thanks to the findings of many researchers who, over the last decade, have used genetic algorithms and similar adaptive methods in the creation of works of art, both visual and musical. However, there has been little sharing of ideas and few attempts to take a broader view over the various pieces of work in this area. The goal of this workshop on Evolutionary Music and Art is to present recent research results, including significant work-in-progress; to identify and explore directions for future research; and to stimulate closer interaction between members of this scientific (and artistic) community.

Each accepted paper will be presented orally at the workshop and printed in the proceedings published by Springer in the LNCS series.

Topics of interest

The workshop will address the following questions.

  • What is the current state-of-the-art in this area?
  • For what kinds of system have these methods not proven successful, and why not?
  • What recognition have these methods received outside the community that understands the technical details behind them? That is, have they the potential to "go mainstream"?
  • Systems have been developed which attempt to simulate the behaviour of human artists, while others attempt to help human artists. What are the commonalities and differences between these systems?
  • Many of these systems make use of interactive genetic algorithms. Can we begin to lay down a foundation for the theoretical analysis of such interactive algorithms, either drawing on mathematical theories of GA behaviour or on psychological theories of human-computer interaction and related topics?
  • How can these ideas be embedded into commercial products, such as electronic music hardware or generative computer graphics systems?
  • Can these approaches be used to support work in cross-art disciplines where multiple art forms are used together? Can they be used in science-art collaborations?
  • What is the role of aesthetics and how do we include aesthetics in these systems? What is the role of emotional response to art in such systems, and how might this tie in with recent developments in affective computing?
  • How might evolutionary art/music systems interact with the various different artistic and musical cultures?
  • Is there a methodology which would permit the joining together of different systems in order to develop a common evolutionary art system?
  • What might be the role of co-operation and competition between agents in such systems? Is the development of meta-level "artistic agents" an interesting direction for work in this field?

The workshop will also address related ideas such as the use of genetic algorithms in musical information retrieval, in musical performance and in the formal analysis of music. It is likely that there will be opportunities for displays of artworks and performances of music based on the techniques described in the paper. More details later.

Programme

Draft: subject to change

See also: Programme overview

Monday 14 April
0900-1000 Registration
1000-1115 EuroGP Session 1:
Conference opening and invited speaker: David Goldberg

Session chair: Terry Soule
1115-1130 Coffee break
1130-1300 Session 1:
Evolutionary Computation in Music and Sound Creation

Session chair: Juan Romero or Colin Johnson
MusicBlox: a Real-time Algorithmic Composition System Incorporating a Distributed Interactive Genetic Algorithm
Gartland-Jones A
Evolutionary Music and the Zipf-Mandelbrot Law: Progress towards Developing Fitness Functions for Pleasant Music.
Manaris W, Vaughan D, Wagner C, Romero J, Davis R
Genophone: Evolving Sounds and Integral Performance Parameter Mappings.
Mandelis J
Genetic Improvisation Model, a framework for real-time performance environments.
Neminovsky P, Watson R
1300-1400 Lunch
1400-1530 Session 2:
Evolutionary Computation Systems in Visual Arts, performances and Installations

Session chair: Colin Johnson or Penousal Machado
The emergence of Social Learning in Artificial Societies.
Annunziato M
Tabula Rasa: A Case Study in Evolutionary Curation.
Bird J, Webster A, Faith J
ArtiE-Fract: The Artist’s Viewpoints.
Lutton E, Cayla E, Chapuis J
Genetic Algorithms for the Generation of Models with Micropopulations.
Saez Y, Sanjuan O, Segovia J, Isasi P
1530-1600 Tea break
1600-1730 Session 3:
The Past, Present and Future of EC in Art and Music

Session chair: Colin Johnson
Towards a prehistory of evolutionary and adaptive computation in music.
Johnson C
On the development of critics in evolutionary computation artists.
Romero J, Machado P, Santos A, Cardoso A

Workshop close

Accepted papers

Springer Lecture Notes in Computer Science series The EvoWorkshops2003 proceedings will be
published by Spinger as part of their
Lecture Notes in Computer Science series.


ArtiE-Fract: The Artist’s Viewpoints.
Lutton E, Cayla E, Chapuis J
ArtiE-Fract is an interactive evolutionary system designed for artistic exploration of the space of fractal 2D shapes. We report in this paper an experiment performed with an artist, the painter Emmanuel Cayla. The benefit of such a collaboration was twofold: first of all, the system itself has evolved in order to better fit the needs of non-computer-scientist users, and second, it as initiated an artistic approach and open up the way to new possible design outputs.
EvoMUSART Session 2: Evolutionary Computation Systems in Visual Arts, performances and Installations: April 14, 1400-1530

Evolutionary Music and the Zipf-Mandelbrot Law: Progress towards Developing Fitness Functions for Pleasant Music.
Manaris W, Vaughan D, Wagner C, Romero J, Davis R
A study on a 220-piece corpus (baroque, classical, romantic, 12-tone, jazz, rock, DNA strings, and random music) reveals that aesthetically pleasing music may be describable under the Zipf-Mandelbrot law. Various Zipf-based metrics have been developed and evaluated. Some focus on music-theoretic at-tributes such as pitch, pitch and duration, melodic intervals, and harmonic inter-vals. Others focus on higher-order attributes and fractal aspects of musical bal-ance. Zipf distributions across certain dimensions appear to be a necessary, but not sufficient condition for pleasant music. Statistical analyses suggest that com-binations of Zipf-based metrics might be used to identify genre and/or composer. This is supported by a preliminary experiment with a neural network classifier. We describe an evolutionary music framework under development, which utilizes Zipf-based metrics as fitness functions.
EvoMUSART Session 1: Evolutionary Computation in Music and Sound Creation: April 14, 1130-1300

Genetic Algorithms for the Generation of Models with Micropopulations.
Saez Y, Sanjuan O, Segovia J, Isasi P
The present article puts forward a method for an interactive model generation through the use of Genetic Algorithms applied to small populations. Micropopulations actually worsen the problem of the premature convergence of the algorithm, since genetic diversity is very limited. In addition, some key factors, which modify the changing likelihood of alleles, cause the likelihood of premature convergence to decrease. The present technique has been applied to the design of 3D models, starting from generic and standard pieces, using objective searches and searches with no defined objective.
EvoMUSART Session 2: Evolutionary Computation Systems in Visual Arts, performances and Installations: April 14, 1400-1530

Genetic Improvisation Model, a framework for real-time performance environments.
Neminovsky P, Watson R
This paper presents the current state in an ongoing development of the Genetic Improvisation Model (GIM): a framework for the design of real-time improvi-sational systems. The aesthetic rationale for the model is presented, followed by a discussion of its general principles. A discussion of the Emonic Environment, a networked system for audiovisual creation built on GIM’s principles, follows.
EvoMUSART Session 1: Evolutionary Computation in Music and Sound Creation: April 14, 1130-1300

Genophone: Evolving Sounds and Integral Performance Parameter Mappings.
Mandelis J
This project explores the application of evolutionary techniques to the design of novel sounds and their characteristics during performance. It is based on the “selective breeding” paradigm and as such dispensing with the need for detailed knowledge of the Sound Synthesis Techniques involved, in order to design sounds that are novel and of musical interest. This approach has been used successfully on several SSTs therefore validating it as an Adaptive Sound Meta-synthesis Technique. Additionally, mappings between the control and the parametric space are evolved as part of the sound setup. These mappings are used during performance.
EvoMUSART Session 1: Evolutionary Computation in Music and Sound Creation: April 14, 1130-1300

MusicBlox: a Real-time Algorithmic Composition System Incorporating a Distributed Interactive Genetic Algorithm
Gartland-Jones A
This paper discusses the motivation, design and construction of a generative music system, 'MusicBlox', (by the author) that utilises a domain specific, knowledge rich Genetic Algorithm (GA). The paper begins by de-scribing the functionality and musical aims of the project, and goes on to detail the implementation of a GA as part of the project's compositional sub-system, including a discussion of the suitability of using a GA for compositional tasks. The paper concludes that the developed GA is able to produce musically suc-cessful results, but that significant additional work still needs to be undertaken before it achieves all the aims outlined.
EvoMUSART Session 1: Evolutionary Computation in Music and Sound Creation: April 14, 1130-1300

On the development of critics in evolutionary computation artists.
Romero J, Machado P, Santos A, Cardoso A
One of the problems in the use of evolutionary computer systems in artistic tasks is the lack of artificial models of human critics. In this paper, based on the state of the art and on our previous related work, we propose a general architecture for an artificial art critic, and a strategy for the validation of this type of system. The architecture includes two modules: the analyser, which does a pre-processing of the artwork, extracting several measurements and characteristics; and the evaluator, which, based on the output of the analyser, classifies the artwork according to a certain criteria. The validation procedure consists of several stages, ranging from author and style discrimination to the integration of critic in a dynamic environment together with humans.
EvoMUSART Session 3: The Past, Present and Future of EC in Art and Music: April 14, 1600-1730

Tabula Rasa: A Case Study in Evolutionary Curation.
Bird J, Webster A, Faith J
This paper describes a novel use of evolutionary techniques to curate a main stream art show,Tabula Rasa .Thisallowedanopen- ended approach to curation that was entirely in keeping with the artistic motivations behind the project.We detail a major dificulty with this approach that will be faced by any future automatic curation systems.
EvoMUSART Session 2: Evolutionary Computation Systems in Visual Arts, performances and Installations: April 14, 1400-1530

The emergence of Social Learning in Artificial Societies.
Annunziato M
The most recent advances of artificial life research are opening up a new frontier: the creation of simulated life environments populated by autonomous agents. In several cases a new paradigm for learning is emerging: social learning as a form of self-organization of many individual learning. In this paper two different approaches are presented and discussed: genetic competition and partial emulation. Finally an example of application of these concepts.
EvoMUSART Session 2: Evolutionary Computation Systems in Visual Arts, performances and Installations: April 14, 1400-1530

Towards a prehistory of evolutionary and adaptive computation in music.
Johnson C
A number of systems have been created which apply genetic algorithms, cellular automata, artificial life, agents, and other evolutionary and adaptive computation ideas in the creation of music. The aim of this paper is to examine the context in which such systems arose by looking for features of experimental music which prefigure the ideas used in such systems. A number of ideas are explored: the use of randomness in music, the view of compositions as parameterized systems, the idea of emergent structure in music and the idea of musicians performing the role of reactive agents.
EvoMUSART Session 3: The Past, Present and Future of EC in Art and Music: April 14, 1600-1730

Chairs

Colin G Johnson <c.g.johnson@ukc.ac.uk>
Juan Jesús Romero Cardalda <jj@udc.es>

Programme committee

  • Peter Bentley (UK)
  • Eleonora Bilotta (Italy)
  • Amílcar Cardoso (Portugal)
  • Matthew Lewis (USA)
  • Penousal Machado (Portugal)
  • Eduardo R. Miranda (Brazil)
  • Luigi Pagliarini (Italy)
  • Antonino Santos (Spain)
  • Stephen Todd (UK)
  • Geraint Wiggins (UK)
  • Tatsuo Unemi (Japan)

Past related conferences and journals