Compositional pattern producing networks: A novel abstraction of development
Abbreviated Journal Title
Genet. Program. Evol. Mach.
evolutionary computation; representation; developmental encoding; indirect encoding; artificial embryogeny; generative systems; complexity; ARTIFICIAL NEURAL-NETWORKS; INTERACTIVE EVOLUTIONARY COMPUTATION; CELLULAR INTERACTIONS; MATHEMATICAL MODELS; GENES; FILAMENTS; INPUTS; Computer Science, Artificial Intelligence; Computer Science, Theory &; Methods
Natural DNA can encode complexity on an enormous scale. Researchers are attempting to achieve the same representational efficiency in computers by implementing developmental encodings, i.e. encodings that map the genotype to the phenotype through a process of growth from a small starting point to a mature form. A major challenge in in this effort is to find the right level of abstraction of biological development to capture its essential properties without introducing unnecessary inefficiencies. In this paper, a novel abstraction of natural development, called Compositional Pattern Producing Networks (CPPNs), is proposed. Unlike currently accepted abstractions such as iterative rewrite systems and cellular growth simulations, CPPNs map to the phenotype without local interaction, that is, each individual component of the phenotype is determined independently of every other component. Results produced with CPPNs through interactive evolution of two-dimensional images show that such an encoding can nevertheless produce structural motifs often attributed to more conventional developmental abstractions, suggesting that local interaction may not be essential to the desirable properties of natural encoding in the way that is usually assumed.
Genetic Programming and Evolvable Machines
"Compositional pattern producing networks: A novel abstraction of development" (2007). Faculty Bibliography 2000s. 7682.