Compositional pattern producing networks: A novel abstraction of development

    Authors

    K. O. Stanley

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    Genet. Program. Evol. Mach.

    Keywords

    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

    Abstract

    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.

    Journal Title

    Genetic Programming and Evolvable Machines

    Volume

    8

    Issue/Number

    2

    Publication Date

    1-1-2007

    Document Type

    Article

    Language

    English

    First Page

    131

    Last Page

    162

    WOS Identifier

    WOS:000249559100003

    ISSN

    1389-2576

    Share

    COinS