EvoWorkshops2005: EvoMUSART

3rd European Workshop on Evolutionary Music and Art

In Applications of Evolutionary Computing.

The application of Evolutionary Computation (EC) techniques for the development of creative systems is a new, exciting and significant area of research. There is a growing interest in the application of these techniques in fields such as: art and music generation, analysis and interpretation; architecture; and design.

EvoMUSART 2005 is the third workshop of the EvoNet working group on Evolutionary Music and Art. Following the success of previous events, the main goal of EvoMUSART 2005 is to bring together researchers who are using Evolutionary Computation in this context, providing the opportunity to promote, present and discuss ongoing work in the area.

The workshop will include an open panel for the discussion of the most relevant questions of the field. In order to promote participation, we encourage the participants to submit topics for debate. To foster cooperation among researchers, there will also be a panel for the proposal and discussion of potential collaboration opportunities.

The event includes a demonstration session, giving an opportunity for the presentation of evolutionary art and music in an informal environment. The submission of works for the demonstration session is independent from the submission of papers.

Accepted papers will be presented orally at the workshop and included in the EuroGP2005 conference proceedings, published by Springer Verlag in the Lecture Notes in Computer Science series.

Web address: http://www.evonet.info/eurogp2005

Topics include

Organising Committee

Program Chairs
Juan Romero
jj AT udc DOT es
University of A Coru“a
 
Penousal Machado
machado AT dei DOT uc DOT pt
CISUC - Centre for Informatics and Systems, University of Coimbra & ISEC - Instituto Superior de Engenharia de Coimbra
 
EvoWorkshops2005 Chair
Franz Rothlauf
rothlauf AT uni-mannheim DOT de
University of Mannheim, Germany
 
Local Chair
Marco Tomassini
Marco.Tomassini AT hec DOT unil DOT ch
University of Lausanne, Switzerland
 
Publicity Chair
Jano van Hemert
jvhemert AT cwi DOT nl
Napier University, Edinburgh, Scotland, UK

Note: the e-mail addresses are masked for spam protection.


Programme Committee

Alan Dorin, Monash University, Australia
AmŪlcar Cardoso, University of Coimbra, Portugal
Anargyros Sarafopoulos, Bournemouth University, UK
Andrew Gartland-Jones, University of Sussex, UK
Bill Manaris, College of Charleston, USA
Carlos Grilo, School of Technology and Management of Leiria, Portugal
Colin Johnson, University of Kent, UK
Eduardo R. Miranda, University of Plymouth, UK
Gary Greenfield, University of Richmond, USA
Geraint A. Wiggins, University of London, UK
Hideyuki Takagi, Kyushu University, Japan
Jon McCormack, Monash University, Australia
Lee Spector, Hampshire College, USA
Luigi Pagliarini, Academy of Fine Arts of Rome, Italy & University of Southern Denmark, Denmark
Martin Hemberg, Imperial College London, UK
Matthew Lewis, Ohio State University, USA
Michael Young, University of London, UK
Paul Brown, Independent Artist and Writer & Visiting Fellow, Birkbeck College, University of London, UK
Paul Nemirovsky, MIT Media Laboratory, USA
Peter Bentley, University College London
Peter Todd, Max Planck Institute for Human Development, Germany
Scott Draves, San Francisco, USA
Stefano Cagnoni, University of Parma., Italy
Stephen Todd, IBM, UK
Tatsuo Unemi, Soka University, Japan
Tim Blackwell, University of London, UK
William B Langdon, University College London, UK
William Latham, Art Games Ltd, UK


EvoMUSART Programme

Wednesday, 30 March 2005

Session1: Posters (1730-2000)

Thursday, 31 March 2005

Session 2: Evolutionary Music (0930-1100)

Understanding Expressive Music Performance Using Genetic Algorithms
Rafael Ramirez
Amaury Hazan

Toward User-directed Evolution of Sound Synthesis Parameters
James McDermott
Niall J.L. Griffith
Michael O'Neill

Evolutionary Search for Musical Parallelism
Soren Tjagvad Madsen
Gerhard Widmer

Session 3: Evolutionary Art (1120-1250)

The Electric Sheep Screen-Saver: A Case Study in Aesthetic Evolution
Scott Draves

Evolutionary Methods for Ant Colony Paintings
Gary Greenfield

Artificial Life, Death and Epidemics in Evolutionary, Generative Electronic Art
Alan Dorin

Session 4: Evolutionary Music and Art (1415-1545)

Bill Manaris
Penousal Machado
Clayton McCauley
Juan Romero
Dwight Krehbiel
Developing Fitness Functions for Pleasant Music: Zipf's Law and Interactive Evolution Systems

Tim Blackwell
Janis Jefferies
Swarm Tech-tiles

John Collomosse
Peter Hall (Best Paper Award Candidate)
Genetic Paint: A Search for Salient Paintings

Session 5: Open Problems (1600-1730)

Jon McCormack (Best Paper Award Candidate)
Open Problems in Evolutionary Music and Art

Discussion (1h)


EvoMUSART: Titles and abstracts of accepted papers

Jon McCormack

Open Problems in Evolutionary Music and Art

(Best Paper Award Candidate)
Applying evolutionary methods to the generation of music and art is a relatively new field of enquiry. While there have been some important developments, it might be argued that to date, successful results in this domain have been limited. Much of the present research can be characterized as finding ad-hoc methods that can produce subjectively interesting results. In this paper, it is argued that a stronger overall research plan is needed if the field is to develop in the longer term and attract more researchers. Five ’open problemsČ’ are defined and explained as broad principle areas of investigation for evolutionary music and art. Each problem is explained and the impetus and background for it is described in the context of creative evolutionary systems.


James McDermott
Niall J.L. Griffith
Michael O'Neill

Toward User-directed Evolution of Sound Synthesis Parameters

Experiments are described which use genetic algorithms operating on the parameter settings of an FM synthesizer, with the aim of mimicking known synthesized sounds. The work is considered as a precursor to the development of synthesis plug-ins using evolution directed by a user. Attention is focussed on the fitness functions used to drive the evolution: the main result is that a composite fitness function – based on a combination of perceptual measures, spectral analysis, and low-level sample-by-sample comparison – drives more successful evolution than fitness functions which use only one of these types of criterion.


Tim Blackwell
Janis Jefferies

Swarm Tech-tiles

This paper describes an exploration of visual and sonic texture. These textures are linked by a swarm of ? tech-tiles? , where each tech-tile is a rectangular element of an image or a sequence of audio samples. An entire image can be converted to a single tech-tile, which can be performed as a composition, or a swarm of small tiles can fly over the image, generating a sonic improvisation. In each case, spatial (visual) structure is mapped into temporal (sonic) structure. The construction of a tech-tile from an image file or a sound clip and the swarm/attractor dynamics is explained in some detail. A number of experiments report on the sonic textures derived from various images.


Andrew R. Brown

Exploring Rhythmic Automata

The use of Cellular Automata (CA) for musical purposes has a rich history. In general the mapping of CA states to note-level music representations has focused on pitch mapping and downplayed rhythm. This paper reports experiments in the application of one-dimensional cellular automata to the generation and evolution of rhythmic patterns. A selection of CA tendencies are identified that can be used as compositional tools to control the rhythmic coherence of monophonic passages and the polyphonic texture of musical works in broad-brush, rather than precisely deterministic, ways. This will provide the composer and researcher with a clearer understanding of the useful application of CAs for generative music.


John P. Collomosse
Peter M. Hall

Genetic Paint: A Search for Salient Paintings

(Best Paper Award Candidate)
The contribution of this paper is a novel non-photorealistic rendering (NPR) algorithm for rendering real images in an impasto painterly style. We argue that figurative artworks are salience maps, and develop a novel painting algorithm that uses a genetic algorithm (GA) to search the space of possible paintings for a given image, so approaching an “optimal” artwork in which salient detail is conserved and non-salient detail is attenuated. We demonstrate the results of our technique on a wide range of images, illustrating both the improved control over level of detail due to our salience adaptive painting approach, and the benefits gained by subsequent relaxation of the painting using the GA.


Alan Dorin

Artificial Life, Death and Epidemics in Evolutionary, Generative Electronic Art

This paper explores strategies for slowing the onset of convergence in an evolving population of agents. The strategies include the emergent main-tenance of separate agent sub-populations and migration between them, and the introduction of virtual diseases that co-evolve parasitically within their hosts. The method looks to Artificial Life and epidemiology for its inspiration but its ultimate concerns are in studying epidemics as a process suitable for application to generative electronic art. The simulation is used to construct a prototype artwork for a fully interactive stereoscopic virtual-reality environment to be exhibited in a science museum.


Alice C. Eldridge

Extra-Music(ologic)al Models for Algorithmic Composition

This paper addresses design approaches to algorithmic composition and suggests that music-theoretic tenets alone are unsuitable as prescriptive principles and could be profitably complemented by attempts to represent and recreate dynamical structures of music. Examples of ongoing work using adaptive dynamical processes for generating dynamic structures are presented.


Gary Greenfield

Evolutionary Methods for Ant Colony Paintings

We investigate evolutionary methods for using an ant colony optimization model to evolve “ant paintings.” Our model is inspired by the recent work of Monmarché et al. The two critical differences between our model and that of Monmarché’s are: (1) we do not use an interactive genetic algorithm, and (2) we allow the pheromone trail to serve as both a repelling and attracting force. Our results show how different fitness measures induce different artistic “styles” in the evolved paintings. Moreover, we explore the sensitivity of these styles to perturbations of the parameters required by the genetic algorithm. We also discuss the evolution and interaction of various castes within our artificial ant colonies.


Bill Manaris
Penousal Machado
Clayton McCauley
Juan Romero
Dwight Krehbiel

Developing Fitness Functions for Pleasant Music: Zipf? s Law and Interactive Evolution Systems

In domains such as music and visual art, where the quality of an individual often depends on subjective or hardto express concepts, the automating fitness assignment becomes a difficult problem. This paper discusses theapplication of Zipf’s Law in evaluation of music pleasantness. Preliminary results indicate that a set of Zipf-based metrics can be effectively used to classify music according to pleasantness as reported by humansubjects. These studies suggest that metrics based on Zipf’s law may capture essential aspects of proportion inmusic as it relates to music aesthetics. We discuss the significance of these results for the automation offitness assignment in evolutionary music systems.


Eduardo Reck Miranda
John Matthias

Granular Sampling using a Pulse-Coupled Network of Spiking Neurons

We present a new technique for granular sampling using a pulse-coupled network of spiking artificial neurons to generate grain events. The system plays randomly selected sound grains from a given sound sample when any one of a weakly coupled network of up to 1000 neurons fires. The network can exhibit loosely correlated temporal solutions and also collective synchronised behaviour. This leads to very interesting sonic results, particularly with regard to rhythmic textures which can be controlled with various parameters within the model.


Thomas J. Mitchell
Anthony G. Pipe

Convergence Synthesis of Dynamic Frequency Modulation Tones Using an Evolution Strategy

This paper reports on steps that have been taken to enhance previously presented evolutionary sound matching work. In doing so, the convergence characteristics are shown to provide a synthesis method that produces interesting sounds. The method implements an Evolution Strategy to optimise a set of real-valued Frequency Modulation parameters. The development of the evolution is synthesised as optimisation takes place, and the corresponding dynamic sound can be observed developing from initial disorder, into a stable, static tone.


Rafael Ramirez
Amaury Hazan

Understanding Expressive Music Performance Using Genetic Algorithms

In this paper, we describe an approach to learning expressive performance rules from monophonic Jazz standards recordings by a skilled saxophonist. We use a melodic transcription system which extracts a set of acoustic features from the recordings producing a melodic representation of the expressive performance played by the musician. We apply genetic algorithms to this representation in order to induce rules of expressive music performance. The rules collected during different runs of our system are of musical interest and have a good prediction accuracy.


Scott Draves

The Electric Sheep Screen-Saver: A Case Study in Aesthetic Evolution

Electric Sheep is a distributed screen-saver that harnesses idle computers into a render farm with the purpose of animating and evolving artificial life-forms known as sheep. The votes of the users form the basis for the fitness function for a genetic algorithm on a space of fractal animations. Users also may design sheep by hand for inclusion in the gene pool. This paper describes the system and its algorithms, and reports statistics from 11 weeks of operation. The data indicate that Electric Sheep functions more as an amplifier of its human collaborators’ creativity rather than as a traditional genetic algorithm that optimizes a fitness function.


Søren Tjagvad Madsen
Gerhard Widmer

Evolutionary Search for Musical Parallelism

This paper presents an Evolutionary Algorithm used to search for similarities in a music score represented as a graph. We show how the graph can be searched for similarities of different kinds using interchangeable similarity measures based on viewpoints. A segmentation algorithm using the EA for automatically finding structures in a score based on a specific-to-general ordering of the viewpoints is proposed. As an example a fugue by J. S. Bach is analysed, revealing its extensive use of inner resemblance.


Paulo Urbano

Playing in the Pheromone Playground: Experiences in Swarm Painting

This paper is about collective artistic work inspired by natural phenomena, namely the use of pheromone substances for mass recruitment in ants. We will describe two different uncoordinated groups of very simple virtual micro-painters: the Colombines and the Anti-Colombines. These painters have very limited perception abilities and cannot communicate directly with other individuals. The virtual canvas, besides being a computational space for depositing paint, is also a pheromone medium (that mirrors the painting patterns) influencing the painters’ behaviour. Patterns are the emergent result of interaction dynamics involving the micro-painters and their pheromone medium.


Peter Worth
Susan Stepney

Growing Music: musical interpretations of L-Systems

L-systems are parallel generative grammars, used to model plant development, with the results usually interpreted graphically. Music can also be represented by grammars, and it is possible to interpret L-systems musically. We search for simultaneous ’pleasing’ graphical and musical renderings of L-systems.