Figure 2 - uploaded by Frederic Fol Leymarie
Content may be subject to copyright.
William Latham uses a grammar of morphological operators and trans-formations to encode the information contained in the "genomes" of his artefacts (Todd, Latham, 1992). An interactive process of selecting successive genomes generates a series of images (here in 3D) based on a process of recombination and mutation of the genes. At each generative step, the artist selects the preferred of these new images to serve as progeny for the next iteration. On the left is shown one outcome of an EvoArt session: PlantForm (© Latham, 1989) and on the right is illustrated one evolutionary step in another session where the central parent, once selected by the artist is used to create 8 new descendants (© Latham, 1991).
Source publication
We analyse works of digital art that use a technique from artificial life (ALife) called computational ecosystems (CEs). These are systems running on computers where agents are organized in a hierarchical structure (of a food-chain) and trade token units (of energy and biomass) as a way of promoting community dynamics. We analyse a collection of fo...
Contexts in source publication
Context 1
... development of computational systems with communities of agents forming ecosystems is a practice with an already established tradition in the artificial life (ALife) community (Dorin, 2005;. Computational ecosystems (CEs) run on computers simulating interactions of individual agents mimicking life in nature (Figures 1 and 2). In a classical CE, agents are organized in a hierarchical structure (of a food-chain) and trade token units (of energy and biomass) as a way to promote community dynamics. ...
Context 2
... complexity of this process of conversion from Gtype to Ptype is open to artistic creativity and the linearity and distance involved in this process of transformation differ widely amongst artists. The diversity of the outcomes this methodology entails is illustrated for example by computational evolutionary art pioneers Latham and Sims: William Latham produces 3D morphologies based on a process of shape deformation (Figure 2), while Karl Sims generates abstract imagery based on a language of mathematical and visual operators (Whitelaw, 2004;Lambert, Latham & Leymarie, 2013). ...
Similar publications
Substantial potential exists to expand supplies of biomass for energy applications through more systematic collection of agricultural residues, more intensive cultivation of croplands, and reduced waste and losses in the food chain. This study aims to show how the potential can be calculated from public information sources, to put the potential in...
Citations
... Evolutionary art is a branch of generative art, which is automatically generated by evolutionary computation. Evolutionary computation can be used to create various artworks, including 2D artworks, 3D artworks, music, and animation artworks [1,2]. The genotype-phenotype algorithms, such as genetic algorithms and many nature-inspired evolution algorithms, are widely used to create evolutionary art [3,4]. ...
We proposed a pixel-based evolution method to automatically generate evolutionary art. Our method can generate diverse artworks, including original artworks and imitating artworks, with different artistic styles and high visual complexity. The generation process is fully automated. In order to adapt to the pixel-based method, a von Neumann neighbor topology-modified particle swarm optimization (PSO) is employed to the proposed method. The fitness functions of PSO are well prepared. Firstly, we come up with a set of aesthetic fitness functions. Next, the imitating fitness function is designed. Finally, the aesthetic fitness functions and the imitating fitness function are weighted into one single object function, which is used in the modified PSO. Both the original outputs and imitating outputs are shown. A questionnaire is designed to investigate the subjective aesthetic feeling of proposed evolutionary art, and the statistics are shown.
... Ecosystemic approaches to evolutionary art are well-established in generative art [4]. While attention is drawn to the creatures of an ecosystem, a key insight is that the depth of their behaviour, (in our view, the invisible connections of visible nodes), are deeply dependent on the qualities of the environment they inhabit. ...
“Infranet” is a generative artwork interweaving data visualization and sonification, artificial intelligence, and evolutionary algorithms in a population of artificial life creatures, thriving upon geospatial data of the infrastructure of a city as its sustenance and canvas. Each exhibit of Infranet utilizes public data available on the host city; including Gwangju, South Korea (2018), New York, USA (2019), and Vancouver, Canada (2019). This paper documents the motivations behind the work, its design and subsequent implementation in details. At its heart is the speculative proposition of the data of a city as a habitat for new forms of life. Our design in response utilizes neural networks at individual, as well as population-wide scales, along with horizontal gene transfer and contagion/entrainment as means for the living beings to open-endedly discover the variety in the data habitat.
... Finally, there is Computer Generative Art where the human intervention is zero or minimal [8]. To this group belong works made with AI like AARON [13] or the Painting Fool [14], evolutionary algorithms [4] or the most recent works by artists like Mario Klingemann, Anna Riddler or Robbie Barrat made using Generative Adversarial Networks (GAN) [30]. In these works, the creative agency of the artificial agent becomes more complex and has the potential to achieve a higher autonomy. ...
Over the past few years, specialised online and offline press blossomed with articles about art made "with" Artificial Intelligence (AI) but the narrative is rapidly changing. In fact, in October 2018, the auction house Christie's sold an art piece allegedly made "by" an AI. We draw from philosophy of art and science arguing that AI as a technical object is always intertwined with human nature despite its level of autonomy. However, the use of creative autonomous agents has cultural and social implications in the way we experience art as creators as well as audience. Therefore, we highlight the importance of an interdisciplinary dialogue by promoting a culture of transparency of the technology used, awareness of the meaning of technology in our society and the value of creativity in our lives.
... There are a couple of issues that will be considered in the future research: (1) As mentioned by [4], introducing other fitness functions to explore the new visual effect of evolved images, especially for more pleasuring texture, is currently under investigation and will be reported later; (2) More alternative evolutionary algorithms based on cloud model may be provided just as or more interesting than result images; thus the extension of the proposed method to improve the performance is well worth further studying on, for example, introducing computational ecosystems [38]. ...
The process of creating nonphotorealistic rendering images and animations can be enjoyable if a useful method is involved. We use an evolutionary algorithm to generate painterly styles of images. Given an input image as the reference target, a cloud model-based evolutionary algorithm that will rerender the target image with nonphotorealistic effects is evolved. The resulting animations have an interesting characteristic in which the target slowly emerges from a set of strokes. A number of experiments are performed, as well as visual comparisons, quantitative comparisons, and user studies. The average scores in normalized feature similarity of standard pixel-wise peak signal-to-noise ratio, mean structural similarity, feature similarity, and gradient similarity based metric are 0.486, 0.628, 0.579, and 0.640, respectively. The average scores in normalized aesthetic measures of Benford’s law, fractal dimension, global contrast factor, and Shannon’s entropy are 0.630, 0.397, 0.418, and 0.708, respectively. Compared with those of similar method, the average score of the proposed method, except peak signal-to-noise ratio, is higher by approximately 10%. The results suggest that the proposed method can generate appealing images and animations with different styles by choosing different strokes, and it would inspire graphic designers who may be interested in computer-based evolutionary art.
This article discusses the challenges in creating Mutator VR: Vortex, a virtual reality experience based on interaction with semi-autonomous, organically inspired agents. The work allows the immersant to morph between a vast number of procedurally-generated microworlds, each with its own visual elements, sounds, agent dynamics, and user interactions. We outline two methods used for procedural generation that are based fundamentally on integration of different modalities. Curve-based synthesis is used for simultaneous generation of entity sounds and shape and flow grains are employed to determine both agent dynamics and user interaction with the agents.
In this paper, we examine virtual ecosystems as general-purpose authoring tools for heterogeneity and spontaneity, and discuss the use of such systems as animation drivers in a variety of contexts: from artistic abstract work, to dance choreographies, or even in the simulation of historical spaces. First, we present the background, motivation and summary for the project. Then, we discuss the use of these systems in the artworks Senhora da Graça, xTNZ, Where is Lourenço Marques?, in the dance choreography, Vishnu's Dance of Life and Death, and in the simulation of the population of the medieval village of Mértola. This emphasizes how an artistic practice informs a movement of transition, taking us from the use of artefacts that mostly rely on their traditionally associated eco-narratives to functional tool generators of diversity and heterogeneity. Finally, we close the article to contend that these systems function as utilitarian authoring tools for multi-contextual purposes.
In this paper, we propose a multi-agent based art production framework. In existing artwork creation systems, images were generated using artificial life and evolutionary computation approaches. In artificial life, swarm intelligence or Boids model, and in evolutionary computation, genetic algorithm or genetic programming are commonly used to create images. These automated artwork creation systems make it easy to create artistic images even if the users are not professional artists. Despite the high possibility of these creation systems, however, much research has not been done so far. In this paper, we propose an art production framework that generates images using multi-agents with chaotic dynamics features. Agents act on the canvas following the three rules of Boids model. In addition, each agent possesses a chaotic neural network which trained by differential evolution algorithm, so that colors can be evolved to represent a better style. As a result, we propose an art production framework for generating processing artworks that contain highly complex dynamics. Finally, we created the glitch artworks using the proposed framework, which shows a new glitch style.
Since 2007, Graham Wakefield and Haru Ji have looked to nature for inspiration as they have created a series of "artificial natures," or interactive visualizations of biologically inspired complex systems that can evoke nature-like aesthetic experiences within mixed-reality art installations. This article describes how they have applied visualization, sonification, and interaction design in their work with artificial ecosystems and organisms using specific examples from their exhibited installations.
We study the use of the generative systems known as computational ecosystems to convey artistic and narrative aims. These are virtual worlds running on computers, composed of agents that trade units of energy and emulate cycles of life and behaviors adapted from biological life forms. In this article we propose a conceptual framework in order to understand these systems, which are involved in processes of authorship and interpretation that this investigation analyzes in order to identify critical instruments for artistic exploration. We formulate a model of narrative that we call system stories (after Mitchell Whitelaw), characterized by the dynamic network of material and conceptual processes that define these artefacts. They account for narrative constellations with multiple agencies from which meaning and messages emerge. Finally, we present three case studies to explore the potential of this model within an artistic and generative domain, arguing that this understanding expands and enriches the palette of the language of these systems.
For millennia people have wondered what makes the living different from the non-living. Beginning in the mid-1980s, artificial life has studied living systems using a synthetic approach: build life in order to understand it better, be it by means of software, hardware, or wetware. This review provides a summary of the advances that led to the development of artificial life, its current research topics, and open problems and opportunities. We classify artificial life research into 14 themes: origins of life, autonomy, self-organization, adaptation (including evolution, development, and learning), ecology, artificial societies, behavior, computational biology, artificial chemistries, information, living technology, art, and philosophy. Being interdisciplinary, artificial life seems to be losing its boundaries and merging with other fields
