Evolutionary systems & genetic algorithms

KStanley is not an artist, but his development of the NeuroEvolution of Augmenting Topologies (NEAT) method has been applied to image making by his students. It has also been applied to video games, the control of animation particle systems, and recently the evolutionary training of virtual dancers. The NEAT method evolves a neural network via complexification. I.e. the system starts with a very simple network and then slowly adds more nodes, connections, and weights as it gets closer and closer to the desired solution.

KStanley is not an artist, but his development of the NeuroEvolution of Augmenting Topologies (NEAT) method has been applied to image making by his students. It has also been applied to video games, the control of animation particle systems, and recently the evolutionary training of virtual dancers. The NEAT method evolves a neural network via complexification. I.e. the system starts with a very simple network and then slowly adds more nodes, connections, and weights as it gets closer and closer to the desired solution.

The student evolutionary art project is available as a web-based Java application [http://picbreeder.org/ here]. A website where you can download the video game developed using the NEAT method is available [http://nerogame.org/ here]. Stanley's Ph.D. dissertation which established the NEAT method is available [http://nn.cs.utexas.edu/downloads/papers/stanley.phd04.pdf here], and his web page is [http://www.cs.ucf.edu/~kstanley/ here]. This relatively recent work holds much promise to address the long standing challenge of effectively designing neural networks using evolutionary methods.

The student evolutionary art project is available as a web-based Java application [http://picbreeder.org/ here]. A website where you can download the video game developed using the NEAT method is available [http://nerogame.org/ here]. Stanley's Ph.D. dissertation which established the NEAT method is available [http://nn.cs.utexas.edu/downloads/papers/stanley.phd04.pdf here], and his web page is [http://www.cs.ucf.edu/~kstanley/ here]. This relatively recent work holds much promise to address the long standing challenge of effectively designing neural networks using evolutionary methods.

<span style="font-size:larger">Driessens & Verstappen</span>

<span style="font-size:larger">Driessens & Verstappen</span>

Erwin Driessens and Maria Verstappen have created a number of generative works and some of these have used evolutionary techniques. [http://www.xs4all.nl/~notnot/breed/Breed.html Breed] creates virtual sculptures using genetic programming to manage the evolution of 3D cellular automata-like systems. The virtual sculptures are then rendered as physical objects using rapid prototyping technology. [http://www.xs4all.nl/~notnot/E-volverLUMC/E-volverLUMC.html E-volver] is presented as an interactive "image-breeding-machine. The resulting images have been used to create large prints and screensaver software. The resulting systems are being used in a larger installation called [http://www.xs4all.nl/~notnot/evolvedxxw/evolvedxxw.html E-volved Cultures XXW].

Erwin Driessens and Maria Verstappen have created a number of generative works and some of these have used evolutionary techniques. [http://www.xs4all.nl/~notnot/breed/Breed.html Breed] creates virtual sculptures using genetic programming to manage the evolution of 3D cellular automata-like systems. The virtual sculptures are then rendered as physical objects using rapid prototyping technology. [http://www.xs4all.nl/~notnot/E-volverLUMC/E-volverLUMC.html E-volver] is presented as an interactive "image-breeding-machine. The resulting images have been used to create large prints and screensaver software. The resulting systems are being used in a larger installation called [http://www.xs4all.nl/~notnot/evolvedxxw/evolvedxxw.html E-volved Cultures XXW].

<span style="font-size:larger">Scott "Spot" Draves</span>

<span style="font-size:larger">Scott "Spot" Draves</span>